Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+DiCo-XL-256/demo.png filter=lfs diff=lfs merge=lfs -text

DiCo-B-256/model_index.json

@@ -0,0 +1,1021 @@
+{
+  "_class_name": [
+    "pipeline",
+    "DiCoPipeline"
+  ],
+  "_diffusers_version": "0.38.0",
+  "scheduler": [
+    "diffusers",
+    "DDIMScheduler"
+  ],
+  "transformer": [
+    "transformer_dico",
+    "DiCoTransformer2DModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ],
+  "id2label": {
+    "0": "tench, Tinca tinca",
+    "1": "goldfish, Carassius auratus",
+    "2": "great white shark, white shark, man-eater, man-eating shark, Carcharodon carcharias",
+    "3": "tiger shark, Galeocerdo cuvieri",
+    "4": "hammerhead, hammerhead shark",
+    "5": "electric ray, crampfish, numbfish, torpedo",
+    "6": "stingray",
+    "7": "cock",
+    "8": "hen",
+    "9": "ostrich, Struthio camelus",
+    "10": "brambling, Fringilla montifringilla",
+    "11": "goldfinch, Carduelis carduelis",
+    "12": "house finch, linnet, Carpodacus mexicanus",
+    "13": "junco, snowbird",
+    "14": "indigo bunting, indigo finch, indigo bird, Passerina cyanea",
+    "15": "robin, American robin, Turdus migratorius",
+    "16": "bulbul",
+    "17": "jay",
+    "18": "magpie",
+    "19": "chickadee",
+    "20": "water ouzel, dipper",
+    "21": "kite",
+    "22": "bald eagle, American eagle, Haliaeetus leucocephalus",
+    "23": "vulture",
+    "24": "great grey owl, great gray owl, Strix nebulosa",
+    "25": "European fire salamander, Salamandra salamandra",
+    "26": "common newt, Triturus vulgaris",
+    "27": "eft",
+    "28": "spotted salamander, Ambystoma maculatum",
+    "29": "axolotl, mud puppy, Ambystoma mexicanum",
+    "30": "bullfrog, Rana catesbeiana",
+    "31": "tree frog, tree-frog",
+    "32": "tailed frog, bell toad, ribbed toad, tailed toad, Ascaphus trui",
+    "33": "loggerhead, loggerhead turtle, Caretta caretta",
+    "34": "leatherback turtle, leatherback, leathery turtle, Dermochelys coriacea",
+    "35": "mud turtle",
+    "36": "terrapin",
+    "37": "box turtle, box tortoise",
+    "38": "banded gecko",
+    "39": "common iguana, iguana, Iguana iguana",
+    "40": "American chameleon, anole, Anolis carolinensis",
+    "41": "whiptail, whiptail lizard",
+    "42": "agama",
+    "43": "frilled lizard, Chlamydosaurus kingi",
+    "44": "alligator lizard",
+    "45": "Gila monster, Heloderma suspectum",
+    "46": "green lizard, Lacerta viridis",
+    "47": "African chameleon, Chamaeleo chamaeleon",
+    "48": "Komodo dragon, Komodo lizard, dragon lizard, giant lizard, Varanus komodoensis",
+    "49": "African crocodile, Nile crocodile, Crocodylus niloticus",
+    "50": "American alligator, Alligator mississipiensis",
+    "51": "triceratops",
+    "52": "thunder snake, worm snake, Carphophis amoenus",
+    "53": "ringneck snake, ring-necked snake, ring snake",
+    "54": "hognose snake, puff adder, sand viper",
+    "55": "green snake, grass snake",
+    "56": "king snake, kingsnake",
+    "57": "garter snake, grass snake",
+    "58": "water snake",
+    "59": "vine snake",
+    "60": "night snake, Hypsiglena torquata",
+    "61": "boa constrictor, Constrictor constrictor",
+    "62": "rock python, rock snake, Python sebae",
+    "63": "Indian cobra, Naja naja",
+    "64": "green mamba",
+    "65": "sea snake",
+    "66": "horned viper, cerastes, sand viper, horned asp, Cerastes cornutus",
+    "67": "diamondback, diamondback rattlesnake, Crotalus adamanteus",
+    "68": "sidewinder, horned rattlesnake, Crotalus cerastes",
+    "69": "trilobite",
+    "70": "harvestman, daddy longlegs, Phalangium opilio",
+    "71": "scorpion",
+    "72": "black and gold garden spider, Argiope aurantia",
+    "73": "barn spider, Araneus cavaticus",
+    "74": "garden spider, Aranea diademata",
+    "75": "black widow, Latrodectus mactans",
+    "76": "tarantula",
+    "77": "wolf spider, hunting spider",
+    "78": "tick",
+    "79": "centipede",
+    "80": "black grouse",
+    "81": "ptarmigan",
+    "82": "ruffed grouse, partridge, Bonasa umbellus",
+    "83": "prairie chicken, prairie grouse, prairie fowl",
+    "84": "peacock",
+    "85": "quail",
+    "86": "partridge",
+    "87": "African grey, African gray, Psittacus erithacus",
+    "88": "macaw",
+    "89": "sulphur-crested cockatoo, Kakatoe galerita, Cacatua galerita",
+    "90": "lorikeet",
+    "91": "coucal",
+    "92": "bee eater",
+    "93": "hornbill",
+    "94": "hummingbird",
+    "95": "jacamar",
+    "96": "toucan",
+    "97": "drake",
+    "98": "red-breasted merganser, Mergus serrator",
+    "99": "goose",
+    "100": "black swan, Cygnus atratus",
+    "101": "tusker",
+    "102": "echidna, spiny anteater, anteater",
+    "103": "platypus, duckbill, duckbilled platypus, duck-billed platypus, Ornithorhynchus anatinus",
+    "104": "wallaby, brush kangaroo",
+    "105": "koala, koala bear, kangaroo bear, native bear, Phascolarctos cinereus",
+    "106": "wombat",
+    "107": "jellyfish",
+    "108": "sea anemone, anemone",
+    "109": "brain coral",
+    "110": "flatworm, platyhelminth",
+    "111": "nematode, nematode worm, roundworm",
+    "112": "conch",
+    "113": "snail",
+    "114": "slug",
+    "115": "sea slug, nudibranch",
+    "116": "chiton, coat-of-mail shell, sea cradle, polyplacophore",
+    "117": "chambered nautilus, pearly nautilus, nautilus",
+    "118": "Dungeness crab, Cancer magister",
+    "119": "rock crab, Cancer irroratus",
+    "120": "fiddler crab",
+    "121": "king crab, Alaska crab, Alaskan king crab, Alaska king crab, Paralithodes camtschatica",
+    "122": "American lobster, Northern lobster, Maine lobster, Homarus americanus",
+    "123": "spiny lobster, langouste, rock lobster, crawfish, crayfish, sea crawfish",
+    "124": "crayfish, crawfish, crawdad, crawdaddy",
+    "125": "hermit crab",
+    "126": "isopod",
+    "127": "white stork, Ciconia ciconia",
+    "128": "black stork, Ciconia nigra",
+    "129": "spoonbill",
+    "130": "flamingo",
+    "131": "little blue heron, Egretta caerulea",
+    "132": "American egret, great white heron, Egretta albus",
+    "133": "bittern",
+    "134": "crane",
+    "135": "limpkin, Aramus pictus",
+    "136": "European gallinule, Porphyrio porphyrio",
+    "137": "American coot, marsh hen, mud hen, water hen, Fulica americana",
+    "138": "bustard",
+    "139": "ruddy turnstone, Arenaria interpres",
+    "140": "red-backed sandpiper, dunlin, Erolia alpina",
+    "141": "redshank, Tringa totanus",
+    "142": "dowitcher",
+    "143": "oystercatcher, oyster catcher",
+    "144": "pelican",
+    "145": "king penguin, Aptenodytes patagonica",
+    "146": "albatross, mollymawk",
+    "147": "grey whale, gray whale, devilfish, Eschrichtius gibbosus, Eschrichtius robustus",
+    "148": "killer whale, killer, orca, grampus, sea wolf, Orcinus orca",
+    "149": "dugong, Dugong dugon",
+    "150": "sea lion",
+    "151": "Chihuahua",
+    "152": "Japanese spaniel",
+    "153": "Maltese dog, Maltese terrier, Maltese",
+    "154": "Pekinese, Pekingese, Peke",
+    "155": "Shih-Tzu",
+    "156": "Blenheim spaniel",
+    "157": "papillon",
+    "158": "toy terrier",
+    "159": "Rhodesian ridgeback",
+    "160": "Afghan hound, Afghan",
+    "161": "basset, basset hound",
+    "162": "beagle",
+    "163": "bloodhound, sleuthhound",
+    "164": "bluetick",
+    "165": "black-and-tan coonhound",
+    "166": "Walker hound, Walker foxhound",
+    "167": "English foxhound",
+    "168": "redbone",
+    "169": "borzoi, Russian wolfhound",
+    "170": "Irish wolfhound",
+    "171": "Italian greyhound",
+    "172": "whippet",
+    "173": "Ibizan hound, Ibizan Podenco",
+    "174": "Norwegian elkhound, elkhound",
+    "175": "otterhound, otter hound",
+    "176": "Saluki, gazelle hound",
+    "177": "Scottish deerhound, deerhound",
+    "178": "Weimaraner",
+    "179": "Staffordshire bullterrier, Staffordshire bull terrier",
+    "180": "American Staffordshire terrier, Staffordshire terrier, American pit bull terrier, pit bull terrier",
+    "181": "Bedlington terrier",
+    "182": "Border terrier",
+    "183": "Kerry blue terrier",
+    "184": "Irish terrier",
+    "185": "Norfolk terrier",
+    "186": "Norwich terrier",
+    "187": "Yorkshire terrier",
+    "188": "wire-haired fox terrier",
+    "189": "Lakeland terrier",
+    "190": "Sealyham terrier, Sealyham",
+    "191": "Airedale, Airedale terrier",
+    "192": "cairn, cairn terrier",
+    "193": "Australian terrier",
+    "194": "Dandie Dinmont, Dandie Dinmont terrier",
+    "195": "Boston bull, Boston terrier",
+    "196": "miniature schnauzer",
+    "197": "giant schnauzer",
+    "198": "standard schnauzer",
+    "199": "Scotch terrier, Scottish terrier, Scottie",
+    "200": "Tibetan terrier, chrysanthemum dog",
+    "201": "silky terrier, Sydney silky",
+    "202": "soft-coated wheaten terrier",
+    "203": "West Highland white terrier",
+    "204": "Lhasa, Lhasa apso",
+    "205": "flat-coated retriever",
+    "206": "curly-coated retriever",
+    "207": "golden retriever",
+    "208": "Labrador retriever",
+    "209": "Chesapeake Bay retriever",
+    "210": "German short-haired pointer",
+    "211": "vizsla, Hungarian pointer",
+    "212": "English setter",
+    "213": "Irish setter, red setter",
+    "214": "Gordon setter",
+    "215": "Brittany spaniel",
+    "216": "clumber, clumber spaniel",
+    "217": "English springer, English springer spaniel",
+    "218": "Welsh springer spaniel",
+    "219": "cocker spaniel, English cocker spaniel, cocker",
+    "220": "Sussex spaniel",
+    "221": "Irish water spaniel",
+    "222": "kuvasz",
+    "223": "schipperke",
+    "224": "groenendael",
+    "225": "malinois",
+    "226": "briard",
+    "227": "kelpie",
+    "228": "komondor",
+    "229": "Old English sheepdog, bobtail",
+    "230": "Shetland sheepdog, Shetland sheep dog, Shetland",
+    "231": "collie",
+    "232": "Border collie",
+    "233": "Bouvier des Flandres, Bouviers des Flandres",
+    "234": "Rottweiler",
+    "235": "German shepherd, German shepherd dog, German police dog, alsatian",
+    "236": "Doberman, Doberman pinscher",
+    "237": "miniature pinscher",
+    "238": "Greater Swiss Mountain dog",
+    "239": "Bernese mountain dog",
+    "240": "Appenzeller",
+    "241": "EntleBucher",
+    "242": "boxer",
+    "243": "bull mastiff",
+    "244": "Tibetan mastiff",
+    "245": "French bulldog",
+    "246": "Great Dane",
+    "247": "Saint Bernard, St Bernard",
+    "248": "Eskimo dog, husky",
+    "249": "malamute, malemute, Alaskan malamute",
+    "250": "Siberian husky",
+    "251": "dalmatian, coach dog, carriage dog",
+    "252": "affenpinscher, monkey pinscher, monkey dog",
+    "253": "basenji",
+    "254": "pug, pug-dog",
+    "255": "Leonberg",
+    "256": "Newfoundland, Newfoundland dog",
+    "257": "Great Pyrenees",
+    "258": "Samoyed, Samoyede",
+    "259": "Pomeranian",
+    "260": "chow, chow chow",
+    "261": "keeshond",
+    "262": "Brabancon griffon",
+    "263": "Pembroke, Pembroke Welsh corgi",
+    "264": "Cardigan, Cardigan Welsh corgi",
+    "265": "toy poodle",
+    "266": "miniature poodle",
+    "267": "standard poodle",
+    "268": "Mexican hairless",
+    "269": "timber wolf, grey wolf, gray wolf, Canis lupus",
+    "270": "white wolf, Arctic wolf, Canis lupus tundrarum",
+    "271": "red wolf, maned wolf, Canis rufus, Canis niger",
+    "272": "coyote, prairie wolf, brush wolf, Canis latrans",
+    "273": "dingo, warrigal, warragal, Canis dingo",
+    "274": "dhole, Cuon alpinus",
+    "275": "African hunting dog, hyena dog, Cape hunting dog, Lycaon pictus",
+    "276": "hyena, hyaena",
+    "277": "red fox, Vulpes vulpes",
+    "278": "kit fox, Vulpes macrotis",
+    "279": "Arctic fox, white fox, Alopex lagopus",
+    "280": "grey fox, gray fox, Urocyon cinereoargenteus",
+    "281": "tabby, tabby cat",
+    "282": "tiger cat",
+    "283": "Persian cat",
+    "284": "Siamese cat, Siamese",
+    "285": "Egyptian cat",
+    "286": "cougar, puma, catamount, mountain lion, painter, panther, Felis concolor",
+    "287": "lynx, catamount",
+    "288": "leopard, Panthera pardus",
+    "289": "snow leopard, ounce, Panthera uncia",
+    "290": "jaguar, panther, Panthera onca, Felis onca",
+    "291": "lion, king of beasts, Panthera leo",
+    "292": "tiger, Panthera tigris",
+    "293": "cheetah, chetah, Acinonyx jubatus",
+    "294": "brown bear, bruin, Ursus arctos",
+    "295": "American black bear, black bear, Ursus americanus, Euarctos americanus",
+    "296": "ice bear, polar bear, Ursus Maritimus, Thalarctos maritimus",
+    "297": "sloth bear, Melursus ursinus, Ursus ursinus",
+    "298": "mongoose",
+    "299": "meerkat, mierkat",
+    "300": "tiger beetle",
+    "301": "ladybug, ladybeetle, lady beetle, ladybird, ladybird beetle",
+    "302": "ground beetle, carabid beetle",
+    "303": "long-horned beetle, longicorn, longicorn beetle",
+    "304": "leaf beetle, chrysomelid",
+    "305": "dung beetle",
+    "306": "rhinoceros beetle",
+    "307": "weevil",
+    "308": "fly",
+    "309": "bee",
+    "310": "ant, emmet, pismire",
+    "311": "grasshopper, hopper",
+    "312": "cricket",
+    "313": "walking stick, walkingstick, stick insect",
+    "314": "cockroach, roach",
+    "315": "mantis, mantid",
+    "316": "cicada, cicala",
+    "317": "leafhopper",
+    "318": "lacewing, lacewing fly",
+    "319": "dragonfly, darning needle, devils darning needle, sewing needle, snake feeder, snake doctor, mosquito hawk, skeeter hawk",
+    "320": "damselfly",
+    "321": "admiral",
+    "322": "ringlet, ringlet butterfly",
+    "323": "monarch, monarch butterfly, milkweed butterfly, Danaus plexippus",
+    "324": "cabbage butterfly",
+    "325": "sulphur butterfly, sulfur butterfly",
+    "326": "lycaenid, lycaenid butterfly",
+    "327": "starfish, sea star",
+    "328": "sea urchin",
+    "329": "sea cucumber, holothurian",
+    "330": "wood rabbit, cottontail, cottontail rabbit",
+    "331": "hare",
+    "332": "Angora, Angora rabbit",
+    "333": "hamster",
+    "334": "porcupine, hedgehog",
+    "335": "fox squirrel, eastern fox squirrel, Sciurus niger",
+    "336": "marmot",
+    "337": "beaver",
+    "338": "guinea pig, Cavia cobaya",
+    "339": "sorrel",
+    "340": "zebra",
+    "341": "hog, pig, grunter, squealer, Sus scrofa",
+    "342": "wild boar, boar, Sus scrofa",
+    "343": "warthog",
+    "344": "hippopotamus, hippo, river horse, Hippopotamus amphibius",
+    "345": "ox",
+    "346": "water buffalo, water ox, Asiatic buffalo, Bubalus bubalis",
+    "347": "bison",
+    "348": "ram, tup",
+    "349": "bighorn, bighorn sheep, cimarron, Rocky Mountain bighorn, Rocky Mountain sheep, Ovis canadensis",
+    "350": "ibex, Capra ibex",
+    "351": "hartebeest",
+    "352": "impala, Aepyceros melampus",
+    "353": "gazelle",
+    "354": "Arabian camel, dromedary, Camelus dromedarius",
+    "355": "llama",
+    "356": "weasel",
+    "357": "mink",
+    "358": "polecat, fitch, foulmart, foumart, Mustela putorius",
+    "359": "black-footed ferret, ferret, Mustela nigripes",
+    "360": "otter",
+    "361": "skunk, polecat, wood pussy",
+    "362": "badger",
+    "363": "armadillo",
+    "364": "three-toed sloth, ai, Bradypus tridactylus",
+    "365": "orangutan, orang, orangutang, Pongo pygmaeus",
+    "366": "gorilla, Gorilla gorilla",
+    "367": "chimpanzee, chimp, Pan troglodytes",
+    "368": "gibbon, Hylobates lar",
+    "369": "siamang, Hylobates syndactylus, Symphalangus syndactylus",
+    "370": "guenon, guenon monkey",
+    "371": "patas, hussar monkey, Erythrocebus patas",
+    "372": "baboon",
+    "373": "macaque",
+    "374": "langur",
+    "375": "colobus, colobus monkey",
+    "376": "proboscis monkey, Nasalis larvatus",
+    "377": "marmoset",
+    "378": "capuchin, ringtail, Cebus capucinus",
+    "379": "howler monkey, howler",
+    "380": "titi, titi monkey",
+    "381": "spider monkey, Ateles geoffroyi",
+    "382": "squirrel monkey, Saimiri sciureus",
+    "383": "Madagascar cat, ring-tailed lemur, Lemur catta",
+    "384": "indri, indris, Indri indri, Indri brevicaudatus",
+    "385": "Indian elephant, Elephas maximus",
+    "386": "African elephant, Loxodonta africana",
+    "387": "lesser panda, red panda, panda, bear cat, cat bear, Ailurus fulgens",
+    "388": "giant panda, panda, panda bear, coon bear, Ailuropoda melanoleuca",
+    "389": "barracouta, snoek",
+    "390": "eel",
+    "391": "coho, cohoe, coho salmon, blue jack, silver salmon, Oncorhynchus kisutch",
+    "392": "rock beauty, Holocanthus tricolor",
+    "393": "anemone fish",
+    "394": "sturgeon",
+    "395": "gar, garfish, garpike, billfish, Lepisosteus osseus",
+    "396": "lionfish",
+    "397": "puffer, pufferfish, blowfish, globefish",
+    "398": "abacus",
+    "399": "abaya",
+    "400": "academic gown, academic robe, judge robe",
+    "401": "accordion, piano accordion, squeeze box",
+    "402": "acoustic guitar",
+    "403": "aircraft carrier, carrier, flattop, attack aircraft carrier",
+    "404": "airliner",
+    "405": "airship, dirigible",
+    "406": "altar",
+    "407": "ambulance",
+    "408": "amphibian, amphibious vehicle",
+    "409": "analog clock",
+    "410": "apiary, bee house",
+    "411": "apron",
+    "412": "ashcan, trash can, garbage can, wastebin, ash bin, ash-bin, ashbin, dustbin, trash barrel, trash bin",
+    "413": "assault rifle, assault gun",
+    "414": "backpack, back pack, knapsack, packsack, rucksack, haversack",
+    "415": "bakery, bakeshop, bakehouse",
+    "416": "balance beam, beam",
+    "417": "balloon",
+    "418": "ballpoint, ballpoint pen, ballpen, Biro",
+    "419": "Band Aid",
+    "420": "banjo",
+    "421": "bannister, banister, balustrade, balusters, handrail",
+    "422": "barbell",
+    "423": "barber chair",
+    "424": "barbershop",
+    "425": "barn",
+    "426": "barometer",
+    "427": "barrel, cask",
+    "428": "barrow, garden cart, lawn cart, wheelbarrow",
+    "429": "baseball",
+    "430": "basketball",
+    "431": "bassinet",
+    "432": "bassoon",
+    "433": "bathing cap, swimming cap",
+    "434": "bath towel",
+    "435": "bathtub, bathing tub, bath, tub",
+    "436": "beach wagon, station wagon, wagon, estate car, beach waggon, station waggon, waggon",
+    "437": "beacon, lighthouse, beacon light, pharos",
+    "438": "beaker",
+    "439": "bearskin, busby, shako",
+    "440": "beer bottle",
+    "441": "beer glass",
+    "442": "bell cote, bell cot",
+    "443": "bib",
+    "444": "bicycle-built-for-two, tandem bicycle, tandem",
+    "445": "bikini, two-piece",
+    "446": "binder, ring-binder",
+    "447": "binoculars, field glasses, opera glasses",
+    "448": "birdhouse",
+    "449": "boathouse",
+    "450": "bobsled, bobsleigh, bob",
+    "451": "bolo tie, bolo, bola tie, bola",
+    "452": "bonnet, poke bonnet",
+    "453": "bookcase",
+    "454": "bookshop, bookstore, bookstall",
+    "455": "bottlecap",
+    "456": "bow",
+    "457": "bow tie, bow-tie, bowtie",
+    "458": "brass, memorial tablet, plaque",
+    "459": "brassiere, bra, bandeau",
+    "460": "breakwater, groin, groyne, mole, bulwark, seawall, jetty",
+    "461": "breastplate, aegis, egis",
+    "462": "broom",
+    "463": "bucket, pail",
+    "464": "buckle",
+    "465": "bulletproof vest",
+    "466": "bullet train, bullet",
+    "467": "butcher shop, meat market",
+    "468": "cab, hack, taxi, taxicab",
+    "469": "caldron, cauldron",
+    "470": "candle, taper, wax light",
+    "471": "cannon",
+    "472": "canoe",
+    "473": "can opener, tin opener",
+    "474": "cardigan",
+    "475": "car mirror",
+    "476": "carousel, carrousel, merry-go-round, roundabout, whirligig",
+    "477": "carpenters kit, tool kit",
+    "478": "carton",
+    "479": "car wheel",
+    "480": "cash machine, cash dispenser, automated teller machine, automatic teller machine, automated teller, automatic teller, ATM",
+    "481": "cassette",
+    "482": "cassette player",
+    "483": "castle",
+    "484": "catamaran",
+    "485": "CD player",
+    "486": "cello, violoncello",
+    "487": "cellular telephone, cellular phone, cellphone, cell, mobile phone",
+    "488": "chain",
+    "489": "chainlink fence",
+    "490": "chain mail, ring mail, mail, chain armor, chain armour, ring armor, ring armour",
+    "491": "chain saw, chainsaw",
+    "492": "chest",
+    "493": "chiffonier, commode",
+    "494": "chime, bell, gong",
+    "495": "china cabinet, china closet",
+    "496": "Christmas stocking",
+    "497": "church, church building",
+    "498": "cinema, movie theater, movie theatre, movie house, picture palace",
+    "499": "cleaver, meat cleaver, chopper",
+    "500": "cliff dwelling",
+    "501": "cloak",
+    "502": "clog, geta, patten, sabot",
+    "503": "cocktail shaker",
+    "504": "coffee mug",
+    "505": "coffeepot",
+    "506": "coil, spiral, volute, whorl, helix",
+    "507": "combination lock",
+    "508": "computer keyboard, keypad",
+    "509": "confectionery, confectionary, candy store",
+    "510": "container ship, containership, container vessel",
+    "511": "convertible",
+    "512": "corkscrew, bottle screw",
+    "513": "cornet, horn, trumpet, trump",
+    "514": "cowboy boot",
+    "515": "cowboy hat, ten-gallon hat",
+    "516": "cradle",
+    "517": "crane",
+    "518": "crash helmet",
+    "519": "crate",
+    "520": "crib, cot",
+    "521": "Crock Pot",
+    "522": "croquet ball",
+    "523": "crutch",
+    "524": "cuirass",
+    "525": "dam, dike, dyke",
+    "526": "desk",
+    "527": "desktop computer",
+    "528": "dial telephone, dial phone",
+    "529": "diaper, nappy, napkin",
+    "530": "digital clock",
+    "531": "digital watch",
+    "532": "dining table, board",
+    "533": "dishrag, dishcloth",
+    "534": "dishwasher, dish washer, dishwashing machine",
+    "535": "disk brake, disc brake",
+    "536": "dock, dockage, docking facility",
+    "537": "dogsled, dog sled, dog sleigh",
+    "538": "dome",
+    "539": "doormat, welcome mat",
+    "540": "drilling platform, offshore rig",
+    "541": "drum, membranophone, tympan",
+    "542": "drumstick",
+    "543": "dumbbell",
+    "544": "Dutch oven",
+    "545": "electric fan, blower",
+    "546": "electric guitar",
+    "547": "electric locomotive",
+    "548": "entertainment center",
+    "549": "envelope",
+    "550": "espresso maker",
+    "551": "face powder",
+    "552": "feather boa, boa",
+    "553": "file, file cabinet, filing cabinet",
+    "554": "fireboat",
+    "555": "fire engine, fire truck",
+    "556": "fire screen, fireguard",
+    "557": "flagpole, flagstaff",
+    "558": "flute, transverse flute",
+    "559": "folding chair",
+    "560": "football helmet",
+    "561": "forklift",
+    "562": "fountain",
+    "563": "fountain pen",
+    "564": "four-poster",
+    "565": "freight car",
+    "566": "French horn, horn",
+    "567": "frying pan, frypan, skillet",
+    "568": "fur coat",
+    "569": "garbage truck, dustcart",
+    "570": "gasmask, respirator, gas helmet",
+    "571": "gas pump, gasoline pump, petrol pump, island dispenser",
+    "572": "goblet",
+    "573": "go-kart",
+    "574": "golf ball",
+    "575": "golfcart, golf cart",
+    "576": "gondola",
+    "577": "gong, tam-tam",
+    "578": "gown",
+    "579": "grand piano, grand",
+    "580": "greenhouse, nursery, glasshouse",
+    "581": "grille, radiator grille",
+    "582": "grocery store, grocery, food market, market",
+    "583": "guillotine",
+    "584": "hair slide",
+    "585": "hair spray",
+    "586": "half track",
+    "587": "hammer",
+    "588": "hamper",
+    "589": "hand blower, blow dryer, blow drier, hair dryer, hair drier",
+    "590": "hand-held computer, hand-held microcomputer",
+    "591": "handkerchief, hankie, hanky, hankey",
+    "592": "hard disc, hard disk, fixed disk",
+    "593": "harmonica, mouth organ, harp, mouth harp",
+    "594": "harp",
+    "595": "harvester, reaper",
+    "596": "hatchet",
+    "597": "holster",
+    "598": "home theater, home theatre",
+    "599": "honeycomb",
+    "600": "hook, claw",
+    "601": "hoopskirt, crinoline",
+    "602": "horizontal bar, high bar",
+    "603": "horse cart, horse-cart",
+    "604": "hourglass",
+    "605": "iPod",
+    "606": "iron, smoothing iron",
+    "607": "jack-o-lantern",
+    "608": "jean, blue jean, denim",
+    "609": "jeep, landrover",
+    "610": "jersey, T-shirt, tee shirt",
+    "611": "jigsaw puzzle",
+    "612": "jinrikisha, ricksha, rickshaw",
+    "613": "joystick",
+    "614": "kimono",
+    "615": "knee pad",
+    "616": "knot",
+    "617": "lab coat, laboratory coat",
+    "618": "ladle",
+    "619": "lampshade, lamp shade",
+    "620": "laptop, laptop computer",
+    "621": "lawn mower, mower",
+    "622": "lens cap, lens cover",
+    "623": "letter opener, paper knife, paperknife",
+    "624": "library",
+    "625": "lifeboat",
+    "626": "lighter, light, igniter, ignitor",
+    "627": "limousine, limo",
+    "628": "liner, ocean liner",
+    "629": "lipstick, lip rouge",
+    "630": "Loafer",
+    "631": "lotion",
+    "632": "loudspeaker, speaker, speaker unit, loudspeaker system, speaker system",
+    "633": "loupe, jewelers loupe",
+    "634": "lumbermill, sawmill",
+    "635": "magnetic compass",
+    "636": "mailbag, postbag",
+    "637": "mailbox, letter box",
+    "638": "maillot",
+    "639": "maillot, tank suit",
+    "640": "manhole cover",
+    "641": "maraca",
+    "642": "marimba, xylophone",
+    "643": "mask",
+    "644": "matchstick",
+    "645": "maypole",
+    "646": "maze, labyrinth",
+    "647": "measuring cup",
+    "648": "medicine chest, medicine cabinet",
+    "649": "megalith, megalithic structure",
+    "650": "microphone, mike",
+    "651": "microwave, microwave oven",
+    "652": "military uniform",
+    "653": "milk can",
+    "654": "minibus",
+    "655": "miniskirt, mini",
+    "656": "minivan",
+    "657": "missile",
+    "658": "mitten",
+    "659": "mixing bowl",
+    "660": "mobile home, manufactured home",
+    "661": "Model T",
+    "662": "modem",
+    "663": "monastery",
+    "664": "monitor",
+    "665": "moped",
+    "666": "mortar",
+    "667": "mortarboard",
+    "668": "mosque",
+    "669": "mosquito net",
+    "670": "motor scooter, scooter",
+    "671": "mountain bike, all-terrain bike, off-roader",
+    "672": "mountain tent",
+    "673": "mouse, computer mouse",
+    "674": "mousetrap",
+    "675": "moving van",
+    "676": "muzzle",
+    "677": "nail",
+    "678": "neck brace",
+    "679": "necklace",
+    "680": "nipple",
+    "681": "notebook, notebook computer",
+    "682": "obelisk",
+    "683": "oboe, hautboy, hautbois",
+    "684": "ocarina, sweet potato",
+    "685": "odometer, hodometer, mileometer, milometer",
+    "686": "oil filter",
+    "687": "organ, pipe organ",
+    "688": "oscilloscope, scope, cathode-ray oscilloscope, CRO",
+    "689": "overskirt",
+    "690": "oxcart",
+    "691": "oxygen mask",
+    "692": "packet",
+    "693": "paddle, boat paddle",
+    "694": "paddlewheel, paddle wheel",
+    "695": "padlock",
+    "696": "paintbrush",
+    "697": "pajama, pyjama, pjs, jammies",
+    "698": "palace",
+    "699": "panpipe, pandean pipe, syrinx",
+    "700": "paper towel",
+    "701": "parachute, chute",
+    "702": "parallel bars, bars",
+    "703": "park bench",
+    "704": "parking meter",
+    "705": "passenger car, coach, carriage",
+    "706": "patio, terrace",
+    "707": "pay-phone, pay-station",
+    "708": "pedestal, plinth, footstall",
+    "709": "pencil box, pencil case",
+    "710": "pencil sharpener",
+    "711": "perfume, essence",
+    "712": "Petri dish",
+    "713": "photocopier",
+    "714": "pick, plectrum, plectron",
+    "715": "pickelhaube",
+    "716": "picket fence, paling",
+    "717": "pickup, pickup truck",
+    "718": "pier",
+    "719": "piggy bank, penny bank",
+    "720": "pill bottle",
+    "721": "pillow",
+    "722": "ping-pong ball",
+    "723": "pinwheel",
+    "724": "pirate, pirate ship",
+    "725": "pitcher, ewer",
+    "726": "plane, carpenters plane, woodworking plane",
+    "727": "planetarium",
+    "728": "plastic bag",
+    "729": "plate rack",
+    "730": "plow, plough",
+    "731": "plunger, plumbers helper",
+    "732": "Polaroid camera, Polaroid Land camera",
+    "733": "pole",
+    "734": "police van, police wagon, paddy wagon, patrol wagon, wagon, black Maria",
+    "735": "poncho",
+    "736": "pool table, billiard table, snooker table",
+    "737": "pop bottle, soda bottle",
+    "738": "pot, flowerpot",
+    "739": "potters wheel",
+    "740": "power drill",
+    "741": "prayer rug, prayer mat",
+    "742": "printer",
+    "743": "prison, prison house",
+    "744": "projectile, missile",
+    "745": "projector",
+    "746": "puck, hockey puck",
+    "747": "punching bag, punch bag, punching ball, punchball",
+    "748": "purse",
+    "749": "quill, quill pen",
+    "750": "quilt, comforter, comfort, puff",
+    "751": "racer, race car, racing car",
+    "752": "racket, racquet",
+    "753": "radiator",
+    "754": "radio, wireless",
+    "755": "radio telescope, radio reflector",
+    "756": "rain barrel",
+    "757": "recreational vehicle, RV, R.V.",
+    "758": "reel",
+    "759": "reflex camera",
+    "760": "refrigerator, icebox",
+    "761": "remote control, remote",
+    "762": "restaurant, eating house, eating place, eatery",
+    "763": "revolver, six-gun, six-shooter",
+    "764": "rifle",
+    "765": "rocking chair, rocker",
+    "766": "rotisserie",
+    "767": "rubber eraser, rubber, pencil eraser",
+    "768": "rugby ball",
+    "769": "rule, ruler",
+    "770": "running shoe",
+    "771": "safe",
+    "772": "safety pin",
+    "773": "saltshaker, salt shaker",
+    "774": "sandal",
+    "775": "sarong",
+    "776": "sax, saxophone",
+    "777": "scabbard",
+    "778": "scale, weighing machine",
+    "779": "school bus",
+    "780": "schooner",
+    "781": "scoreboard",
+    "782": "screen, CRT screen",
+    "783": "screw",
+    "784": "screwdriver",
+    "785": "seat belt, seatbelt",
+    "786": "sewing machine",
+    "787": "shield, buckler",
+    "788": "shoe shop, shoe-shop, shoe store",
+    "789": "shoji",
+    "790": "shopping basket",
+    "791": "shopping cart",
+    "792": "shovel",
+    "793": "shower cap",
+    "794": "shower curtain",
+    "795": "ski",
+    "796": "ski mask",
+    "797": "sleeping bag",
+    "798": "slide rule, slipstick",
+    "799": "sliding door",
+    "800": "slot, one-armed bandit",
+    "801": "snorkel",
+    "802": "snowmobile",
+    "803": "snowplow, snowplough",
+    "804": "soap dispenser",
+    "805": "soccer ball",
+    "806": "sock",
+    "807": "solar dish, solar collector, solar furnace",
+    "808": "sombrero",
+    "809": "soup bowl",
+    "810": "space bar",
+    "811": "space heater",
+    "812": "space shuttle",
+    "813": "spatula",
+    "814": "speedboat",
+    "815": "spider web, spiders web",
+    "816": "spindle",
+    "817": "sports car, sport car",
+    "818": "spotlight, spot",
+    "819": "stage",
+    "820": "steam locomotive",
+    "821": "steel arch bridge",
+    "822": "steel drum",
+    "823": "stethoscope",
+    "824": "stole",
+    "825": "stone wall",
+    "826": "stopwatch, stop watch",
+    "827": "stove",
+    "828": "strainer",
+    "829": "streetcar, tram, tramcar, trolley, trolley car",
+    "830": "stretcher",
+    "831": "studio couch, day bed",
+    "832": "stupa, tope",
+    "833": "submarine, pigboat, sub, U-boat",
+    "834": "suit, suit of clothes",
+    "835": "sundial",
+    "836": "sunglass",
+    "837": "sunglasses, dark glasses, shades",
+    "838": "sunscreen, sunblock, sun blocker",
+    "839": "suspension bridge",
+    "840": "swab, swob, mop",
+    "841": "sweatshirt",
+    "842": "swimming trunks, bathing trunks",
+    "843": "swing",
+    "844": "switch, electric switch, electrical switch",
+    "845": "syringe",
+    "846": "table lamp",
+    "847": "tank, army tank, armored combat vehicle, armoured combat vehicle",
+    "848": "tape player",
+    "849": "teapot",
+    "850": "teddy, teddy bear",
+    "851": "television, television system",
+    "852": "tennis ball",
+    "853": "thatch, thatched roof",
+    "854": "theater curtain, theatre curtain",
+    "855": "thimble",
+    "856": "thresher, thrasher, threshing machine",
+    "857": "throne",
+    "858": "tile roof",
+    "859": "toaster",
+    "860": "tobacco shop, tobacconist shop, tobacconist",
+    "861": "toilet seat",
+    "862": "torch",
+    "863": "totem pole",
+    "864": "tow truck, tow car, wrecker",
+    "865": "toyshop",
+    "866": "tractor",
+    "867": "trailer truck, tractor trailer, trucking rig, rig, articulated lorry, semi",
+    "868": "tray",
+    "869": "trench coat",
+    "870": "tricycle, trike, velocipede",
+    "871": "trimaran",
+    "872": "tripod",
+    "873": "triumphal arch",
+    "874": "trolleybus, trolley coach, trackless trolley",
+    "875": "trombone",
+    "876": "tub, vat",
+    "877": "turnstile",
+    "878": "typewriter keyboard",
+    "879": "umbrella",
+    "880": "unicycle, monocycle",
+    "881": "upright, upright piano",
+    "882": "vacuum, vacuum cleaner",
+    "883": "vase",
+    "884": "vault",
+    "885": "velvet",
+    "886": "vending machine",
+    "887": "vestment",
+    "888": "viaduct",
+    "889": "violin, fiddle",
+    "890": "volleyball",
+    "891": "waffle iron",
+    "892": "wall clock",
+    "893": "wallet, billfold, notecase, pocketbook",
+    "894": "wardrobe, closet, press",
+    "895": "warplane, military plane",
+    "896": "washbasin, handbasin, washbowl, lavabo, wash-hand basin",
+    "897": "washer, automatic washer, washing machine",
+    "898": "water bottle",
+    "899": "water jug",
+    "900": "water tower",
+    "901": "whiskey jug",
+    "902": "whistle",
+    "903": "wig",
+    "904": "window screen",
+    "905": "window shade",
+    "906": "Windsor tie",
+    "907": "wine bottle",
+    "908": "wing",
+    "909": "wok",
+    "910": "wooden spoon",
+    "911": "wool, woolen, woollen",
+    "912": "worm fence, snake fence, snake-rail fence, Virginia fence",
+    "913": "wreck",
+    "914": "yawl",
+    "915": "yurt",
+    "916": "web site, website, internet site, site",
+    "917": "comic book",
+    "918": "crossword puzzle, crossword",
+    "919": "street sign",
+    "920": "traffic light, traffic signal, stoplight",
+    "921": "book jacket, dust cover, dust jacket, dust wrapper",
+    "922": "menu",
+    "923": "plate",
+    "924": "guacamole",
+    "925": "consomme",
+    "926": "hot pot, hotpot",
+    "927": "trifle",
+    "928": "ice cream, icecream",
+    "929": "ice lolly, lolly, lollipop, popsicle",
+    "930": "French loaf",
+    "931": "bagel, beigel",
+    "932": "pretzel",
+    "933": "cheeseburger",
+    "934": "hotdog, hot dog, red hot",
+    "935": "mashed potato",
+    "936": "head cabbage",
+    "937": "broccoli",
+    "938": "cauliflower",
+    "939": "zucchini, courgette",
+    "940": "spaghetti squash",
+    "941": "acorn squash",
+    "942": "butternut squash",
+    "943": "cucumber, cuke",
+    "944": "artichoke, globe artichoke",
+    "945": "bell pepper",
+    "946": "cardoon",
+    "947": "mushroom",
+    "948": "Granny Smith",
+    "949": "strawberry",
+    "950": "orange",
+    "951": "lemon",
+    "952": "fig",
+    "953": "pineapple, ananas",
+    "954": "banana",
+    "955": "jackfruit, jak, jack",
+    "956": "custard apple",
+    "957": "pomegranate",
+    "958": "hay",
+    "959": "carbonara",
+    "960": "chocolate sauce, chocolate syrup",
+    "961": "dough",
+    "962": "meat loaf, meatloaf",
+    "963": "pizza, pizza pie",
+    "964": "potpie",
+    "965": "burrito",
+    "966": "red wine",
+    "967": "espresso",
+    "968": "cup",
+    "969": "eggnog",
+    "970": "alp",
+    "971": "bubble",
+    "972": "cliff, drop, drop-off",
+    "973": "coral reef",
+    "974": "geyser",
+    "975": "lakeside, lakeshore",
+    "976": "promontory, headland, head, foreland",
+    "977": "sandbar, sand bar",
+    "978": "seashore, coast, seacoast, sea-coast",
+    "979": "valley, vale",
+    "980": "volcano",
+    "981": "ballplayer, baseball player",
+    "982": "groom, bridegroom",
+    "983": "scuba diver",
+    "984": "rapeseed",
+    "985": "daisy",
+    "986": "yellow ladys slipper, yellow lady-slipper, Cypripedium calceolus, Cypripedium parviflorum",
+    "987": "corn",
+    "988": "acorn",
+    "989": "hip, rose hip, rosehip",
+    "990": "buckeye, horse chestnut, conker",
+    "991": "coral fungus",
+    "992": "agaric",
+    "993": "gyromitra",
+    "994": "stinkhorn, carrion fungus",
+    "995": "earthstar",
+    "996": "hen-of-the-woods, hen of the woods, Polyporus frondosus, Grifola frondosa",
+    "997": "bolete",
+    "998": "ear, spike, capitulum",
+    "999": "toilet tissue, toilet paper, bathroom tissue"
+  }
+}

DiCo-B-256/pipeline.py

@@ -0,0 +1,398 @@
+"""Hub custom pipeline: DiCoPipeline.
+Load with native Hugging Face diffusers and trust_remote_code=True.
+"""
+
+# Copyright 2026 The HuggingFace Team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from __future__ import annotations
+
+import inspect
+import json
+from pathlib import Path
+from typing import Dict, List, Optional, Tuple, Union
+
+import torch
+from diffusers.image_processor import VaeImageProcessor
+from diffusers.models import AutoencoderKL
+from diffusers.pipelines.pipeline_utils import DiffusionPipeline, ImagePipelineOutput
+from diffusers.schedulers import DDIMScheduler, KarrasDiffusionSchedulers
+from diffusers.utils.torch_utils import randn_tensor
+
+
+EXAMPLE_DOC_STRING = """
+    Examples:
+        ```py
+        >>> from pathlib import Path
+        >>> from diffusers import DiffusionPipeline
+        >>> import torch
+
+        >>> model_dir = Path("./DiCo-XL-256").resolve()
+        >>> pipe = DiffusionPipeline.from_pretrained(
+        ...     str(model_dir),
+        ...     local_files_only=True,
+        ...     custom_pipeline=str(model_dir / "pipeline.py"),
+        ...     trust_remote_code=True,
+        ...     torch_dtype=torch.bfloat16,
+        ... )
+        >>> pipe.to("cuda")
+
+        >>> image = pipe(
+        ...     class_labels="golden retriever",
+        ...     num_inference_steps=250,
+        ...     guidance_scale=1.4,
+        ...     generator=torch.Generator("cuda").manual_seed(0),
+        ... ).images[0]
+        ```
+"""
+
+
+class DiCoPipeline(DiffusionPipeline):
+    r"""
+    Pipeline for class-conditional image generation with DiCo (Diffusion ConvNet).
+
+    Parameters:
+        transformer ([`DiCoTransformer2DModel`]):
+            Class-conditional DiCo denoiser operating in VAE latent space.
+        vae ([`AutoencoderKL`]):
+            Variational autoencoder used to decode latents to pixels.
+        scheduler ([`DDIMScheduler`]):
+            Diffusion scheduler. Other [`KarrasDiffusionSchedulers`] can be swapped at inference time.
+        id2label (`dict[int, str]`, *optional*):
+            ImageNet class id to English label mapping. Values may contain comma-separated synonyms.
+    """
+
+    model_cpu_offload_seq = "transformer->vae"
+
+    @staticmethod
+    def prepare_extra_step_kwargs(
+        scheduler: KarrasDiffusionSchedulers,
+        generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
+        eta: float = 0.0,
+    ) -> Dict[str, object]:
+        kwargs: Dict[str, object] = {}
+        step_params = set(inspect.signature(scheduler.step).parameters.keys())
+        if "generator" in step_params:
+            kwargs["generator"] = generator
+        if "eta" in step_params:
+            kwargs["eta"] = eta
+        return kwargs
+
+    def __init__(
+        self,
+        transformer,
+        vae: AutoencoderKL,
+        scheduler: KarrasDiffusionSchedulers,
+        id2label: Optional[Dict[Union[int, str], str]] = None,
+    ):
+        super().__init__()
+        if scheduler is None:
+            scheduler = DDIMScheduler(
+                num_train_timesteps=1000,
+                beta_start=0.0001,
+                beta_end=0.02,
+                beta_schedule="linear",
+                clip_sample=False,
+                set_alpha_to_one=True,
+                steps_offset=0,
+                prediction_type="epsilon",
+            )
+        self.register_modules(transformer=transformer, vae=vae, scheduler=scheduler)
+        self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1)
+        self.image_processor = VaeImageProcessor(vae_scale_factor=self.vae_scale_factor)
+        self._id2label = self._normalize_id2label(id2label)
+        self.labels = self._build_label2id(self._id2label)
+        self._labels_loaded_from_model_index = bool(self._id2label)
+
+    @classmethod
+    def from_pretrained(cls, pretrained_model_name_or_path: str, **kwargs):
+        model_kwargs = dict(kwargs)
+        transformer_subfolder = model_kwargs.pop("transformer_subfolder", None)
+        scheduler_subfolder = model_kwargs.pop("scheduler_subfolder", None)
+        vae_subfolder = model_kwargs.pop("vae_subfolder", None)
+        scheduler_kwargs = model_kwargs.pop("scheduler_kwargs", {})
+        base_path = Path(pretrained_model_name_or_path)
+
+        if transformer_subfolder is None and (base_path / "transformer").exists():
+            transformer_subfolder = "transformer"
+        if scheduler_subfolder is None and (base_path / "scheduler").exists():
+            scheduler_subfolder = "scheduler"
+        if vae_subfolder is None and (base_path / "vae").exists():
+            vae_subfolder = "vae"
+
+        try:
+            return super().from_pretrained(pretrained_model_name_or_path, **kwargs)
+        except Exception:
+            transformer_path = str(base_path / transformer_subfolder) if transformer_subfolder else pretrained_model_name_or_path
+            from transformer.transformer_dico import DiCoTransformer2DModel
+            transformer = DiCoTransformer2DModel.from_pretrained(transformer_path, **model_kwargs)
+            try:
+                scheduler = DDIMScheduler.from_pretrained(
+                    pretrained_model_name_or_path,
+                    subfolder=scheduler_subfolder,
+                    **scheduler_kwargs,
+                )
+            except Exception:
+                scheduler = DDIMScheduler(
+                    num_train_timesteps=1000,
+                    beta_start=0.0001,
+                    beta_end=0.02,
+                    beta_schedule="linear",
+                    clip_sample=False,
+                    set_alpha_to_one=True,
+                    steps_offset=0,
+                    prediction_type="epsilon",
+                    **scheduler_kwargs,
+                )
+            try:
+                vae = AutoencoderKL.from_pretrained(
+                    pretrained_model_name_or_path,
+                    subfolder=vae_subfolder,
+                    **model_kwargs,
+                )
+            except Exception:
+                vae = AutoencoderKL.from_pretrained("stabilityai/sd-vae-ft-ema", **model_kwargs)
+            id2label = cls._read_id2label_from_model_index(str(base_path))
+            return cls(transformer=transformer, vae=vae, scheduler=scheduler, id2label=id2label)
+
+    def _ensure_labels_loaded(self) -> None:
+        if self._labels_loaded_from_model_index:
+            return
+        loaded = self._read_id2label_from_model_index(getattr(self.config, "_name_or_path", None))
+        if loaded:
+            self._id2label = loaded
+            self.labels = self._build_label2id(self._id2label)
+        self._labels_loaded_from_model_index = True
+
+    @staticmethod
+    def _normalize_id2label(id2label: Optional[Dict[Union[int, str], str]]) -> Dict[int, str]:
+        if not id2label:
+            return {}
+        return {int(key): value for key, value in id2label.items()}
+
+    @staticmethod
+    def _read_id2label_from_model_index(variant_path: Optional[str]) -> Dict[int, str]:
+        if not variant_path:
+            return {}
+        model_index_path = Path(variant_path).resolve() / "model_index.json"
+        if not model_index_path.exists():
+            return {}
+        raw = json.loads(model_index_path.read_text(encoding="utf-8"))
+        id2label = raw.get("id2label")
+        if not isinstance(id2label, dict):
+            return {}
+        return {int(key): value for key, value in id2label.items()}
+
+    @staticmethod
+    def _build_label2id(id2label: Dict[int, str]) -> Dict[str, int]:
+        label2id: Dict[str, int] = {}
+        for class_id, value in id2label.items():
+            for synonym in value.split(","):
+                synonym = synonym.strip()
+                if synonym:
+                    label2id[synonym] = int(class_id)
+        return dict(sorted(label2id.items()))
+
+    @property
+    def id2label(self) -> Dict[int, str]:
+        self._ensure_labels_loaded()
+        return self._id2label
+
+    def get_label_ids(self, label: Union[str, List[str]]) -> List[int]:
+        self._ensure_labels_loaded()
+        if not self.labels:
+            raise ValueError("No English labels loaded. Ensure `id2label` exists in model_index.json.")
+        if isinstance(label, str):
+            label = [label]
+        missing = [item for item in label if item not in self.labels]
+        if missing:
+            preview = ", ".join(list(self.labels.keys())[:8])
+            raise ValueError(f"Unknown English label(s): {missing}. Example valid labels: {preview}, ...")
+        return [self.labels[item] for item in label]
+
+    def _normalize_class_labels(
+        self,
+        class_labels: Union[int, str, List[Union[int, str]], torch.LongTensor],
+    ) -> torch.LongTensor:
+        if torch.is_tensor(class_labels):
+            return class_labels.to(device=self._execution_device, dtype=torch.long).reshape(-1)
+        if isinstance(class_labels, int):
+            class_label_ids = [class_labels]
+        elif isinstance(class_labels, str):
+            class_label_ids = self.get_label_ids(class_labels)
+        elif class_labels and isinstance(class_labels[0], str):
+            class_label_ids = self.get_label_ids(class_labels)
+        else:
+            class_label_ids = list(class_labels)
+        return torch.tensor(class_label_ids, device=self._execution_device, dtype=torch.long).reshape(-1)
+
+    def _default_image_size(self) -> int:
+        return int(self.transformer.config.input_size) * self.vae_scale_factor
+
+    def check_inputs(
+        self,
+        height: int,
+        width: int,
+        num_inference_steps: int,
+        output_type: str,
+    ) -> None:
+        if num_inference_steps < 1:
+            raise ValueError("num_inference_steps must be >= 1.")
+        if output_type not in {"pil", "np", "pt", "latent"}:
+            raise ValueError("output_type must be one of: 'pil', 'np', 'pt', 'latent'.")
+        if height % self.vae_scale_factor != 0 or width % self.vae_scale_factor != 0:
+            raise ValueError(
+                f"height and width must be divisible by the VAE downsample factor {self.vae_scale_factor}."
+            )
+        latent_height = height // self.vae_scale_factor
+        latent_width = width // self.vae_scale_factor
+        expected_size = int(self.transformer.config.input_size)
+        if latent_height != expected_size or latent_width != expected_size:
+            raise ValueError(
+                f"Requested latent size {(latent_height, latent_width)} does not match the pretrained "
+                f"transformer input_size={expected_size}. Use height=width={self._default_image_size()}."
+            )
+
+    def prepare_latents(
+        self,
+        batch_size: int,
+        height: int,
+        width: int,
+        dtype: torch.dtype,
+        device: torch.device,
+        generator: Optional[Union[torch.Generator, List[torch.Generator]]],
+    ) -> torch.Tensor:
+        latent_height = height // self.vae_scale_factor
+        latent_width = width // self.vae_scale_factor
+        return randn_tensor(
+            (batch_size, self.transformer.config.in_channels, latent_height, latent_width),
+            generator=generator,
+            device=device,
+            dtype=dtype,
+        )
+
+    @staticmethod
+    def _expand_timestep(timestep, batch: int, device: torch.device) -> torch.Tensor:
+        if not torch.is_tensor(timestep):
+            timestep = torch.tensor([timestep], dtype=torch.long, device=device)
+        elif timestep.ndim == 0:
+            timestep = timestep[None].to(device=device)
+        return timestep.expand(batch)
+
+    @staticmethod
+    def _prepare_model_output_for_scheduler(
+        model_output: torch.Tensor,
+        latent_channels: int,
+        scheduler: KarrasDiffusionSchedulers,
+    ) -> torch.Tensor:
+        if model_output.shape[1] != 2 * latent_channels:
+            return model_output
+        variance_type = getattr(scheduler.config, "variance_type", None)
+        if scheduler.__class__.__name__ == "DDPMScheduler" and variance_type in ("learned", "learned_range"):
+            return model_output
+        model_output, _ = torch.split(model_output, latent_channels, dim=1)
+        return model_output
+
+    def decode_latents(self, latents: torch.Tensor, output_type: str = "pil"):
+        if output_type == "latent":
+            return latents
+        scaling_factor = getattr(self.vae.config, "scaling_factor", 0.18215)
+        image = self.vae.decode(latents / scaling_factor).sample
+        if output_type == "pt":
+            return image
+        return self.image_processor.postprocess(image, output_type=output_type)
+
+    @torch.inference_mode()
+    def __call__(
+        self,
+        class_labels: Union[int, str, List[Union[int, str]], torch.LongTensor],
+        height: Optional[int] = None,
+        width: Optional[int] = None,
+        num_inference_steps: int = 250,
+        guidance_scale: float = 1.0,
+        eta: float = 0.0,
+        generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
+        output_type: str = "pil",
+        return_dict: bool = True,
+    ) -> Union[ImagePipelineOutput, Tuple]:
+        default_size = self._default_image_size()
+        height = int(height or default_size)
+        width = int(width or default_size)
+        self.check_inputs(height, width, num_inference_steps, output_type)
+
+        device = self._execution_device
+        model_dtype = next(self.transformer.parameters()).dtype
+        class_labels_tensor = self._normalize_class_labels(class_labels)
+        batch_size = class_labels_tensor.numel()
+        latent_channels = int(self.transformer.config.in_channels)
+        null_class_val = int(self.transformer.config.num_classes)
+        do_cfg = guidance_scale > 1.0
+
+        latents = self.prepare_latents(
+            batch_size=batch_size,
+            height=height,
+            width=width,
+            dtype=model_dtype,
+            device=device,
+            generator=generator,
+        )
+        latent_model_input = torch.cat([latents] * 2) if do_cfg else latents
+
+        class_labels_input = class_labels_tensor
+        if do_cfg:
+            class_null = torch.full_like(class_labels_tensor, null_class_val)
+            class_labels_input = torch.cat([class_labels_tensor, class_null], dim=0)
+
+        self.scheduler.set_timesteps(num_inference_steps, device=device)
+        extra_step_kwargs = self.prepare_extra_step_kwargs(self.scheduler, generator=generator, eta=eta)
+
+        for t in self.progress_bar(self.scheduler.timesteps):
+            if do_cfg:
+                half = latent_model_input[: len(latent_model_input) // 2]
+                latent_model_input = torch.cat([half, half], dim=0)
+            latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)
+            timesteps = self._expand_timestep(t, latent_model_input.shape[0], latent_model_input.device)
+
+            noise_pred = self.transformer(
+                hidden_states=latent_model_input,
+                timestep=timesteps,
+                class_labels=class_labels_input,
+                return_dict=True,
+            ).sample
+
+            if do_cfg:
+                eps, rest = noise_pred[:, :latent_channels], noise_pred[:, latent_channels:]
+                cond_eps, uncond_eps = torch.split(eps, len(eps) // 2, dim=0)
+                half_eps = uncond_eps + guidance_scale * (cond_eps - uncond_eps)
+                eps = torch.cat([half_eps, half_eps], dim=0)
+                noise_pred = torch.cat([eps, rest], dim=1)
+
+            model_output = self._prepare_model_output_for_scheduler(noise_pred, latent_channels, self.scheduler)
+            latent_model_input = self.scheduler.step(
+                model_output, t, latent_model_input, return_dict=True, **extra_step_kwargs
+            ).prev_sample
+
+        if do_cfg:
+            latents, _ = latent_model_input.chunk(2, dim=0)
+        else:
+            latents = latent_model_input
+
+        image = self.decode_latents(latents, output_type=output_type)
+        self.maybe_free_model_hooks()
+        if not return_dict:
+            return (image,)
+        return ImagePipelineOutput(images=image)
+
+
+DiCoPipelineOutput = ImagePipelineOutput

DiCo-B-256/scheduler/scheduler_config.json

@@ -0,0 +1,12 @@
+{
+  "_class_name": "DDIMScheduler",
+  "_diffusers_version": "0.35.1",
+  "num_train_timesteps": 1000,
+  "beta_start": 0.0001,
+  "beta_end": 0.02,
+  "beta_schedule": "linear",
+  "clip_sample": false,
+  "set_alpha_to_one": true,
+  "steps_offset": 0,
+  "prediction_type": "epsilon"
+}

DiCo-B-256/transformer/config.json

@@ -0,0 +1,14 @@
+{
+  "_class_name": "DiCoTransformer2DModel",
+  "_diffusers_version": "0.38.0",
+  "class_dropout_prob": 0.1,
+  "depth": null,
+  "hidden_size": 416,
+  "in_channels": 4,
+  "input_size": 32,
+  "learn_sigma": true,
+  "mlp_ratio": 2.0,
+  "model_type": "DiCo-B",
+  "num_class_embeds": null,
+  "num_classes": 1000
+}

DiCo-B-256/transformer/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a70318a80eaff9e024b40cad7792244a1771fc167fbde9103c13ed2c5c159074
+size 520003840

DiCo-B-256/transformer/transformer_dico.py

@@ -0,0 +1,479 @@
+# Copyright 2026 The HuggingFace Team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from __future__ import annotations
+
+import argparse
+import math
+from collections.abc import Mapping
+from typing import Dict, Literal, Optional, Tuple
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+from diffusers.configuration_utils import ConfigMixin, register_to_config
+from diffusers.models.modeling_outputs import Transformer2DModelOutput
+from diffusers.models.modeling_utils import ModelMixin
+
+
+DICO_PRESET_CONFIGS: Dict[str, Dict[str, object]] = {
+    "DiCo-S": {
+        "hidden_size": 128,
+        "depth": [5, 4, 4, 4, 4],
+        "mlp_ratio": 2.0,
+    },
+    "DiCo-B": {
+        "hidden_size": 256,
+        "depth": [5, 4, 4, 4, 4],
+        "mlp_ratio": 2.0,
+    },
+    "DiCo-L": {
+        "hidden_size": 352,
+        "depth": [9, 8, 9, 8, 9],
+        "mlp_ratio": 2.0,
+    },
+    "DiCo-XL": {
+        "hidden_size": 416,
+        "depth": [9, 9, 10, 9, 9],
+        "mlp_ratio": 2.0,
+    },
+    "DiCo-H": {
+        "hidden_size": 416,
+        "depth": [14, 12, 10, 12, 14],
+        "mlp_ratio": 4.0,
+    },
+}
+
+
+def remap_legacy_state_dict(state_dict: Dict[str, torch.Tensor]) -> Dict[str, torch.Tensor]:
+    """Map wrapper/backbone keys from legacy checkpoints to native model keys."""
+    remapped: Dict[str, torch.Tensor] = {}
+    for key, value in state_dict.items():
+        new_key = key
+        for prefix in ("transformer.", "model.", "net."):
+            if new_key.startswith(prefix):
+                new_key = new_key[len(prefix) :]
+                break
+        remapped[new_key] = value
+    return remapped
+
+
+def infer_learn_sigma(state_dict: Dict[str, torch.Tensor], in_channels: int = 4) -> bool:
+    weight = state_dict.get("final_layer.out_proj.weight")
+    if weight is None:
+        return True
+    return int(weight.shape[0]) == in_channels * 2
+
+
+def config_from_legacy(config: Dict[str, object]) -> Dict[str, object]:
+    """Build native config kwargs from a legacy config.json dict."""
+    model_type = config.get("model_type") or config.get("model_name") or config.get("model")
+    if model_type not in DICO_PRESET_CONFIGS:
+        raise ValueError(f"Unknown DiCo preset '{model_type}'. Known: {list(DICO_PRESET_CONFIGS)}")
+
+    preset = dict(DICO_PRESET_CONFIGS[model_type])
+    preset["num_classes"] = int(config.get("num_class_embeds") or config.get("num_classes") or 1000)
+    preset["model_type"] = model_type
+    preset["input_size"] = int(config.get("input_size") or config.get("sample_size") or 32)
+    if config.get("learn_sigma") is not None:
+        preset["learn_sigma"] = bool(config["learn_sigma"])
+    return preset
+
+
+def modulate(x: torch.Tensor, shift: torch.Tensor, scale: torch.Tensor) -> torch.Tensor:
+    return x * (1 + scale.unsqueeze(-1).unsqueeze(-1)) + shift.unsqueeze(-1).unsqueeze(-1)
+
+
+class LayerNorm2d(nn.LayerNorm):
+    def __init__(self, num_channels: int, eps: float = 1e-6, affine: bool = True):
+        super().__init__(num_channels, eps=eps, elementwise_affine=affine)
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        x = x.permute(0, 2, 3, 1)
+        x = F.layer_norm(x, self.normalized_shape, self.weight, self.bias, self.eps)
+        return x.permute(0, 3, 1, 2)
+
+
+class DiCoTimestepEmbedder(nn.Module):
+    def __init__(self, hidden_size: int, frequency_embedding_size: int = 256):
+        super().__init__()
+        self.mlp = nn.Sequential(
+            nn.Linear(frequency_embedding_size, hidden_size, bias=True),
+            nn.SiLU(),
+            nn.Linear(hidden_size, hidden_size, bias=True),
+        )
+        self.frequency_embedding_size = frequency_embedding_size
+
+    @staticmethod
+    def timestep_embedding(t: torch.Tensor, dim: int, max_period: int = 10000) -> torch.Tensor:
+        half = dim // 2
+        freqs = torch.exp(
+            -math.log(max_period) * torch.arange(start=0, end=half, dtype=torch.float32) / half
+        ).to(device=t.device)
+        args = t[:, None].float() * freqs[None]
+        embedding = torch.cat([torch.cos(args), torch.sin(args)], dim=-1)
+        if dim % 2:
+            embedding = torch.cat([embedding, torch.zeros_like(embedding[:, :1])], dim=-1)
+        return embedding
+
+    def forward(self, t: torch.Tensor) -> torch.Tensor:
+        t_freq = self.timestep_embedding(t, self.frequency_embedding_size)
+        weight_dtype = self.mlp[0].weight.dtype
+        return self.mlp(t_freq.to(dtype=weight_dtype))
+
+
+class DiCoLabelEmbedder(nn.Module):
+    def __init__(self, num_classes: int, hidden_size: int, dropout_prob: float):
+        super().__init__()
+        use_cfg_embedding = dropout_prob > 0
+        self.embedding_table = nn.Embedding(num_classes + use_cfg_embedding, hidden_size)
+        self.num_classes = num_classes
+        self.dropout_prob = dropout_prob
+
+    def token_drop(self, labels: torch.Tensor, force_drop_ids: Optional[torch.Tensor] = None) -> torch.Tensor:
+        if force_drop_ids is None:
+            drop_ids = torch.rand(labels.shape[0], device=labels.device) < self.dropout_prob
+        else:
+            drop_ids = force_drop_ids == 1
+        return torch.where(drop_ids, self.num_classes, labels)
+
+    def forward(
+        self,
+        labels: torch.Tensor,
+        train: bool,
+        force_drop_ids: Optional[torch.Tensor] = None,
+    ) -> torch.Tensor:
+        use_dropout = self.dropout_prob > 0
+        if (train and use_dropout) or (force_drop_ids is not None):
+            labels = self.token_drop(labels, force_drop_ids)
+        return self.embedding_table(labels)
+
+
+class DiCoMultiScaleLabelEmbedder(nn.Module):
+    def __init__(
+        self,
+        num_classes: int,
+        hidden_size_0: int,
+        hidden_size_1: int,
+        hidden_size_2: int,
+        dropout_prob: float,
+    ):
+        super().__init__()
+        use_cfg_embedding = dropout_prob > 0
+        self.embedding_table_0 = nn.Embedding(num_classes + use_cfg_embedding, hidden_size_0)
+        self.embedding_table_1 = nn.Embedding(num_classes + use_cfg_embedding, hidden_size_1)
+        self.embedding_table_2 = nn.Embedding(num_classes + use_cfg_embedding, hidden_size_2)
+        self.num_classes = num_classes
+        self.dropout_prob = dropout_prob
+
+    def token_drop(self, labels: torch.Tensor, force_drop_ids: Optional[torch.Tensor] = None) -> torch.Tensor:
+        if force_drop_ids is None:
+            drop_ids = torch.rand(labels.shape[0], device=labels.device) < self.dropout_prob
+        else:
+            drop_ids = force_drop_ids == 1
+        return torch.where(drop_ids, self.num_classes, labels)
+
+    def forward(
+        self,
+        labels: torch.Tensor,
+        train: bool,
+        force_drop_ids: Optional[torch.Tensor] = None,
+    ) -> Tuple[torch.Tensor, torch.Tensor, torch.Tensor]:
+        use_dropout = self.dropout_prob > 0
+        if (train and use_dropout) or (force_drop_ids is not None):
+            labels = self.token_drop(labels, force_drop_ids)
+        return (
+            self.embedding_table_0(labels),
+            self.embedding_table_1(labels),
+            self.embedding_table_2(labels),
+        )
+
+
+class DiCoBlock(nn.Module):
+    def __init__(self, hidden_size: int, mlp_ratio: float = 4.0):
+        super().__init__()
+        self.conv1 = nn.Conv2d(hidden_size, hidden_size, kernel_size=1, padding=0, stride=1, groups=1, bias=True)
+        self.conv2 = nn.Conv2d(
+            hidden_size, hidden_size, kernel_size=3, padding=1, stride=1, groups=hidden_size, bias=True
+        )
+        self.conv3 = nn.Conv2d(hidden_size, hidden_size, kernel_size=1, padding=0, stride=1, groups=1, bias=True)
+        self.ca = nn.Sequential(
+            nn.AdaptiveAvgPool2d(1),
+            nn.Conv2d(hidden_size, hidden_size, kernel_size=1, padding=0, stride=1, groups=1, bias=True),
+            nn.Sigmoid(),
+        )
+        ffn_channel = int(mlp_ratio * hidden_size)
+        self.conv4 = nn.Conv2d(hidden_size, ffn_channel, kernel_size=1, padding=0, stride=1, groups=1, bias=True)
+        self.conv5 = nn.Conv2d(ffn_channel, hidden_size, kernel_size=1, padding=0, stride=1, groups=1, bias=True)
+        self.norm1 = LayerNorm2d(hidden_size, affine=False, eps=1e-6)
+        self.norm2 = LayerNorm2d(hidden_size, affine=False, eps=1e-6)
+        self.adaLN_modulation = nn.Sequential(nn.SiLU(), nn.Linear(hidden_size, 6 * hidden_size, bias=True))
+
+    def forward(self, inp: torch.Tensor, c: torch.Tensor) -> torch.Tensor:
+        shift_msa, scale_msa, gate_msa, shift_mlp, scale_mlp, gate_mlp = self.adaLN_modulation(c).chunk(6, dim=1)
+        x = modulate(self.norm1(inp), shift_msa, scale_msa)
+        x = F.gelu(self.conv2(self.conv1(x)))
+        x = x * self.ca(x)
+        x = self.conv3(x)
+        x = inp + gate_msa.unsqueeze(-1).unsqueeze(-1) * x
+        x = x + gate_mlp.unsqueeze(-1).unsqueeze(-1) * self.conv5(
+            F.gelu(self.conv4(modulate(self.norm2(x), shift_mlp, scale_mlp)))
+        )
+        return x
+
+
+class DiCoFinalLayer(nn.Module):
+    def __init__(self, hidden_size: int, out_channels: int):
+        super().__init__()
+        self.norm_final = LayerNorm2d(hidden_size, affine=False, eps=1e-6)
+        self.out_proj = nn.Conv2d(hidden_size, out_channels, kernel_size=3, stride=1, padding=1, bias=True)
+        self.adaLN_modulation = nn.Sequential(nn.SiLU(), nn.Linear(hidden_size, 2 * hidden_size, bias=True))
+
+    def forward(self, x: torch.Tensor, c: torch.Tensor) -> torch.Tensor:
+        shift, scale = self.adaLN_modulation(c).chunk(2, dim=1)
+        x = modulate(self.norm_final(x), shift, scale)
+        return self.out_proj(x)
+
+
+class OverlapPatchEmbed(nn.Module):
+    def __init__(self, in_c: int = 3, embed_dim: int = 48, bias: bool = False):
+        super().__init__()
+        self.proj = nn.Conv2d(in_c, embed_dim, kernel_size=3, stride=1, padding=1, bias=bias)
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        return self.proj(x)
+
+
+class Downsample(nn.Module):
+    def __init__(self, n_feat: int):
+        super().__init__()
+        self.body = nn.Sequential(
+            nn.Conv2d(n_feat, n_feat // 2, kernel_size=3, stride=1, padding=1, bias=False),
+            nn.PixelUnshuffle(2),
+        )
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        return self.body(x)
+
+
+class Upsample(nn.Module):
+    def __init__(self, n_feat: int):
+        super().__init__()
+        self.body = nn.Sequential(
+            nn.Conv2d(n_feat, n_feat * 2, kernel_size=3, stride=1, padding=1, bias=False),
+            nn.PixelShuffle(2),
+        )
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        return self.body(x)
+
+
+class DiCoTransformer2DModel(ModelMixin, ConfigMixin):
+    r"""
+    DiCo (Diffusion ConvNet) denoiser for class-conditional latent diffusion.
+
+    ConvNet U-Net backbone with multi-scale adaLN conditioning, operating on VAE latents.
+    """
+
+    _supports_gradient_checkpointing = True
+
+    @register_to_config
+    def __init__(
+        self,
+        input_size: int = 32,
+        in_channels: int = 4,
+        hidden_size: int = 416,
+        depth: Optional[list[int]] = None,
+        mlp_ratio: float = 2.0,
+        class_dropout_prob: float = 0.1,
+        num_classes: int = 1000,
+        learn_sigma: bool = True,
+        model_type: str | None = None,
+        num_class_embeds: int | None = None,
+    ):
+        super().__init__()
+        if num_class_embeds is not None:
+            num_classes = int(num_class_embeds)
+        if model_type in DICO_PRESET_CONFIGS:
+            preset = DICO_PRESET_CONFIGS[model_type]
+            hidden_size = int(preset["hidden_size"])
+            depth = list(preset["depth"])
+            mlp_ratio = float(preset["mlp_ratio"])
+
+        if depth is None:
+            depth = [9, 9, 10, 9, 9]
+
+        self.learn_sigma = learn_sigma
+        self.in_channels = in_channels
+        self.out_channels = in_channels * 2 if learn_sigma else in_channels
+        self.num_classes = num_classes
+        self.gradient_checkpointing = False
+
+        self.x_embedder = OverlapPatchEmbed(in_channels, hidden_size, bias=True)
+        self.t_embedder_1 = DiCoTimestepEmbedder(hidden_size)
+        self.y_embedder = DiCoMultiScaleLabelEmbedder(
+            num_classes, hidden_size, hidden_size * 2, hidden_size * 4, class_dropout_prob
+        )
+        self.t_embedder_2 = DiCoTimestepEmbedder(hidden_size * 2)
+        self.t_embedder_3 = DiCoTimestepEmbedder(hidden_size * 4)
+
+        self.encoder_level_1 = nn.ModuleList([DiCoBlock(hidden_size, mlp_ratio) for _ in range(depth[0])])
+        self.down1_2 = Downsample(hidden_size)
+        self.encoder_level_2 = nn.ModuleList([DiCoBlock(hidden_size * 2, mlp_ratio) for _ in range(depth[1])])
+        self.down2_3 = Downsample(hidden_size * 2)
+        self.latent = nn.ModuleList([DiCoBlock(hidden_size * 4, mlp_ratio) for _ in range(depth[2])])
+        self.up3_2 = Upsample(int(hidden_size * 4))
+        self.reduce_chan_level2 = nn.Conv2d(int(hidden_size * 4), int(hidden_size * 2), kernel_size=1, bias=True)
+        self.decoder_level_2 = nn.ModuleList([DiCoBlock(hidden_size * 2, mlp_ratio) for _ in range(depth[3])])
+        self.up2_1 = Upsample(int(hidden_size * 2))
+        self.reduce_chan_level1 = nn.Conv2d(int(hidden_size * 2), int(hidden_size * 2), kernel_size=1, bias=True)
+        self.decoder_level_1 = nn.ModuleList([DiCoBlock(hidden_size * 2, mlp_ratio) for _ in range(depth[4])])
+        self.final_layer = DiCoFinalLayer(hidden_size * 2, self.out_channels)
+        self.initialize_weights()
+
+    def initialize_weights(self) -> None:
+        def _basic_init(module: nn.Module):
+            if isinstance(module, (nn.Linear, nn.Conv2d)):
+                torch.nn.init.xavier_uniform_(module.weight)
+                if module.bias is not None:
+                    nn.init.constant_(module.bias, 0)
+
+        self.apply(_basic_init)
+        w = self.x_embedder.proj.weight.data
+        nn.init.xavier_uniform_(w.view([w.shape[0], -1]))
+        nn.init.constant_(self.x_embedder.proj.bias, 0)
+        nn.init.normal_(self.y_embedder.embedding_table_0.weight, std=0.02)
+        nn.init.normal_(self.y_embedder.embedding_table_1.weight, std=0.02)
+        nn.init.normal_(self.y_embedder.embedding_table_2.weight, std=0.02)
+        for embedder in (self.t_embedder_1, self.t_embedder_2, self.t_embedder_3):
+            nn.init.normal_(embedder.mlp[0].weight, std=0.02)
+            nn.init.normal_(embedder.mlp[2].weight, std=0.02)
+
+        blocks = (
+            self.encoder_level_1
+            + self.encoder_level_2
+            + self.latent
+            + self.decoder_level_2
+            + self.decoder_level_1
+        )
+        for block in blocks:
+            nn.init.constant_(block.adaLN_modulation[-1].weight, 0)
+            nn.init.constant_(block.adaLN_modulation[-1].bias, 0)
+        nn.init.constant_(self.final_layer.adaLN_modulation[-1].weight, 0)
+        nn.init.constant_(self.final_layer.adaLN_modulation[-1].bias, 0)
+        nn.init.constant_(self.final_layer.out_proj.weight, 0)
+        nn.init.constant_(self.final_layer.out_proj.bias, 0)
+
+    def _run_block(self, block: DiCoBlock, x: torch.Tensor, c: torch.Tensor) -> torch.Tensor:
+        if self.training and self.gradient_checkpointing:
+            return torch.utils.checkpoint.checkpoint(block, x, c, use_reentrant=False)
+        return block(x, c)
+
+    def forward(
+        self,
+        hidden_states: torch.Tensor,
+        timestep: torch.LongTensor,
+        class_labels: torch.LongTensor,
+        force_drop_ids: Optional[torch.Tensor] = None,
+        return_dict: bool = True,
+    ) -> Transformer2DModelOutput | Tuple:
+        timestep = torch.as_tensor(timestep, device=hidden_states.device)
+        if timestep.ndim == 0:
+            timestep = timestep.repeat(hidden_states.shape[0])
+        else:
+            timestep = timestep.reshape(-1)
+            if timestep.shape[0] == 1 and hidden_states.shape[0] > 1:
+                timestep = timestep.repeat(hidden_states.shape[0])
+
+        x = self.x_embedder(hidden_states)
+        t1 = self.t_embedder_1(timestep)
+        y1, y2, y3 = self.y_embedder(class_labels, self.training, force_drop_ids=force_drop_ids)
+        c1 = t1 + y1
+        c2 = self.t_embedder_2(timestep) + y2
+        c3 = self.t_embedder_3(timestep) + y3
+
+        out_enc_level1 = x
+        for block in self.encoder_level_1:
+            out_enc_level1 = self._run_block(block, out_enc_level1, c1)
+        out_enc_level2 = self.down1_2(out_enc_level1)
+        for block in self.encoder_level_2:
+            out_enc_level2 = self._run_block(block, out_enc_level2, c2)
+        latent = self.down2_3(out_enc_level2)
+        for block in self.latent:
+            latent = self._run_block(block, latent, c3)
+
+        inp_dec_level2 = self.reduce_chan_level2(torch.cat([self.up3_2(latent), out_enc_level2], dim=1))
+        for block in self.decoder_level_2:
+            inp_dec_level2 = self._run_block(block, inp_dec_level2, c2)
+        inp_dec_level1 = self.reduce_chan_level1(torch.cat([self.up2_1(inp_dec_level2), out_enc_level1], dim=1))
+        for block in self.decoder_level_1:
+            inp_dec_level1 = self._run_block(block, inp_dec_level1, c2)
+
+        output = self.final_layer(inp_dec_level1, c2)
+        if not return_dict:
+            return (output,)
+        return Transformer2DModelOutput(sample=output)
+
+    @classmethod
+    def from_dico_checkpoint(
+        cls,
+        checkpoint_path: str,
+        weights: Literal["model", "ema"] = "ema",
+        map_location: str = "cpu",
+        strict: bool = True,
+        model_type: str | None = None,
+    ) -> Tuple["DiCoTransformer2DModel", Dict[str, object]]:
+        checkpoint = torch.load(checkpoint_path, map_location=map_location, weights_only=False)
+        state_dict = checkpoint
+        if isinstance(checkpoint, Mapping):
+            if weights in checkpoint:
+                state_dict = checkpoint[weights]
+            elif "state_dict" in checkpoint:
+                state_dict = checkpoint["state_dict"]
+
+        state_dict = remap_legacy_state_dict(state_dict)
+
+        ckpt_args = checkpoint.get("args") if isinstance(checkpoint, Mapping) else None
+        args_dict: Dict[str, object] = {}
+        if ckpt_args is not None:
+            if isinstance(ckpt_args, argparse.Namespace):
+                args_dict = vars(ckpt_args)
+            elif isinstance(ckpt_args, Mapping):
+                args_dict = dict(ckpt_args)
+
+        resolved_model_type = model_type or args_dict.get("model") or args_dict.get("model_type")
+        image_size = int(args_dict.get("image_size") or 256)
+        num_classes = int(args_dict.get("num_classes") or 1000)
+
+        config: Dict[str, object] = {
+            "input_size": image_size // 8,
+            "num_classes": num_classes,
+            "learn_sigma": infer_learn_sigma(state_dict),
+        }
+        if resolved_model_type in DICO_PRESET_CONFIGS:
+            config["model_type"] = resolved_model_type
+
+        model = cls(**config)
+        model.load_state_dict(state_dict, strict=strict)
+        metadata = {
+            "checkpoint_path": checkpoint_path,
+            "weights": weights,
+            "model_type": resolved_model_type,
+            "source_args": ckpt_args,
+        }
+        return model, metadata
+
+
+DiCoDiffusersModel = DiCoTransformer2DModel

DiCo-B-256/vae/config.json

@@ -0,0 +1,38 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.38.0",
+  "_name_or_path": "stabilityai/sd-vae-ft-ema",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "force_upcast": true,
+  "in_channels": 3,
+  "latent_channels": 4,
+  "latents_mean": null,
+  "latents_std": null,
+  "layers_per_block": 2,
+  "mid_block_add_attention": true,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 256,
+  "scaling_factor": 0.18215,
+  "shift_factor": null,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ],
+  "use_post_quant_conv": true,
+  "use_quant_conv": true
+}

DiCo-B-256/vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:703abdcd7c389316b5128faa9b750a530ea1680b453170b27afebac5e4db30c4
+size 334643268

DiCo-L-256/model_index.json

@@ -0,0 +1,1021 @@
+{
+  "_class_name": [
+    "pipeline",
+    "DiCoPipeline"
+  ],
+  "_diffusers_version": "0.38.0",
+  "scheduler": [
+    "diffusers",
+    "DDIMScheduler"
+  ],
+  "transformer": [
+    "transformer_dico",
+    "DiCoTransformer2DModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ],
+  "id2label": {
+    "0": "tench, Tinca tinca",
+    "1": "goldfish, Carassius auratus",
+    "2": "great white shark, white shark, man-eater, man-eating shark, Carcharodon carcharias",
+    "3": "tiger shark, Galeocerdo cuvieri",
+    "4": "hammerhead, hammerhead shark",
+    "5": "electric ray, crampfish, numbfish, torpedo",
+    "6": "stingray",
+    "7": "cock",
+    "8": "hen",
+    "9": "ostrich, Struthio camelus",
+    "10": "brambling, Fringilla montifringilla",
+    "11": "goldfinch, Carduelis carduelis",
+    "12": "house finch, linnet, Carpodacus mexicanus",
+    "13": "junco, snowbird",
+    "14": "indigo bunting, indigo finch, indigo bird, Passerina cyanea",
+    "15": "robin, American robin, Turdus migratorius",
+    "16": "bulbul",
+    "17": "jay",
+    "18": "magpie",
+    "19": "chickadee",
+    "20": "water ouzel, dipper",
+    "21": "kite",
+    "22": "bald eagle, American eagle, Haliaeetus leucocephalus",
+    "23": "vulture",
+    "24": "great grey owl, great gray owl, Strix nebulosa",
+    "25": "European fire salamander, Salamandra salamandra",
+    "26": "common newt, Triturus vulgaris",
+    "27": "eft",
+    "28": "spotted salamander, Ambystoma maculatum",
+    "29": "axolotl, mud puppy, Ambystoma mexicanum",
+    "30": "bullfrog, Rana catesbeiana",
+    "31": "tree frog, tree-frog",
+    "32": "tailed frog, bell toad, ribbed toad, tailed toad, Ascaphus trui",
+    "33": "loggerhead, loggerhead turtle, Caretta caretta",
+    "34": "leatherback turtle, leatherback, leathery turtle, Dermochelys coriacea",
+    "35": "mud turtle",
+    "36": "terrapin",
+    "37": "box turtle, box tortoise",
+    "38": "banded gecko",
+    "39": "common iguana, iguana, Iguana iguana",
+    "40": "American chameleon, anole, Anolis carolinensis",
+    "41": "whiptail, whiptail lizard",
+    "42": "agama",
+    "43": "frilled lizard, Chlamydosaurus kingi",
+    "44": "alligator lizard",
+    "45": "Gila monster, Heloderma suspectum",
+    "46": "green lizard, Lacerta viridis",
+    "47": "African chameleon, Chamaeleo chamaeleon",
+    "48": "Komodo dragon, Komodo lizard, dragon lizard, giant lizard, Varanus komodoensis",
+    "49": "African crocodile, Nile crocodile, Crocodylus niloticus",
+    "50": "American alligator, Alligator mississipiensis",
+    "51": "triceratops",
+    "52": "thunder snake, worm snake, Carphophis amoenus",
+    "53": "ringneck snake, ring-necked snake, ring snake",
+    "54": "hognose snake, puff adder, sand viper",
+    "55": "green snake, grass snake",
+    "56": "king snake, kingsnake",
+    "57": "garter snake, grass snake",
+    "58": "water snake",
+    "59": "vine snake",
+    "60": "night snake, Hypsiglena torquata",
+    "61": "boa constrictor, Constrictor constrictor",
+    "62": "rock python, rock snake, Python sebae",
+    "63": "Indian cobra, Naja naja",
+    "64": "green mamba",
+    "65": "sea snake",
+    "66": "horned viper, cerastes, sand viper, horned asp, Cerastes cornutus",
+    "67": "diamondback, diamondback rattlesnake, Crotalus adamanteus",
+    "68": "sidewinder, horned rattlesnake, Crotalus cerastes",
+    "69": "trilobite",
+    "70": "harvestman, daddy longlegs, Phalangium opilio",
+    "71": "scorpion",
+    "72": "black and gold garden spider, Argiope aurantia",
+    "73": "barn spider, Araneus cavaticus",
+    "74": "garden spider, Aranea diademata",
+    "75": "black widow, Latrodectus mactans",
+    "76": "tarantula",
+    "77": "wolf spider, hunting spider",
+    "78": "tick",
+    "79": "centipede",
+    "80": "black grouse",
+    "81": "ptarmigan",
+    "82": "ruffed grouse, partridge, Bonasa umbellus",
+    "83": "prairie chicken, prairie grouse, prairie fowl",
+    "84": "peacock",
+    "85": "quail",
+    "86": "partridge",
+    "87": "African grey, African gray, Psittacus erithacus",
+    "88": "macaw",
+    "89": "sulphur-crested cockatoo, Kakatoe galerita, Cacatua galerita",
+    "90": "lorikeet",
+    "91": "coucal",
+    "92": "bee eater",
+    "93": "hornbill",
+    "94": "hummingbird",
+    "95": "jacamar",
+    "96": "toucan",
+    "97": "drake",
+    "98": "red-breasted merganser, Mergus serrator",
+    "99": "goose",
+    "100": "black swan, Cygnus atratus",
+    "101": "tusker",
+    "102": "echidna, spiny anteater, anteater",
+    "103": "platypus, duckbill, duckbilled platypus, duck-billed platypus, Ornithorhynchus anatinus",
+    "104": "wallaby, brush kangaroo",
+    "105": "koala, koala bear, kangaroo bear, native bear, Phascolarctos cinereus",
+    "106": "wombat",
+    "107": "jellyfish",
+    "108": "sea anemone, anemone",
+    "109": "brain coral",
+    "110": "flatworm, platyhelminth",
+    "111": "nematode, nematode worm, roundworm",
+    "112": "conch",
+    "113": "snail",
+    "114": "slug",
+    "115": "sea slug, nudibranch",
+    "116": "chiton, coat-of-mail shell, sea cradle, polyplacophore",
+    "117": "chambered nautilus, pearly nautilus, nautilus",
+    "118": "Dungeness crab, Cancer magister",
+    "119": "rock crab, Cancer irroratus",
+    "120": "fiddler crab",
+    "121": "king crab, Alaska crab, Alaskan king crab, Alaska king crab, Paralithodes camtschatica",
+    "122": "American lobster, Northern lobster, Maine lobster, Homarus americanus",
+    "123": "spiny lobster, langouste, rock lobster, crawfish, crayfish, sea crawfish",
+    "124": "crayfish, crawfish, crawdad, crawdaddy",
+    "125": "hermit crab",
+    "126": "isopod",
+    "127": "white stork, Ciconia ciconia",
+    "128": "black stork, Ciconia nigra",
+    "129": "spoonbill",
+    "130": "flamingo",
+    "131": "little blue heron, Egretta caerulea",
+    "132": "American egret, great white heron, Egretta albus",
+    "133": "bittern",
+    "134": "crane",
+    "135": "limpkin, Aramus pictus",
+    "136": "European gallinule, Porphyrio porphyrio",
+    "137": "American coot, marsh hen, mud hen, water hen, Fulica americana",
+    "138": "bustard",
+    "139": "ruddy turnstone, Arenaria interpres",
+    "140": "red-backed sandpiper, dunlin, Erolia alpina",
+    "141": "redshank, Tringa totanus",
+    "142": "dowitcher",
+    "143": "oystercatcher, oyster catcher",
+    "144": "pelican",
+    "145": "king penguin, Aptenodytes patagonica",
+    "146": "albatross, mollymawk",
+    "147": "grey whale, gray whale, devilfish, Eschrichtius gibbosus, Eschrichtius robustus",
+    "148": "killer whale, killer, orca, grampus, sea wolf, Orcinus orca",
+    "149": "dugong, Dugong dugon",
+    "150": "sea lion",
+    "151": "Chihuahua",
+    "152": "Japanese spaniel",
+    "153": "Maltese dog, Maltese terrier, Maltese",
+    "154": "Pekinese, Pekingese, Peke",
+    "155": "Shih-Tzu",
+    "156": "Blenheim spaniel",
+    "157": "papillon",
+    "158": "toy terrier",
+    "159": "Rhodesian ridgeback",
+    "160": "Afghan hound, Afghan",
+    "161": "basset, basset hound",
+    "162": "beagle",
+    "163": "bloodhound, sleuthhound",
+    "164": "bluetick",
+    "165": "black-and-tan coonhound",
+    "166": "Walker hound, Walker foxhound",
+    "167": "English foxhound",
+    "168": "redbone",
+    "169": "borzoi, Russian wolfhound",
+    "170": "Irish wolfhound",
+    "171": "Italian greyhound",
+    "172": "whippet",
+    "173": "Ibizan hound, Ibizan Podenco",
+    "174": "Norwegian elkhound, elkhound",
+    "175": "otterhound, otter hound",
+    "176": "Saluki, gazelle hound",
+    "177": "Scottish deerhound, deerhound",
+    "178": "Weimaraner",
+    "179": "Staffordshire bullterrier, Staffordshire bull terrier",
+    "180": "American Staffordshire terrier, Staffordshire terrier, American pit bull terrier, pit bull terrier",
+    "181": "Bedlington terrier",
+    "182": "Border terrier",
+    "183": "Kerry blue terrier",
+    "184": "Irish terrier",
+    "185": "Norfolk terrier",
+    "186": "Norwich terrier",
+    "187": "Yorkshire terrier",
+    "188": "wire-haired fox terrier",
+    "189": "Lakeland terrier",
+    "190": "Sealyham terrier, Sealyham",
+    "191": "Airedale, Airedale terrier",
+    "192": "cairn, cairn terrier",
+    "193": "Australian terrier",
+    "194": "Dandie Dinmont, Dandie Dinmont terrier",
+    "195": "Boston bull, Boston terrier",
+    "196": "miniature schnauzer",
+    "197": "giant schnauzer",
+    "198": "standard schnauzer",
+    "199": "Scotch terrier, Scottish terrier, Scottie",
+    "200": "Tibetan terrier, chrysanthemum dog",
+    "201": "silky terrier, Sydney silky",
+    "202": "soft-coated wheaten terrier",
+    "203": "West Highland white terrier",
+    "204": "Lhasa, Lhasa apso",
+    "205": "flat-coated retriever",
+    "206": "curly-coated retriever",
+    "207": "golden retriever",
+    "208": "Labrador retriever",
+    "209": "Chesapeake Bay retriever",
+    "210": "German short-haired pointer",
+    "211": "vizsla, Hungarian pointer",
+    "212": "English setter",
+    "213": "Irish setter, red setter",
+    "214": "Gordon setter",
+    "215": "Brittany spaniel",
+    "216": "clumber, clumber spaniel",
+    "217": "English springer, English springer spaniel",
+    "218": "Welsh springer spaniel",
+    "219": "cocker spaniel, English cocker spaniel, cocker",
+    "220": "Sussex spaniel",
+    "221": "Irish water spaniel",
+    "222": "kuvasz",
+    "223": "schipperke",
+    "224": "groenendael",
+    "225": "malinois",
+    "226": "briard",
+    "227": "kelpie",
+    "228": "komondor",
+    "229": "Old English sheepdog, bobtail",
+    "230": "Shetland sheepdog, Shetland sheep dog, Shetland",
+    "231": "collie",
+    "232": "Border collie",
+    "233": "Bouvier des Flandres, Bouviers des Flandres",
+    "234": "Rottweiler",
+    "235": "German shepherd, German shepherd dog, German police dog, alsatian",
+    "236": "Doberman, Doberman pinscher",
+    "237": "miniature pinscher",
+    "238": "Greater Swiss Mountain dog",
+    "239": "Bernese mountain dog",
+    "240": "Appenzeller",
+    "241": "EntleBucher",
+    "242": "boxer",
+    "243": "bull mastiff",
+    "244": "Tibetan mastiff",
+    "245": "French bulldog",
+    "246": "Great Dane",
+    "247": "Saint Bernard, St Bernard",
+    "248": "Eskimo dog, husky",
+    "249": "malamute, malemute, Alaskan malamute",
+    "250": "Siberian husky",
+    "251": "dalmatian, coach dog, carriage dog",
+    "252": "affenpinscher, monkey pinscher, monkey dog",
+    "253": "basenji",
+    "254": "pug, pug-dog",
+    "255": "Leonberg",
+    "256": "Newfoundland, Newfoundland dog",
+    "257": "Great Pyrenees",
+    "258": "Samoyed, Samoyede",
+    "259": "Pomeranian",
+    "260": "chow, chow chow",
+    "261": "keeshond",
+    "262": "Brabancon griffon",
+    "263": "Pembroke, Pembroke Welsh corgi",
+    "264": "Cardigan, Cardigan Welsh corgi",
+    "265": "toy poodle",
+    "266": "miniature poodle",
+    "267": "standard poodle",
+    "268": "Mexican hairless",
+    "269": "timber wolf, grey wolf, gray wolf, Canis lupus",
+    "270": "white wolf, Arctic wolf, Canis lupus tundrarum",
+    "271": "red wolf, maned wolf, Canis rufus, Canis niger",
+    "272": "coyote, prairie wolf, brush wolf, Canis latrans",
+    "273": "dingo, warrigal, warragal, Canis dingo",
+    "274": "dhole, Cuon alpinus",
+    "275": "African hunting dog, hyena dog, Cape hunting dog, Lycaon pictus",
+    "276": "hyena, hyaena",
+    "277": "red fox, Vulpes vulpes",
+    "278": "kit fox, Vulpes macrotis",
+    "279": "Arctic fox, white fox, Alopex lagopus",
+    "280": "grey fox, gray fox, Urocyon cinereoargenteus",
+    "281": "tabby, tabby cat",
+    "282": "tiger cat",
+    "283": "Persian cat",
+    "284": "Siamese cat, Siamese",
+    "285": "Egyptian cat",
+    "286": "cougar, puma, catamount, mountain lion, painter, panther, Felis concolor",
+    "287": "lynx, catamount",
+    "288": "leopard, Panthera pardus",
+    "289": "snow leopard, ounce, Panthera uncia",
+    "290": "jaguar, panther, Panthera onca, Felis onca",
+    "291": "lion, king of beasts, Panthera leo",
+    "292": "tiger, Panthera tigris",
+    "293": "cheetah, chetah, Acinonyx jubatus",
+    "294": "brown bear, bruin, Ursus arctos",
+    "295": "American black bear, black bear, Ursus americanus, Euarctos americanus",
+    "296": "ice bear, polar bear, Ursus Maritimus, Thalarctos maritimus",
+    "297": "sloth bear, Melursus ursinus, Ursus ursinus",
+    "298": "mongoose",
+    "299": "meerkat, mierkat",
+    "300": "tiger beetle",
+    "301": "ladybug, ladybeetle, lady beetle, ladybird, ladybird beetle",
+    "302": "ground beetle, carabid beetle",
+    "303": "long-horned beetle, longicorn, longicorn beetle",
+    "304": "leaf beetle, chrysomelid",
+    "305": "dung beetle",
+    "306": "rhinoceros beetle",
+    "307": "weevil",
+    "308": "fly",
+    "309": "bee",
+    "310": "ant, emmet, pismire",
+    "311": "grasshopper, hopper",
+    "312": "cricket",
+    "313": "walking stick, walkingstick, stick insect",
+    "314": "cockroach, roach",
+    "315": "mantis, mantid",
+    "316": "cicada, cicala",
+    "317": "leafhopper",
+    "318": "lacewing, lacewing fly",
+    "319": "dragonfly, darning needle, devils darning needle, sewing needle, snake feeder, snake doctor, mosquito hawk, skeeter hawk",
+    "320": "damselfly",
+    "321": "admiral",
+    "322": "ringlet, ringlet butterfly",
+    "323": "monarch, monarch butterfly, milkweed butterfly, Danaus plexippus",
+    "324": "cabbage butterfly",
+    "325": "sulphur butterfly, sulfur butterfly",
+    "326": "lycaenid, lycaenid butterfly",
+    "327": "starfish, sea star",
+    "328": "sea urchin",
+    "329": "sea cucumber, holothurian",
+    "330": "wood rabbit, cottontail, cottontail rabbit",
+    "331": "hare",
+    "332": "Angora, Angora rabbit",
+    "333": "hamster",
+    "334": "porcupine, hedgehog",
+    "335": "fox squirrel, eastern fox squirrel, Sciurus niger",
+    "336": "marmot",
+    "337": "beaver",
+    "338": "guinea pig, Cavia cobaya",
+    "339": "sorrel",
+    "340": "zebra",
+    "341": "hog, pig, grunter, squealer, Sus scrofa",
+    "342": "wild boar, boar, Sus scrofa",
+    "343": "warthog",
+    "344": "hippopotamus, hippo, river horse, Hippopotamus amphibius",
+    "345": "ox",
+    "346": "water buffalo, water ox, Asiatic buffalo, Bubalus bubalis",
+    "347": "bison",
+    "348": "ram, tup",
+    "349": "bighorn, bighorn sheep, cimarron, Rocky Mountain bighorn, Rocky Mountain sheep, Ovis canadensis",
+    "350": "ibex, Capra ibex",
+    "351": "hartebeest",
+    "352": "impala, Aepyceros melampus",
+    "353": "gazelle",
+    "354": "Arabian camel, dromedary, Camelus dromedarius",
+    "355": "llama",
+    "356": "weasel",
+    "357": "mink",
+    "358": "polecat, fitch, foulmart, foumart, Mustela putorius",
+    "359": "black-footed ferret, ferret, Mustela nigripes",
+    "360": "otter",
+    "361": "skunk, polecat, wood pussy",
+    "362": "badger",
+    "363": "armadillo",
+    "364": "three-toed sloth, ai, Bradypus tridactylus",
+    "365": "orangutan, orang, orangutang, Pongo pygmaeus",
+    "366": "gorilla, Gorilla gorilla",
+    "367": "chimpanzee, chimp, Pan troglodytes",
+    "368": "gibbon, Hylobates lar",
+    "369": "siamang, Hylobates syndactylus, Symphalangus syndactylus",
+    "370": "guenon, guenon monkey",
+    "371": "patas, hussar monkey, Erythrocebus patas",
+    "372": "baboon",
+    "373": "macaque",
+    "374": "langur",
+    "375": "colobus, colobus monkey",
+    "376": "proboscis monkey, Nasalis larvatus",
+    "377": "marmoset",
+    "378": "capuchin, ringtail, Cebus capucinus",
+    "379": "howler monkey, howler",
+    "380": "titi, titi monkey",
+    "381": "spider monkey, Ateles geoffroyi",
+    "382": "squirrel monkey, Saimiri sciureus",
+    "383": "Madagascar cat, ring-tailed lemur, Lemur catta",
+    "384": "indri, indris, Indri indri, Indri brevicaudatus",
+    "385": "Indian elephant, Elephas maximus",
+    "386": "African elephant, Loxodonta africana",
+    "387": "lesser panda, red panda, panda, bear cat, cat bear, Ailurus fulgens",
+    "388": "giant panda, panda, panda bear, coon bear, Ailuropoda melanoleuca",
+    "389": "barracouta, snoek",
+    "390": "eel",
+    "391": "coho, cohoe, coho salmon, blue jack, silver salmon, Oncorhynchus kisutch",
+    "392": "rock beauty, Holocanthus tricolor",
+    "393": "anemone fish",
+    "394": "sturgeon",
+    "395": "gar, garfish, garpike, billfish, Lepisosteus osseus",
+    "396": "lionfish",
+    "397": "puffer, pufferfish, blowfish, globefish",
+    "398": "abacus",
+    "399": "abaya",
+    "400": "academic gown, academic robe, judge robe",
+    "401": "accordion, piano accordion, squeeze box",
+    "402": "acoustic guitar",
+    "403": "aircraft carrier, carrier, flattop, attack aircraft carrier",
+    "404": "airliner",
+    "405": "airship, dirigible",
+    "406": "altar",
+    "407": "ambulance",
+    "408": "amphibian, amphibious vehicle",
+    "409": "analog clock",
+    "410": "apiary, bee house",
+    "411": "apron",
+    "412": "ashcan, trash can, garbage can, wastebin, ash bin, ash-bin, ashbin, dustbin, trash barrel, trash bin",
+    "413": "assault rifle, assault gun",
+    "414": "backpack, back pack, knapsack, packsack, rucksack, haversack",
+    "415": "bakery, bakeshop, bakehouse",
+    "416": "balance beam, beam",
+    "417": "balloon",
+    "418": "ballpoint, ballpoint pen, ballpen, Biro",
+    "419": "Band Aid",
+    "420": "banjo",
+    "421": "bannister, banister, balustrade, balusters, handrail",
+    "422": "barbell",
+    "423": "barber chair",
+    "424": "barbershop",
+    "425": "barn",
+    "426": "barometer",
+    "427": "barrel, cask",
+    "428": "barrow, garden cart, lawn cart, wheelbarrow",
+    "429": "baseball",
+    "430": "basketball",
+    "431": "bassinet",
+    "432": "bassoon",
+    "433": "bathing cap, swimming cap",
+    "434": "bath towel",
+    "435": "bathtub, bathing tub, bath, tub",
+    "436": "beach wagon, station wagon, wagon, estate car, beach waggon, station waggon, waggon",
+    "437": "beacon, lighthouse, beacon light, pharos",
+    "438": "beaker",
+    "439": "bearskin, busby, shako",
+    "440": "beer bottle",
+    "441": "beer glass",
+    "442": "bell cote, bell cot",
+    "443": "bib",
+    "444": "bicycle-built-for-two, tandem bicycle, tandem",
+    "445": "bikini, two-piece",
+    "446": "binder, ring-binder",
+    "447": "binoculars, field glasses, opera glasses",
+    "448": "birdhouse",
+    "449": "boathouse",
+    "450": "bobsled, bobsleigh, bob",
+    "451": "bolo tie, bolo, bola tie, bola",
+    "452": "bonnet, poke bonnet",
+    "453": "bookcase",
+    "454": "bookshop, bookstore, bookstall",
+    "455": "bottlecap",
+    "456": "bow",
+    "457": "bow tie, bow-tie, bowtie",
+    "458": "brass, memorial tablet, plaque",
+    "459": "brassiere, bra, bandeau",
+    "460": "breakwater, groin, groyne, mole, bulwark, seawall, jetty",
+    "461": "breastplate, aegis, egis",
+    "462": "broom",
+    "463": "bucket, pail",
+    "464": "buckle",
+    "465": "bulletproof vest",
+    "466": "bullet train, bullet",
+    "467": "butcher shop, meat market",
+    "468": "cab, hack, taxi, taxicab",
+    "469": "caldron, cauldron",
+    "470": "candle, taper, wax light",
+    "471": "cannon",
+    "472": "canoe",
+    "473": "can opener, tin opener",
+    "474": "cardigan",
+    "475": "car mirror",
+    "476": "carousel, carrousel, merry-go-round, roundabout, whirligig",
+    "477": "carpenters kit, tool kit",
+    "478": "carton",
+    "479": "car wheel",
+    "480": "cash machine, cash dispenser, automated teller machine, automatic teller machine, automated teller, automatic teller, ATM",
+    "481": "cassette",
+    "482": "cassette player",
+    "483": "castle",
+    "484": "catamaran",
+    "485": "CD player",
+    "486": "cello, violoncello",
+    "487": "cellular telephone, cellular phone, cellphone, cell, mobile phone",
+    "488": "chain",
+    "489": "chainlink fence",
+    "490": "chain mail, ring mail, mail, chain armor, chain armour, ring armor, ring armour",
+    "491": "chain saw, chainsaw",
+    "492": "chest",
+    "493": "chiffonier, commode",
+    "494": "chime, bell, gong",
+    "495": "china cabinet, china closet",
+    "496": "Christmas stocking",
+    "497": "church, church building",
+    "498": "cinema, movie theater, movie theatre, movie house, picture palace",
+    "499": "cleaver, meat cleaver, chopper",
+    "500": "cliff dwelling",
+    "501": "cloak",
+    "502": "clog, geta, patten, sabot",
+    "503": "cocktail shaker",
+    "504": "coffee mug",
+    "505": "coffeepot",
+    "506": "coil, spiral, volute, whorl, helix",
+    "507": "combination lock",
+    "508": "computer keyboard, keypad",
+    "509": "confectionery, confectionary, candy store",
+    "510": "container ship, containership, container vessel",
+    "511": "convertible",
+    "512": "corkscrew, bottle screw",
+    "513": "cornet, horn, trumpet, trump",
+    "514": "cowboy boot",
+    "515": "cowboy hat, ten-gallon hat",
+    "516": "cradle",
+    "517": "crane",
+    "518": "crash helmet",
+    "519": "crate",
+    "520": "crib, cot",
+    "521": "Crock Pot",
+    "522": "croquet ball",
+    "523": "crutch",
+    "524": "cuirass",
+    "525": "dam, dike, dyke",
+    "526": "desk",
+    "527": "desktop computer",
+    "528": "dial telephone, dial phone",
+    "529": "diaper, nappy, napkin",
+    "530": "digital clock",
+    "531": "digital watch",
+    "532": "dining table, board",
+    "533": "dishrag, dishcloth",
+    "534": "dishwasher, dish washer, dishwashing machine",
+    "535": "disk brake, disc brake",
+    "536": "dock, dockage, docking facility",
+    "537": "dogsled, dog sled, dog sleigh",
+    "538": "dome",
+    "539": "doormat, welcome mat",
+    "540": "drilling platform, offshore rig",
+    "541": "drum, membranophone, tympan",
+    "542": "drumstick",
+    "543": "dumbbell",
+    "544": "Dutch oven",
+    "545": "electric fan, blower",
+    "546": "electric guitar",
+    "547": "electric locomotive",
+    "548": "entertainment center",
+    "549": "envelope",
+    "550": "espresso maker",
+    "551": "face powder",
+    "552": "feather boa, boa",
+    "553": "file, file cabinet, filing cabinet",
+    "554": "fireboat",
+    "555": "fire engine, fire truck",
+    "556": "fire screen, fireguard",
+    "557": "flagpole, flagstaff",
+    "558": "flute, transverse flute",
+    "559": "folding chair",
+    "560": "football helmet",
+    "561": "forklift",
+    "562": "fountain",
+    "563": "fountain pen",
+    "564": "four-poster",
+    "565": "freight car",
+    "566": "French horn, horn",
+    "567": "frying pan, frypan, skillet",
+    "568": "fur coat",
+    "569": "garbage truck, dustcart",
+    "570": "gasmask, respirator, gas helmet",
+    "571": "gas pump, gasoline pump, petrol pump, island dispenser",
+    "572": "goblet",
+    "573": "go-kart",
+    "574": "golf ball",
+    "575": "golfcart, golf cart",
+    "576": "gondola",
+    "577": "gong, tam-tam",
+    "578": "gown",
+    "579": "grand piano, grand",
+    "580": "greenhouse, nursery, glasshouse",
+    "581": "grille, radiator grille",
+    "582": "grocery store, grocery, food market, market",
+    "583": "guillotine",
+    "584": "hair slide",
+    "585": "hair spray",
+    "586": "half track",
+    "587": "hammer",
+    "588": "hamper",
+    "589": "hand blower, blow dryer, blow drier, hair dryer, hair drier",
+    "590": "hand-held computer, hand-held microcomputer",
+    "591": "handkerchief, hankie, hanky, hankey",
+    "592": "hard disc, hard disk, fixed disk",
+    "593": "harmonica, mouth organ, harp, mouth harp",
+    "594": "harp",
+    "595": "harvester, reaper",
+    "596": "hatchet",
+    "597": "holster",
+    "598": "home theater, home theatre",
+    "599": "honeycomb",
+    "600": "hook, claw",
+    "601": "hoopskirt, crinoline",
+    "602": "horizontal bar, high bar",
+    "603": "horse cart, horse-cart",
+    "604": "hourglass",
+    "605": "iPod",
+    "606": "iron, smoothing iron",
+    "607": "jack-o-lantern",
+    "608": "jean, blue jean, denim",
+    "609": "jeep, landrover",
+    "610": "jersey, T-shirt, tee shirt",
+    "611": "jigsaw puzzle",
+    "612": "jinrikisha, ricksha, rickshaw",
+    "613": "joystick",
+    "614": "kimono",
+    "615": "knee pad",
+    "616": "knot",
+    "617": "lab coat, laboratory coat",
+    "618": "ladle",
+    "619": "lampshade, lamp shade",
+    "620": "laptop, laptop computer",
+    "621": "lawn mower, mower",
+    "622": "lens cap, lens cover",
+    "623": "letter opener, paper knife, paperknife",
+    "624": "library",
+    "625": "lifeboat",
+    "626": "lighter, light, igniter, ignitor",
+    "627": "limousine, limo",
+    "628": "liner, ocean liner",
+    "629": "lipstick, lip rouge",
+    "630": "Loafer",
+    "631": "lotion",
+    "632": "loudspeaker, speaker, speaker unit, loudspeaker system, speaker system",
+    "633": "loupe, jewelers loupe",
+    "634": "lumbermill, sawmill",
+    "635": "magnetic compass",
+    "636": "mailbag, postbag",
+    "637": "mailbox, letter box",
+    "638": "maillot",
+    "639": "maillot, tank suit",
+    "640": "manhole cover",
+    "641": "maraca",
+    "642": "marimba, xylophone",
+    "643": "mask",
+    "644": "matchstick",
+    "645": "maypole",
+    "646": "maze, labyrinth",
+    "647": "measuring cup",
+    "648": "medicine chest, medicine cabinet",
+    "649": "megalith, megalithic structure",
+    "650": "microphone, mike",
+    "651": "microwave, microwave oven",
+    "652": "military uniform",
+    "653": "milk can",
+    "654": "minibus",
+    "655": "miniskirt, mini",
+    "656": "minivan",
+    "657": "missile",
+    "658": "mitten",
+    "659": "mixing bowl",
+    "660": "mobile home, manufactured home",
+    "661": "Model T",
+    "662": "modem",
+    "663": "monastery",
+    "664": "monitor",
+    "665": "moped",
+    "666": "mortar",
+    "667": "mortarboard",
+    "668": "mosque",
+    "669": "mosquito net",
+    "670": "motor scooter, scooter",
+    "671": "mountain bike, all-terrain bike, off-roader",
+    "672": "mountain tent",
+    "673": "mouse, computer mouse",
+    "674": "mousetrap",
+    "675": "moving van",
+    "676": "muzzle",
+    "677": "nail",
+    "678": "neck brace",
+    "679": "necklace",
+    "680": "nipple",
+    "681": "notebook, notebook computer",
+    "682": "obelisk",
+    "683": "oboe, hautboy, hautbois",
+    "684": "ocarina, sweet potato",
+    "685": "odometer, hodometer, mileometer, milometer",
+    "686": "oil filter",
+    "687": "organ, pipe organ",
+    "688": "oscilloscope, scope, cathode-ray oscilloscope, CRO",
+    "689": "overskirt",
+    "690": "oxcart",
+    "691": "oxygen mask",
+    "692": "packet",
+    "693": "paddle, boat paddle",
+    "694": "paddlewheel, paddle wheel",
+    "695": "padlock",
+    "696": "paintbrush",
+    "697": "pajama, pyjama, pjs, jammies",
+    "698": "palace",
+    "699": "panpipe, pandean pipe, syrinx",
+    "700": "paper towel",
+    "701": "parachute, chute",
+    "702": "parallel bars, bars",
+    "703": "park bench",
+    "704": "parking meter",
+    "705": "passenger car, coach, carriage",
+    "706": "patio, terrace",
+    "707": "pay-phone, pay-station",
+    "708": "pedestal, plinth, footstall",
+    "709": "pencil box, pencil case",
+    "710": "pencil sharpener",
+    "711": "perfume, essence",
+    "712": "Petri dish",
+    "713": "photocopier",
+    "714": "pick, plectrum, plectron",
+    "715": "pickelhaube",
+    "716": "picket fence, paling",
+    "717": "pickup, pickup truck",
+    "718": "pier",
+    "719": "piggy bank, penny bank",
+    "720": "pill bottle",
+    "721": "pillow",
+    "722": "ping-pong ball",
+    "723": "pinwheel",
+    "724": "pirate, pirate ship",
+    "725": "pitcher, ewer",
+    "726": "plane, carpenters plane, woodworking plane",
+    "727": "planetarium",
+    "728": "plastic bag",
+    "729": "plate rack",
+    "730": "plow, plough",
+    "731": "plunger, plumbers helper",
+    "732": "Polaroid camera, Polaroid Land camera",
+    "733": "pole",
+    "734": "police van, police wagon, paddy wagon, patrol wagon, wagon, black Maria",
+    "735": "poncho",
+    "736": "pool table, billiard table, snooker table",
+    "737": "pop bottle, soda bottle",
+    "738": "pot, flowerpot",
+    "739": "potters wheel",
+    "740": "power drill",
+    "741": "prayer rug, prayer mat",
+    "742": "printer",
+    "743": "prison, prison house",
+    "744": "projectile, missile",
+    "745": "projector",
+    "746": "puck, hockey puck",
+    "747": "punching bag, punch bag, punching ball, punchball",
+    "748": "purse",
+    "749": "quill, quill pen",
+    "750": "quilt, comforter, comfort, puff",
+    "751": "racer, race car, racing car",
+    "752": "racket, racquet",
+    "753": "radiator",
+    "754": "radio, wireless",
+    "755": "radio telescope, radio reflector",
+    "756": "rain barrel",
+    "757": "recreational vehicle, RV, R.V.",
+    "758": "reel",
+    "759": "reflex camera",
+    "760": "refrigerator, icebox",
+    "761": "remote control, remote",
+    "762": "restaurant, eating house, eating place, eatery",
+    "763": "revolver, six-gun, six-shooter",
+    "764": "rifle",
+    "765": "rocking chair, rocker",
+    "766": "rotisserie",
+    "767": "rubber eraser, rubber, pencil eraser",
+    "768": "rugby ball",
+    "769": "rule, ruler",
+    "770": "running shoe",
+    "771": "safe",
+    "772": "safety pin",
+    "773": "saltshaker, salt shaker",
+    "774": "sandal",
+    "775": "sarong",
+    "776": "sax, saxophone",
+    "777": "scabbard",
+    "778": "scale, weighing machine",
+    "779": "school bus",
+    "780": "schooner",
+    "781": "scoreboard",
+    "782": "screen, CRT screen",
+    "783": "screw",
+    "784": "screwdriver",
+    "785": "seat belt, seatbelt",
+    "786": "sewing machine",
+    "787": "shield, buckler",
+    "788": "shoe shop, shoe-shop, shoe store",
+    "789": "shoji",
+    "790": "shopping basket",
+    "791": "shopping cart",
+    "792": "shovel",
+    "793": "shower cap",
+    "794": "shower curtain",
+    "795": "ski",
+    "796": "ski mask",
+    "797": "sleeping bag",
+    "798": "slide rule, slipstick",
+    "799": "sliding door",
+    "800": "slot, one-armed bandit",
+    "801": "snorkel",
+    "802": "snowmobile",
+    "803": "snowplow, snowplough",
+    "804": "soap dispenser",
+    "805": "soccer ball",
+    "806": "sock",
+    "807": "solar dish, solar collector, solar furnace",
+    "808": "sombrero",
+    "809": "soup bowl",
+    "810": "space bar",
+    "811": "space heater",
+    "812": "space shuttle",
+    "813": "spatula",
+    "814": "speedboat",
+    "815": "spider web, spiders web",
+    "816": "spindle",
+    "817": "sports car, sport car",
+    "818": "spotlight, spot",
+    "819": "stage",
+    "820": "steam locomotive",
+    "821": "steel arch bridge",
+    "822": "steel drum",
+    "823": "stethoscope",
+    "824": "stole",
+    "825": "stone wall",
+    "826": "stopwatch, stop watch",
+    "827": "stove",
+    "828": "strainer",
+    "829": "streetcar, tram, tramcar, trolley, trolley car",
+    "830": "stretcher",
+    "831": "studio couch, day bed",
+    "832": "stupa, tope",
+    "833": "submarine, pigboat, sub, U-boat",
+    "834": "suit, suit of clothes",
+    "835": "sundial",
+    "836": "sunglass",
+    "837": "sunglasses, dark glasses, shades",
+    "838": "sunscreen, sunblock, sun blocker",
+    "839": "suspension bridge",
+    "840": "swab, swob, mop",
+    "841": "sweatshirt",
+    "842": "swimming trunks, bathing trunks",
+    "843": "swing",
+    "844": "switch, electric switch, electrical switch",
+    "845": "syringe",
+    "846": "table lamp",
+    "847": "tank, army tank, armored combat vehicle, armoured combat vehicle",
+    "848": "tape player",
+    "849": "teapot",
+    "850": "teddy, teddy bear",
+    "851": "television, television system",
+    "852": "tennis ball",
+    "853": "thatch, thatched roof",
+    "854": "theater curtain, theatre curtain",
+    "855": "thimble",
+    "856": "thresher, thrasher, threshing machine",
+    "857": "throne",
+    "858": "tile roof",
+    "859": "toaster",
+    "860": "tobacco shop, tobacconist shop, tobacconist",
+    "861": "toilet seat",
+    "862": "torch",
+    "863": "totem pole",
+    "864": "tow truck, tow car, wrecker",
+    "865": "toyshop",
+    "866": "tractor",
+    "867": "trailer truck, tractor trailer, trucking rig, rig, articulated lorry, semi",
+    "868": "tray",
+    "869": "trench coat",
+    "870": "tricycle, trike, velocipede",
+    "871": "trimaran",
+    "872": "tripod",
+    "873": "triumphal arch",
+    "874": "trolleybus, trolley coach, trackless trolley",
+    "875": "trombone",
+    "876": "tub, vat",
+    "877": "turnstile",
+    "878": "typewriter keyboard",
+    "879": "umbrella",
+    "880": "unicycle, monocycle",
+    "881": "upright, upright piano",
+    "882": "vacuum, vacuum cleaner",
+    "883": "vase",
+    "884": "vault",
+    "885": "velvet",
+    "886": "vending machine",
+    "887": "vestment",
+    "888": "viaduct",
+    "889": "violin, fiddle",
+    "890": "volleyball",
+    "891": "waffle iron",
+    "892": "wall clock",
+    "893": "wallet, billfold, notecase, pocketbook",
+    "894": "wardrobe, closet, press",
+    "895": "warplane, military plane",
+    "896": "washbasin, handbasin, washbowl, lavabo, wash-hand basin",
+    "897": "washer, automatic washer, washing machine",
+    "898": "water bottle",
+    "899": "water jug",
+    "900": "water tower",
+    "901": "whiskey jug",
+    "902": "whistle",
+    "903": "wig",
+    "904": "window screen",
+    "905": "window shade",
+    "906": "Windsor tie",
+    "907": "wine bottle",
+    "908": "wing",
+    "909": "wok",
+    "910": "wooden spoon",
+    "911": "wool, woolen, woollen",
+    "912": "worm fence, snake fence, snake-rail fence, Virginia fence",
+    "913": "wreck",
+    "914": "yawl",
+    "915": "yurt",
+    "916": "web site, website, internet site, site",
+    "917": "comic book",
+    "918": "crossword puzzle, crossword",
+    "919": "street sign",
+    "920": "traffic light, traffic signal, stoplight",
+    "921": "book jacket, dust cover, dust jacket, dust wrapper",
+    "922": "menu",
+    "923": "plate",
+    "924": "guacamole",
+    "925": "consomme",
+    "926": "hot pot, hotpot",
+    "927": "trifle",
+    "928": "ice cream, icecream",
+    "929": "ice lolly, lolly, lollipop, popsicle",
+    "930": "French loaf",
+    "931": "bagel, beigel",
+    "932": "pretzel",
+    "933": "cheeseburger",
+    "934": "hotdog, hot dog, red hot",
+    "935": "mashed potato",
+    "936": "head cabbage",
+    "937": "broccoli",
+    "938": "cauliflower",
+    "939": "zucchini, courgette",
+    "940": "spaghetti squash",
+    "941": "acorn squash",
+    "942": "butternut squash",
+    "943": "cucumber, cuke",
+    "944": "artichoke, globe artichoke",
+    "945": "bell pepper",
+    "946": "cardoon",
+    "947": "mushroom",
+    "948": "Granny Smith",
+    "949": "strawberry",
+    "950": "orange",
+    "951": "lemon",
+    "952": "fig",
+    "953": "pineapple, ananas",
+    "954": "banana",
+    "955": "jackfruit, jak, jack",
+    "956": "custard apple",
+    "957": "pomegranate",
+    "958": "hay",
+    "959": "carbonara",
+    "960": "chocolate sauce, chocolate syrup",
+    "961": "dough",
+    "962": "meat loaf, meatloaf",
+    "963": "pizza, pizza pie",
+    "964": "potpie",
+    "965": "burrito",
+    "966": "red wine",
+    "967": "espresso",
+    "968": "cup",
+    "969": "eggnog",
+    "970": "alp",
+    "971": "bubble",
+    "972": "cliff, drop, drop-off",
+    "973": "coral reef",
+    "974": "geyser",
+    "975": "lakeside, lakeshore",
+    "976": "promontory, headland, head, foreland",
+    "977": "sandbar, sand bar",
+    "978": "seashore, coast, seacoast, sea-coast",
+    "979": "valley, vale",
+    "980": "volcano",
+    "981": "ballplayer, baseball player",
+    "982": "groom, bridegroom",
+    "983": "scuba diver",
+    "984": "rapeseed",
+    "985": "daisy",
+    "986": "yellow ladys slipper, yellow lady-slipper, Cypripedium calceolus, Cypripedium parviflorum",
+    "987": "corn",
+    "988": "acorn",
+    "989": "hip, rose hip, rosehip",
+    "990": "buckeye, horse chestnut, conker",
+    "991": "coral fungus",
+    "992": "agaric",
+    "993": "gyromitra",
+    "994": "stinkhorn, carrion fungus",
+    "995": "earthstar",
+    "996": "hen-of-the-woods, hen of the woods, Polyporus frondosus, Grifola frondosa",
+    "997": "bolete",
+    "998": "ear, spike, capitulum",
+    "999": "toilet tissue, toilet paper, bathroom tissue"
+  }
+}

DiCo-L-256/pipeline.py

@@ -0,0 +1,398 @@
+"""Hub custom pipeline: DiCoPipeline.
+Load with native Hugging Face diffusers and trust_remote_code=True.
+"""
+
+# Copyright 2026 The HuggingFace Team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from __future__ import annotations
+
+import inspect
+import json
+from pathlib import Path
+from typing import Dict, List, Optional, Tuple, Union
+
+import torch
+from diffusers.image_processor import VaeImageProcessor
+from diffusers.models import AutoencoderKL
+from diffusers.pipelines.pipeline_utils import DiffusionPipeline, ImagePipelineOutput
+from diffusers.schedulers import DDIMScheduler, KarrasDiffusionSchedulers
+from diffusers.utils.torch_utils import randn_tensor
+
+
+EXAMPLE_DOC_STRING = """
+    Examples:
+        ```py
+        >>> from pathlib import Path
+        >>> from diffusers import DiffusionPipeline
+        >>> import torch
+
+        >>> model_dir = Path("./DiCo-XL-256").resolve()
+        >>> pipe = DiffusionPipeline.from_pretrained(
+        ...     str(model_dir),
+        ...     local_files_only=True,
+        ...     custom_pipeline=str(model_dir / "pipeline.py"),
+        ...     trust_remote_code=True,
+        ...     torch_dtype=torch.bfloat16,
+        ... )
+        >>> pipe.to("cuda")
+
+        >>> image = pipe(
+        ...     class_labels="golden retriever",
+        ...     num_inference_steps=250,
+        ...     guidance_scale=1.4,
+        ...     generator=torch.Generator("cuda").manual_seed(0),
+        ... ).images[0]
+        ```
+"""
+
+
+class DiCoPipeline(DiffusionPipeline):
+    r"""
+    Pipeline for class-conditional image generation with DiCo (Diffusion ConvNet).
+
+    Parameters:
+        transformer ([`DiCoTransformer2DModel`]):
+            Class-conditional DiCo denoiser operating in VAE latent space.
+        vae ([`AutoencoderKL`]):
+            Variational autoencoder used to decode latents to pixels.
+        scheduler ([`DDIMScheduler`]):
+            Diffusion scheduler. Other [`KarrasDiffusionSchedulers`] can be swapped at inference time.
+        id2label (`dict[int, str]`, *optional*):
+            ImageNet class id to English label mapping. Values may contain comma-separated synonyms.
+    """
+
+    model_cpu_offload_seq = "transformer->vae"
+
+    @staticmethod
+    def prepare_extra_step_kwargs(
+        scheduler: KarrasDiffusionSchedulers,
+        generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
+        eta: float = 0.0,
+    ) -> Dict[str, object]:
+        kwargs: Dict[str, object] = {}
+        step_params = set(inspect.signature(scheduler.step).parameters.keys())
+        if "generator" in step_params:
+            kwargs["generator"] = generator
+        if "eta" in step_params:
+            kwargs["eta"] = eta
+        return kwargs
+
+    def __init__(
+        self,
+        transformer,
+        vae: AutoencoderKL,
+        scheduler: KarrasDiffusionSchedulers,
+        id2label: Optional[Dict[Union[int, str], str]] = None,
+    ):
+        super().__init__()
+        if scheduler is None:
+            scheduler = DDIMScheduler(
+                num_train_timesteps=1000,
+                beta_start=0.0001,
+                beta_end=0.02,
+                beta_schedule="linear",
+                clip_sample=False,
+                set_alpha_to_one=True,
+                steps_offset=0,
+                prediction_type="epsilon",
+            )
+        self.register_modules(transformer=transformer, vae=vae, scheduler=scheduler)
+        self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1)
+        self.image_processor = VaeImageProcessor(vae_scale_factor=self.vae_scale_factor)
+        self._id2label = self._normalize_id2label(id2label)
+        self.labels = self._build_label2id(self._id2label)
+        self._labels_loaded_from_model_index = bool(self._id2label)
+
+    @classmethod
+    def from_pretrained(cls, pretrained_model_name_or_path: str, **kwargs):
+        model_kwargs = dict(kwargs)
+        transformer_subfolder = model_kwargs.pop("transformer_subfolder", None)
+        scheduler_subfolder = model_kwargs.pop("scheduler_subfolder", None)
+        vae_subfolder = model_kwargs.pop("vae_subfolder", None)
+        scheduler_kwargs = model_kwargs.pop("scheduler_kwargs", {})
+        base_path = Path(pretrained_model_name_or_path)
+
+        if transformer_subfolder is None and (base_path / "transformer").exists():
+            transformer_subfolder = "transformer"
+        if scheduler_subfolder is None and (base_path / "scheduler").exists():
+            scheduler_subfolder = "scheduler"
+        if vae_subfolder is None and (base_path / "vae").exists():
+            vae_subfolder = "vae"
+
+        try:
+            return super().from_pretrained(pretrained_model_name_or_path, **kwargs)
+        except Exception:
+            transformer_path = str(base_path / transformer_subfolder) if transformer_subfolder else pretrained_model_name_or_path
+            from transformer.transformer_dico import DiCoTransformer2DModel
+            transformer = DiCoTransformer2DModel.from_pretrained(transformer_path, **model_kwargs)
+            try:
+                scheduler = DDIMScheduler.from_pretrained(
+                    pretrained_model_name_or_path,
+                    subfolder=scheduler_subfolder,
+                    **scheduler_kwargs,
+                )
+            except Exception:
+                scheduler = DDIMScheduler(
+                    num_train_timesteps=1000,
+                    beta_start=0.0001,
+                    beta_end=0.02,
+                    beta_schedule="linear",
+                    clip_sample=False,
+                    set_alpha_to_one=True,
+                    steps_offset=0,
+                    prediction_type="epsilon",
+                    **scheduler_kwargs,
+                )
+            try:
+                vae = AutoencoderKL.from_pretrained(
+                    pretrained_model_name_or_path,
+                    subfolder=vae_subfolder,
+                    **model_kwargs,
+                )
+            except Exception:
+                vae = AutoencoderKL.from_pretrained("stabilityai/sd-vae-ft-ema", **model_kwargs)
+            id2label = cls._read_id2label_from_model_index(str(base_path))
+            return cls(transformer=transformer, vae=vae, scheduler=scheduler, id2label=id2label)
+
+    def _ensure_labels_loaded(self) -> None:
+        if self._labels_loaded_from_model_index:
+            return
+        loaded = self._read_id2label_from_model_index(getattr(self.config, "_name_or_path", None))
+        if loaded:
+            self._id2label = loaded
+            self.labels = self._build_label2id(self._id2label)
+        self._labels_loaded_from_model_index = True
+
+    @staticmethod
+    def _normalize_id2label(id2label: Optional[Dict[Union[int, str], str]]) -> Dict[int, str]:
+        if not id2label:
+            return {}
+        return {int(key): value for key, value in id2label.items()}
+
+    @staticmethod
+    def _read_id2label_from_model_index(variant_path: Optional[str]) -> Dict[int, str]:
+        if not variant_path:
+            return {}
+        model_index_path = Path(variant_path).resolve() / "model_index.json"
+        if not model_index_path.exists():
+            return {}
+        raw = json.loads(model_index_path.read_text(encoding="utf-8"))
+        id2label = raw.get("id2label")
+        if not isinstance(id2label, dict):
+            return {}
+        return {int(key): value for key, value in id2label.items()}
+
+    @staticmethod
+    def _build_label2id(id2label: Dict[int, str]) -> Dict[str, int]:
+        label2id: Dict[str, int] = {}
+        for class_id, value in id2label.items():
+            for synonym in value.split(","):
+                synonym = synonym.strip()
+                if synonym:
+                    label2id[synonym] = int(class_id)
+        return dict(sorted(label2id.items()))
+
+    @property
+    def id2label(self) -> Dict[int, str]:
+        self._ensure_labels_loaded()
+        return self._id2label
+
+    def get_label_ids(self, label: Union[str, List[str]]) -> List[int]:
+        self._ensure_labels_loaded()
+        if not self.labels:
+            raise ValueError("No English labels loaded. Ensure `id2label` exists in model_index.json.")
+        if isinstance(label, str):
+            label = [label]
+        missing = [item for item in label if item not in self.labels]
+        if missing:
+            preview = ", ".join(list(self.labels.keys())[:8])
+            raise ValueError(f"Unknown English label(s): {missing}. Example valid labels: {preview}, ...")
+        return [self.labels[item] for item in label]
+
+    def _normalize_class_labels(
+        self,
+        class_labels: Union[int, str, List[Union[int, str]], torch.LongTensor],
+    ) -> torch.LongTensor:
+        if torch.is_tensor(class_labels):
+            return class_labels.to(device=self._execution_device, dtype=torch.long).reshape(-1)
+        if isinstance(class_labels, int):
+            class_label_ids = [class_labels]
+        elif isinstance(class_labels, str):
+            class_label_ids = self.get_label_ids(class_labels)
+        elif class_labels and isinstance(class_labels[0], str):
+            class_label_ids = self.get_label_ids(class_labels)
+        else:
+            class_label_ids = list(class_labels)
+        return torch.tensor(class_label_ids, device=self._execution_device, dtype=torch.long).reshape(-1)
+
+    def _default_image_size(self) -> int:
+        return int(self.transformer.config.input_size) * self.vae_scale_factor
+
+    def check_inputs(
+        self,
+        height: int,
+        width: int,
+        num_inference_steps: int,
+        output_type: str,
+    ) -> None:
+        if num_inference_steps < 1:
+            raise ValueError("num_inference_steps must be >= 1.")
+        if output_type not in {"pil", "np", "pt", "latent"}:
+            raise ValueError("output_type must be one of: 'pil', 'np', 'pt', 'latent'.")
+        if height % self.vae_scale_factor != 0 or width % self.vae_scale_factor != 0:
+            raise ValueError(
+                f"height and width must be divisible by the VAE downsample factor {self.vae_scale_factor}."
+            )
+        latent_height = height // self.vae_scale_factor
+        latent_width = width // self.vae_scale_factor
+        expected_size = int(self.transformer.config.input_size)
+        if latent_height != expected_size or latent_width != expected_size:
+            raise ValueError(
+                f"Requested latent size {(latent_height, latent_width)} does not match the pretrained "
+                f"transformer input_size={expected_size}. Use height=width={self._default_image_size()}."
+            )
+
+    def prepare_latents(
+        self,
+        batch_size: int,
+        height: int,
+        width: int,
+        dtype: torch.dtype,
+        device: torch.device,
+        generator: Optional[Union[torch.Generator, List[torch.Generator]]],
+    ) -> torch.Tensor:
+        latent_height = height // self.vae_scale_factor
+        latent_width = width // self.vae_scale_factor
+        return randn_tensor(
+            (batch_size, self.transformer.config.in_channels, latent_height, latent_width),
+            generator=generator,
+            device=device,
+            dtype=dtype,
+        )
+
+    @staticmethod
+    def _expand_timestep(timestep, batch: int, device: torch.device) -> torch.Tensor:
+        if not torch.is_tensor(timestep):
+            timestep = torch.tensor([timestep], dtype=torch.long, device=device)
+        elif timestep.ndim == 0:
+            timestep = timestep[None].to(device=device)
+        return timestep.expand(batch)
+
+    @staticmethod
+    def _prepare_model_output_for_scheduler(
+        model_output: torch.Tensor,
+        latent_channels: int,
+        scheduler: KarrasDiffusionSchedulers,
+    ) -> torch.Tensor:
+        if model_output.shape[1] != 2 * latent_channels:
+            return model_output
+        variance_type = getattr(scheduler.config, "variance_type", None)
+        if scheduler.__class__.__name__ == "DDPMScheduler" and variance_type in ("learned", "learned_range"):
+            return model_output
+        model_output, _ = torch.split(model_output, latent_channels, dim=1)
+        return model_output
+
+    def decode_latents(self, latents: torch.Tensor, output_type: str = "pil"):
+        if output_type == "latent":
+            return latents
+        scaling_factor = getattr(self.vae.config, "scaling_factor", 0.18215)
+        image = self.vae.decode(latents / scaling_factor).sample
+        if output_type == "pt":
+            return image
+        return self.image_processor.postprocess(image, output_type=output_type)
+
+    @torch.inference_mode()
+    def __call__(
+        self,
+        class_labels: Union[int, str, List[Union[int, str]], torch.LongTensor],
+        height: Optional[int] = None,
+        width: Optional[int] = None,
+        num_inference_steps: int = 250,
+        guidance_scale: float = 1.0,
+        eta: float = 0.0,
+        generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
+        output_type: str = "pil",
+        return_dict: bool = True,
+    ) -> Union[ImagePipelineOutput, Tuple]:
+        default_size = self._default_image_size()
+        height = int(height or default_size)
+        width = int(width or default_size)
+        self.check_inputs(height, width, num_inference_steps, output_type)
+
+        device = self._execution_device
+        model_dtype = next(self.transformer.parameters()).dtype
+        class_labels_tensor = self._normalize_class_labels(class_labels)
+        batch_size = class_labels_tensor.numel()
+        latent_channels = int(self.transformer.config.in_channels)
+        null_class_val = int(self.transformer.config.num_classes)
+        do_cfg = guidance_scale > 1.0
+
+        latents = self.prepare_latents(
+            batch_size=batch_size,
+            height=height,
+            width=width,
+            dtype=model_dtype,
+            device=device,
+            generator=generator,
+        )
+        latent_model_input = torch.cat([latents] * 2) if do_cfg else latents
+
+        class_labels_input = class_labels_tensor
+        if do_cfg:
+            class_null = torch.full_like(class_labels_tensor, null_class_val)
+            class_labels_input = torch.cat([class_labels_tensor, class_null], dim=0)
+
+        self.scheduler.set_timesteps(num_inference_steps, device=device)
+        extra_step_kwargs = self.prepare_extra_step_kwargs(self.scheduler, generator=generator, eta=eta)
+
+        for t in self.progress_bar(self.scheduler.timesteps):
+            if do_cfg:
+                half = latent_model_input[: len(latent_model_input) // 2]
+                latent_model_input = torch.cat([half, half], dim=0)
+            latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)
+            timesteps = self._expand_timestep(t, latent_model_input.shape[0], latent_model_input.device)
+
+            noise_pred = self.transformer(
+                hidden_states=latent_model_input,
+                timestep=timesteps,
+                class_labels=class_labels_input,
+                return_dict=True,
+            ).sample
+
+            if do_cfg:
+                eps, rest = noise_pred[:, :latent_channels], noise_pred[:, latent_channels:]
+                cond_eps, uncond_eps = torch.split(eps, len(eps) // 2, dim=0)
+                half_eps = uncond_eps + guidance_scale * (cond_eps - uncond_eps)
+                eps = torch.cat([half_eps, half_eps], dim=0)
+                noise_pred = torch.cat([eps, rest], dim=1)
+
+            model_output = self._prepare_model_output_for_scheduler(noise_pred, latent_channels, self.scheduler)
+            latent_model_input = self.scheduler.step(
+                model_output, t, latent_model_input, return_dict=True, **extra_step_kwargs
+            ).prev_sample
+
+        if do_cfg:
+            latents, _ = latent_model_input.chunk(2, dim=0)
+        else:
+            latents = latent_model_input
+
+        image = self.decode_latents(latents, output_type=output_type)
+        self.maybe_free_model_hooks()
+        if not return_dict:
+            return (image,)
+        return ImagePipelineOutput(images=image)
+
+
+DiCoPipelineOutput = ImagePipelineOutput

DiCo-L-256/scheduler/scheduler_config.json

@@ -0,0 +1,12 @@
+{
+  "_class_name": "DDIMScheduler",
+  "_diffusers_version": "0.35.1",
+  "num_train_timesteps": 1000,
+  "beta_start": 0.0001,
+  "beta_end": 0.02,
+  "beta_schedule": "linear",
+  "clip_sample": false,
+  "set_alpha_to_one": true,
+  "steps_offset": 0,
+  "prediction_type": "epsilon"
+}

DiCo-L-256/transformer/config.json

@@ -0,0 +1,14 @@
+{
+  "_class_name": "DiCoTransformer2DModel",
+  "_diffusers_version": "0.38.0",
+  "class_dropout_prob": 0.1,
+  "depth": null,
+  "hidden_size": 416,
+  "in_channels": 4,
+  "input_size": 32,
+  "learn_sigma": true,
+  "mlp_ratio": 2.0,
+  "model_type": "DiCo-L",
+  "num_class_embeds": null,
+  "num_classes": 1000
+}

DiCo-L-256/transformer/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7469911f0c5515536c89563c0f48110466d4c02fcdc9775ab73d4b14151ae6a
+size 1855656952

DiCo-L-256/transformer/transformer_dico.py

@@ -0,0 +1,479 @@
+# Copyright 2026 The HuggingFace Team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from __future__ import annotations
+
+import argparse
+import math
+from collections.abc import Mapping
+from typing import Dict, Literal, Optional, Tuple
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+from diffusers.configuration_utils import ConfigMixin, register_to_config
+from diffusers.models.modeling_outputs import Transformer2DModelOutput
+from diffusers.models.modeling_utils import ModelMixin
+
+
+DICO_PRESET_CONFIGS: Dict[str, Dict[str, object]] = {
+    "DiCo-S": {
+        "hidden_size": 128,
+        "depth": [5, 4, 4, 4, 4],
+        "mlp_ratio": 2.0,
+    },
+    "DiCo-B": {
+        "hidden_size": 256,
+        "depth": [5, 4, 4, 4, 4],
+        "mlp_ratio": 2.0,
+    },
+    "DiCo-L": {
+        "hidden_size": 352,
+        "depth": [9, 8, 9, 8, 9],
+        "mlp_ratio": 2.0,
+    },
+    "DiCo-XL": {
+        "hidden_size": 416,
+        "depth": [9, 9, 10, 9, 9],
+        "mlp_ratio": 2.0,
+    },
+    "DiCo-H": {
+        "hidden_size": 416,
+        "depth": [14, 12, 10, 12, 14],
+        "mlp_ratio": 4.0,
+    },
+}
+
+
+def remap_legacy_state_dict(state_dict: Dict[str, torch.Tensor]) -> Dict[str, torch.Tensor]:
+    """Map wrapper/backbone keys from legacy checkpoints to native model keys."""
+    remapped: Dict[str, torch.Tensor] = {}
+    for key, value in state_dict.items():
+        new_key = key
+        for prefix in ("transformer.", "model.", "net."):
+            if new_key.startswith(prefix):
+                new_key = new_key[len(prefix) :]
+                break
+        remapped[new_key] = value
+    return remapped
+
+
+def infer_learn_sigma(state_dict: Dict[str, torch.Tensor], in_channels: int = 4) -> bool:
+    weight = state_dict.get("final_layer.out_proj.weight")
+    if weight is None:
+        return True
+    return int(weight.shape[0]) == in_channels * 2
+
+
+def config_from_legacy(config: Dict[str, object]) -> Dict[str, object]:
+    """Build native config kwargs from a legacy config.json dict."""
+    model_type = config.get("model_type") or config.get("model_name") or config.get("model")
+    if model_type not in DICO_PRESET_CONFIGS:
+        raise ValueError(f"Unknown DiCo preset '{model_type}'. Known: {list(DICO_PRESET_CONFIGS)}")
+
+    preset = dict(DICO_PRESET_CONFIGS[model_type])
+    preset["num_classes"] = int(config.get("num_class_embeds") or config.get("num_classes") or 1000)
+    preset["model_type"] = model_type
+    preset["input_size"] = int(config.get("input_size") or config.get("sample_size") or 32)
+    if config.get("learn_sigma") is not None:
+        preset["learn_sigma"] = bool(config["learn_sigma"])
+    return preset
+
+
+def modulate(x: torch.Tensor, shift: torch.Tensor, scale: torch.Tensor) -> torch.Tensor:
+    return x * (1 + scale.unsqueeze(-1).unsqueeze(-1)) + shift.unsqueeze(-1).unsqueeze(-1)
+
+
+class LayerNorm2d(nn.LayerNorm):
+    def __init__(self, num_channels: int, eps: float = 1e-6, affine: bool = True):
+        super().__init__(num_channels, eps=eps, elementwise_affine=affine)
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        x = x.permute(0, 2, 3, 1)
+        x = F.layer_norm(x, self.normalized_shape, self.weight, self.bias, self.eps)
+        return x.permute(0, 3, 1, 2)
+
+
+class DiCoTimestepEmbedder(nn.Module):
+    def __init__(self, hidden_size: int, frequency_embedding_size: int = 256):
+        super().__init__()
+        self.mlp = nn.Sequential(
+            nn.Linear(frequency_embedding_size, hidden_size, bias=True),
+            nn.SiLU(),
+            nn.Linear(hidden_size, hidden_size, bias=True),
+        )
+        self.frequency_embedding_size = frequency_embedding_size
+
+    @staticmethod
+    def timestep_embedding(t: torch.Tensor, dim: int, max_period: int = 10000) -> torch.Tensor:
+        half = dim // 2
+        freqs = torch.exp(
+            -math.log(max_period) * torch.arange(start=0, end=half, dtype=torch.float32) / half
+        ).to(device=t.device)
+        args = t[:, None].float() * freqs[None]
+        embedding = torch.cat([torch.cos(args), torch.sin(args)], dim=-1)
+        if dim % 2:
+            embedding = torch.cat([embedding, torch.zeros_like(embedding[:, :1])], dim=-1)
+        return embedding
+
+    def forward(self, t: torch.Tensor) -> torch.Tensor:
+        t_freq = self.timestep_embedding(t, self.frequency_embedding_size)
+        weight_dtype = self.mlp[0].weight.dtype
+        return self.mlp(t_freq.to(dtype=weight_dtype))
+
+
+class DiCoLabelEmbedder(nn.Module):
+    def __init__(self, num_classes: int, hidden_size: int, dropout_prob: float):
+        super().__init__()
+        use_cfg_embedding = dropout_prob > 0
+        self.embedding_table = nn.Embedding(num_classes + use_cfg_embedding, hidden_size)
+        self.num_classes = num_classes
+        self.dropout_prob = dropout_prob
+
+    def token_drop(self, labels: torch.Tensor, force_drop_ids: Optional[torch.Tensor] = None) -> torch.Tensor:
+        if force_drop_ids is None:
+            drop_ids = torch.rand(labels.shape[0], device=labels.device) < self.dropout_prob
+        else:
+            drop_ids = force_drop_ids == 1
+        return torch.where(drop_ids, self.num_classes, labels)
+
+    def forward(
+        self,
+        labels: torch.Tensor,
+        train: bool,
+        force_drop_ids: Optional[torch.Tensor] = None,
+    ) -> torch.Tensor:
+        use_dropout = self.dropout_prob > 0
+        if (train and use_dropout) or (force_drop_ids is not None):
+            labels = self.token_drop(labels, force_drop_ids)
+        return self.embedding_table(labels)
+
+
+class DiCoMultiScaleLabelEmbedder(nn.Module):
+    def __init__(
+        self,
+        num_classes: int,
+        hidden_size_0: int,
+        hidden_size_1: int,
+        hidden_size_2: int,
+        dropout_prob: float,
+    ):
+        super().__init__()
+        use_cfg_embedding = dropout_prob > 0
+        self.embedding_table_0 = nn.Embedding(num_classes + use_cfg_embedding, hidden_size_0)
+        self.embedding_table_1 = nn.Embedding(num_classes + use_cfg_embedding, hidden_size_1)
+        self.embedding_table_2 = nn.Embedding(num_classes + use_cfg_embedding, hidden_size_2)
+        self.num_classes = num_classes
+        self.dropout_prob = dropout_prob
+
+    def token_drop(self, labels: torch.Tensor, force_drop_ids: Optional[torch.Tensor] = None) -> torch.Tensor:
+        if force_drop_ids is None:
+            drop_ids = torch.rand(labels.shape[0], device=labels.device) < self.dropout_prob
+        else:
+            drop_ids = force_drop_ids == 1
+        return torch.where(drop_ids, self.num_classes, labels)
+
+    def forward(
+        self,
+        labels: torch.Tensor,
+        train: bool,
+        force_drop_ids: Optional[torch.Tensor] = None,
+    ) -> Tuple[torch.Tensor, torch.Tensor, torch.Tensor]:
+        use_dropout = self.dropout_prob > 0
+        if (train and use_dropout) or (force_drop_ids is not None):
+            labels = self.token_drop(labels, force_drop_ids)
+        return (
+            self.embedding_table_0(labels),
+            self.embedding_table_1(labels),
+            self.embedding_table_2(labels),
+        )
+
+
+class DiCoBlock(nn.Module):
+    def __init__(self, hidden_size: int, mlp_ratio: float = 4.0):
+        super().__init__()
+        self.conv1 = nn.Conv2d(hidden_size, hidden_size, kernel_size=1, padding=0, stride=1, groups=1, bias=True)
+        self.conv2 = nn.Conv2d(
+            hidden_size, hidden_size, kernel_size=3, padding=1, stride=1, groups=hidden_size, bias=True
+        )
+        self.conv3 = nn.Conv2d(hidden_size, hidden_size, kernel_size=1, padding=0, stride=1, groups=1, bias=True)
+        self.ca = nn.Sequential(
+            nn.AdaptiveAvgPool2d(1),
+            nn.Conv2d(hidden_size, hidden_size, kernel_size=1, padding=0, stride=1, groups=1, bias=True),
+            nn.Sigmoid(),
+        )
+        ffn_channel = int(mlp_ratio * hidden_size)
+        self.conv4 = nn.Conv2d(hidden_size, ffn_channel, kernel_size=1, padding=0, stride=1, groups=1, bias=True)
+        self.conv5 = nn.Conv2d(ffn_channel, hidden_size, kernel_size=1, padding=0, stride=1, groups=1, bias=True)
+        self.norm1 = LayerNorm2d(hidden_size, affine=False, eps=1e-6)
+        self.norm2 = LayerNorm2d(hidden_size, affine=False, eps=1e-6)
+        self.adaLN_modulation = nn.Sequential(nn.SiLU(), nn.Linear(hidden_size, 6 * hidden_size, bias=True))
+
+    def forward(self, inp: torch.Tensor, c: torch.Tensor) -> torch.Tensor:
+        shift_msa, scale_msa, gate_msa, shift_mlp, scale_mlp, gate_mlp = self.adaLN_modulation(c).chunk(6, dim=1)
+        x = modulate(self.norm1(inp), shift_msa, scale_msa)
+        x = F.gelu(self.conv2(self.conv1(x)))
+        x = x * self.ca(x)
+        x = self.conv3(x)
+        x = inp + gate_msa.unsqueeze(-1).unsqueeze(-1) * x
+        x = x + gate_mlp.unsqueeze(-1).unsqueeze(-1) * self.conv5(
+            F.gelu(self.conv4(modulate(self.norm2(x), shift_mlp, scale_mlp)))
+        )
+        return x
+
+
+class DiCoFinalLayer(nn.Module):
+    def __init__(self, hidden_size: int, out_channels: int):
+        super().__init__()
+        self.norm_final = LayerNorm2d(hidden_size, affine=False, eps=1e-6)
+        self.out_proj = nn.Conv2d(hidden_size, out_channels, kernel_size=3, stride=1, padding=1, bias=True)
+        self.adaLN_modulation = nn.Sequential(nn.SiLU(), nn.Linear(hidden_size, 2 * hidden_size, bias=True))
+
+    def forward(self, x: torch.Tensor, c: torch.Tensor) -> torch.Tensor:
+        shift, scale = self.adaLN_modulation(c).chunk(2, dim=1)
+        x = modulate(self.norm_final(x), shift, scale)
+        return self.out_proj(x)
+
+
+class OverlapPatchEmbed(nn.Module):
+    def __init__(self, in_c: int = 3, embed_dim: int = 48, bias: bool = False):
+        super().__init__()
+        self.proj = nn.Conv2d(in_c, embed_dim, kernel_size=3, stride=1, padding=1, bias=bias)
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        return self.proj(x)
+
+
+class Downsample(nn.Module):
+    def __init__(self, n_feat: int):
+        super().__init__()
+        self.body = nn.Sequential(
+            nn.Conv2d(n_feat, n_feat // 2, kernel_size=3, stride=1, padding=1, bias=False),
+            nn.PixelUnshuffle(2),
+        )
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        return self.body(x)
+
+
+class Upsample(nn.Module):
+    def __init__(self, n_feat: int):
+        super().__init__()
+        self.body = nn.Sequential(
+            nn.Conv2d(n_feat, n_feat * 2, kernel_size=3, stride=1, padding=1, bias=False),
+            nn.PixelShuffle(2),
+        )
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        return self.body(x)
+
+
+class DiCoTransformer2DModel(ModelMixin, ConfigMixin):
+    r"""
+    DiCo (Diffusion ConvNet) denoiser for class-conditional latent diffusion.
+
+    ConvNet U-Net backbone with multi-scale adaLN conditioning, operating on VAE latents.
+    """
+
+    _supports_gradient_checkpointing = True
+
+    @register_to_config
+    def __init__(
+        self,
+        input_size: int = 32,
+        in_channels: int = 4,
+        hidden_size: int = 416,
+        depth: Optional[list[int]] = None,
+        mlp_ratio: float = 2.0,
+        class_dropout_prob: float = 0.1,
+        num_classes: int = 1000,
+        learn_sigma: bool = True,
+        model_type: str | None = None,
+        num_class_embeds: int | None = None,
+    ):
+        super().__init__()
+        if num_class_embeds is not None:
+            num_classes = int(num_class_embeds)
+        if model_type in DICO_PRESET_CONFIGS:
+            preset = DICO_PRESET_CONFIGS[model_type]
+            hidden_size = int(preset["hidden_size"])
+            depth = list(preset["depth"])
+            mlp_ratio = float(preset["mlp_ratio"])
+
+        if depth is None:
+            depth = [9, 9, 10, 9, 9]
+
+        self.learn_sigma = learn_sigma
+        self.in_channels = in_channels
+        self.out_channels = in_channels * 2 if learn_sigma else in_channels
+        self.num_classes = num_classes
+        self.gradient_checkpointing = False
+
+        self.x_embedder = OverlapPatchEmbed(in_channels, hidden_size, bias=True)
+        self.t_embedder_1 = DiCoTimestepEmbedder(hidden_size)
+        self.y_embedder = DiCoMultiScaleLabelEmbedder(
+            num_classes, hidden_size, hidden_size * 2, hidden_size * 4, class_dropout_prob
+        )
+        self.t_embedder_2 = DiCoTimestepEmbedder(hidden_size * 2)
+        self.t_embedder_3 = DiCoTimestepEmbedder(hidden_size * 4)
+
+        self.encoder_level_1 = nn.ModuleList([DiCoBlock(hidden_size, mlp_ratio) for _ in range(depth[0])])
+        self.down1_2 = Downsample(hidden_size)
+        self.encoder_level_2 = nn.ModuleList([DiCoBlock(hidden_size * 2, mlp_ratio) for _ in range(depth[1])])
+        self.down2_3 = Downsample(hidden_size * 2)
+        self.latent = nn.ModuleList([DiCoBlock(hidden_size * 4, mlp_ratio) for _ in range(depth[2])])
+        self.up3_2 = Upsample(int(hidden_size * 4))
+        self.reduce_chan_level2 = nn.Conv2d(int(hidden_size * 4), int(hidden_size * 2), kernel_size=1, bias=True)
+        self.decoder_level_2 = nn.ModuleList([DiCoBlock(hidden_size * 2, mlp_ratio) for _ in range(depth[3])])
+        self.up2_1 = Upsample(int(hidden_size * 2))
+        self.reduce_chan_level1 = nn.Conv2d(int(hidden_size * 2), int(hidden_size * 2), kernel_size=1, bias=True)
+        self.decoder_level_1 = nn.ModuleList([DiCoBlock(hidden_size * 2, mlp_ratio) for _ in range(depth[4])])
+        self.final_layer = DiCoFinalLayer(hidden_size * 2, self.out_channels)
+        self.initialize_weights()
+
+    def initialize_weights(self) -> None:
+        def _basic_init(module: nn.Module):
+            if isinstance(module, (nn.Linear, nn.Conv2d)):
+                torch.nn.init.xavier_uniform_(module.weight)
+                if module.bias is not None:
+                    nn.init.constant_(module.bias, 0)
+
+        self.apply(_basic_init)
+        w = self.x_embedder.proj.weight.data
+        nn.init.xavier_uniform_(w.view([w.shape[0], -1]))
+        nn.init.constant_(self.x_embedder.proj.bias, 0)
+        nn.init.normal_(self.y_embedder.embedding_table_0.weight, std=0.02)
+        nn.init.normal_(self.y_embedder.embedding_table_1.weight, std=0.02)
+        nn.init.normal_(self.y_embedder.embedding_table_2.weight, std=0.02)
+        for embedder in (self.t_embedder_1, self.t_embedder_2, self.t_embedder_3):
+            nn.init.normal_(embedder.mlp[0].weight, std=0.02)
+            nn.init.normal_(embedder.mlp[2].weight, std=0.02)
+
+        blocks = (
+            self.encoder_level_1
+            + self.encoder_level_2
+            + self.latent
+            + self.decoder_level_2
+            + self.decoder_level_1
+        )
+        for block in blocks:
+            nn.init.constant_(block.adaLN_modulation[-1].weight, 0)
+            nn.init.constant_(block.adaLN_modulation[-1].bias, 0)
+        nn.init.constant_(self.final_layer.adaLN_modulation[-1].weight, 0)
+        nn.init.constant_(self.final_layer.adaLN_modulation[-1].bias, 0)
+        nn.init.constant_(self.final_layer.out_proj.weight, 0)
+        nn.init.constant_(self.final_layer.out_proj.bias, 0)
+
+    def _run_block(self, block: DiCoBlock, x: torch.Tensor, c: torch.Tensor) -> torch.Tensor:
+        if self.training and self.gradient_checkpointing:
+            return torch.utils.checkpoint.checkpoint(block, x, c, use_reentrant=False)
+        return block(x, c)
+
+    def forward(
+        self,
+        hidden_states: torch.Tensor,
+        timestep: torch.LongTensor,
+        class_labels: torch.LongTensor,
+        force_drop_ids: Optional[torch.Tensor] = None,
+        return_dict: bool = True,
+    ) -> Transformer2DModelOutput | Tuple:
+        timestep = torch.as_tensor(timestep, device=hidden_states.device)
+        if timestep.ndim == 0:
+            timestep = timestep.repeat(hidden_states.shape[0])
+        else:
+            timestep = timestep.reshape(-1)
+            if timestep.shape[0] == 1 and hidden_states.shape[0] > 1:
+                timestep = timestep.repeat(hidden_states.shape[0])
+
+        x = self.x_embedder(hidden_states)
+        t1 = self.t_embedder_1(timestep)
+        y1, y2, y3 = self.y_embedder(class_labels, self.training, force_drop_ids=force_drop_ids)
+        c1 = t1 + y1
+        c2 = self.t_embedder_2(timestep) + y2
+        c3 = self.t_embedder_3(timestep) + y3
+
+        out_enc_level1 = x
+        for block in self.encoder_level_1:
+            out_enc_level1 = self._run_block(block, out_enc_level1, c1)
+        out_enc_level2 = self.down1_2(out_enc_level1)
+        for block in self.encoder_level_2:
+            out_enc_level2 = self._run_block(block, out_enc_level2, c2)
+        latent = self.down2_3(out_enc_level2)
+        for block in self.latent:
+            latent = self._run_block(block, latent, c3)
+
+        inp_dec_level2 = self.reduce_chan_level2(torch.cat([self.up3_2(latent), out_enc_level2], dim=1))
+        for block in self.decoder_level_2:
+            inp_dec_level2 = self._run_block(block, inp_dec_level2, c2)
+        inp_dec_level1 = self.reduce_chan_level1(torch.cat([self.up2_1(inp_dec_level2), out_enc_level1], dim=1))
+        for block in self.decoder_level_1:
+            inp_dec_level1 = self._run_block(block, inp_dec_level1, c2)
+
+        output = self.final_layer(inp_dec_level1, c2)
+        if not return_dict:
+            return (output,)
+        return Transformer2DModelOutput(sample=output)
+
+    @classmethod
+    def from_dico_checkpoint(
+        cls,
+        checkpoint_path: str,
+        weights: Literal["model", "ema"] = "ema",
+        map_location: str = "cpu",
+        strict: bool = True,
+        model_type: str | None = None,
+    ) -> Tuple["DiCoTransformer2DModel", Dict[str, object]]:
+        checkpoint = torch.load(checkpoint_path, map_location=map_location, weights_only=False)
+        state_dict = checkpoint
+        if isinstance(checkpoint, Mapping):
+            if weights in checkpoint:
+                state_dict = checkpoint[weights]
+            elif "state_dict" in checkpoint:
+                state_dict = checkpoint["state_dict"]
+
+        state_dict = remap_legacy_state_dict(state_dict)
+
+        ckpt_args = checkpoint.get("args") if isinstance(checkpoint, Mapping) else None
+        args_dict: Dict[str, object] = {}
+        if ckpt_args is not None:
+            if isinstance(ckpt_args, argparse.Namespace):
+                args_dict = vars(ckpt_args)
+            elif isinstance(ckpt_args, Mapping):
+                args_dict = dict(ckpt_args)
+
+        resolved_model_type = model_type or args_dict.get("model") or args_dict.get("model_type")
+        image_size = int(args_dict.get("image_size") or 256)
+        num_classes = int(args_dict.get("num_classes") or 1000)
+
+        config: Dict[str, object] = {
+            "input_size": image_size // 8,
+            "num_classes": num_classes,
+            "learn_sigma": infer_learn_sigma(state_dict),
+        }
+        if resolved_model_type in DICO_PRESET_CONFIGS:
+            config["model_type"] = resolved_model_type
+
+        model = cls(**config)
+        model.load_state_dict(state_dict, strict=strict)
+        metadata = {
+            "checkpoint_path": checkpoint_path,
+            "weights": weights,
+            "model_type": resolved_model_type,
+            "source_args": ckpt_args,
+        }
+        return model, metadata
+
+
+DiCoDiffusersModel = DiCoTransformer2DModel

DiCo-L-256/vae/config.json

@@ -0,0 +1,38 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.38.0",
+  "_name_or_path": "stabilityai/sd-vae-ft-ema",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "force_upcast": true,
+  "in_channels": 3,
+  "latent_channels": 4,
+  "latents_mean": null,
+  "latents_std": null,
+  "layers_per_block": 2,
+  "mid_block_add_attention": true,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 256,
+  "scaling_factor": 0.18215,
+  "shift_factor": null,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ],
+  "use_post_quant_conv": true,
+  "use_quant_conv": true
+}

DiCo-L-256/vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:703abdcd7c389316b5128faa9b750a530ea1680b453170b27afebac5e4db30c4
+size 334643268

DiCo-S-256/model_index.json

@@ -0,0 +1,1021 @@
+{
+  "_class_name": [
+    "pipeline",
+    "DiCoPipeline"
+  ],
+  "_diffusers_version": "0.38.0",
+  "scheduler": [
+    "diffusers",
+    "DDIMScheduler"
+  ],
+  "transformer": [
+    "transformer_dico",
+    "DiCoTransformer2DModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ],
+  "id2label": {
+    "0": "tench, Tinca tinca",
+    "1": "goldfish, Carassius auratus",
+    "2": "great white shark, white shark, man-eater, man-eating shark, Carcharodon carcharias",
+    "3": "tiger shark, Galeocerdo cuvieri",
+    "4": "hammerhead, hammerhead shark",
+    "5": "electric ray, crampfish, numbfish, torpedo",
+    "6": "stingray",
+    "7": "cock",
+    "8": "hen",
+    "9": "ostrich, Struthio camelus",
+    "10": "brambling, Fringilla montifringilla",
+    "11": "goldfinch, Carduelis carduelis",
+    "12": "house finch, linnet, Carpodacus mexicanus",
+    "13": "junco, snowbird",
+    "14": "indigo bunting, indigo finch, indigo bird, Passerina cyanea",
+    "15": "robin, American robin, Turdus migratorius",
+    "16": "bulbul",
+    "17": "jay",
+    "18": "magpie",
+    "19": "chickadee",
+    "20": "water ouzel, dipper",
+    "21": "kite",
+    "22": "bald eagle, American eagle, Haliaeetus leucocephalus",
+    "23": "vulture",
+    "24": "great grey owl, great gray owl, Strix nebulosa",
+    "25": "European fire salamander, Salamandra salamandra",
+    "26": "common newt, Triturus vulgaris",
+    "27": "eft",
+    "28": "spotted salamander, Ambystoma maculatum",
+    "29": "axolotl, mud puppy, Ambystoma mexicanum",
+    "30": "bullfrog, Rana catesbeiana",
+    "31": "tree frog, tree-frog",
+    "32": "tailed frog, bell toad, ribbed toad, tailed toad, Ascaphus trui",
+    "33": "loggerhead, loggerhead turtle, Caretta caretta",
+    "34": "leatherback turtle, leatherback, leathery turtle, Dermochelys coriacea",
+    "35": "mud turtle",
+    "36": "terrapin",
+    "37": "box turtle, box tortoise",
+    "38": "banded gecko",
+    "39": "common iguana, iguana, Iguana iguana",
+    "40": "American chameleon, anole, Anolis carolinensis",
+    "41": "whiptail, whiptail lizard",
+    "42": "agama",
+    "43": "frilled lizard, Chlamydosaurus kingi",
+    "44": "alligator lizard",
+    "45": "Gila monster, Heloderma suspectum",
+    "46": "green lizard, Lacerta viridis",
+    "47": "African chameleon, Chamaeleo chamaeleon",
+    "48": "Komodo dragon, Komodo lizard, dragon lizard, giant lizard, Varanus komodoensis",
+    "49": "African crocodile, Nile crocodile, Crocodylus niloticus",
+    "50": "American alligator, Alligator mississipiensis",
+    "51": "triceratops",
+    "52": "thunder snake, worm snake, Carphophis amoenus",
+    "53": "ringneck snake, ring-necked snake, ring snake",
+    "54": "hognose snake, puff adder, sand viper",
+    "55": "green snake, grass snake",
+    "56": "king snake, kingsnake",
+    "57": "garter snake, grass snake",
+    "58": "water snake",
+    "59": "vine snake",
+    "60": "night snake, Hypsiglena torquata",
+    "61": "boa constrictor, Constrictor constrictor",
+    "62": "rock python, rock snake, Python sebae",
+    "63": "Indian cobra, Naja naja",
+    "64": "green mamba",
+    "65": "sea snake",
+    "66": "horned viper, cerastes, sand viper, horned asp, Cerastes cornutus",
+    "67": "diamondback, diamondback rattlesnake, Crotalus adamanteus",
+    "68": "sidewinder, horned rattlesnake, Crotalus cerastes",
+    "69": "trilobite",
+    "70": "harvestman, daddy longlegs, Phalangium opilio",
+    "71": "scorpion",
+    "72": "black and gold garden spider, Argiope aurantia",
+    "73": "barn spider, Araneus cavaticus",
+    "74": "garden spider, Aranea diademata",
+    "75": "black widow, Latrodectus mactans",
+    "76": "tarantula",
+    "77": "wolf spider, hunting spider",
+    "78": "tick",
+    "79": "centipede",
+    "80": "black grouse",
+    "81": "ptarmigan",
+    "82": "ruffed grouse, partridge, Bonasa umbellus",
+    "83": "prairie chicken, prairie grouse, prairie fowl",
+    "84": "peacock",
+    "85": "quail",
+    "86": "partridge",
+    "87": "African grey, African gray, Psittacus erithacus",
+    "88": "macaw",
+    "89": "sulphur-crested cockatoo, Kakatoe galerita, Cacatua galerita",
+    "90": "lorikeet",
+    "91": "coucal",
+    "92": "bee eater",
+    "93": "hornbill",
+    "94": "hummingbird",
+    "95": "jacamar",
+    "96": "toucan",
+    "97": "drake",
+    "98": "red-breasted merganser, Mergus serrator",
+    "99": "goose",
+    "100": "black swan, Cygnus atratus",
+    "101": "tusker",
+    "102": "echidna, spiny anteater, anteater",
+    "103": "platypus, duckbill, duckbilled platypus, duck-billed platypus, Ornithorhynchus anatinus",
+    "104": "wallaby, brush kangaroo",
+    "105": "koala, koala bear, kangaroo bear, native bear, Phascolarctos cinereus",
+    "106": "wombat",
+    "107": "jellyfish",
+    "108": "sea anemone, anemone",
+    "109": "brain coral",
+    "110": "flatworm, platyhelminth",
+    "111": "nematode, nematode worm, roundworm",
+    "112": "conch",
+    "113": "snail",
+    "114": "slug",
+    "115": "sea slug, nudibranch",
+    "116": "chiton, coat-of-mail shell, sea cradle, polyplacophore",
+    "117": "chambered nautilus, pearly nautilus, nautilus",
+    "118": "Dungeness crab, Cancer magister",
+    "119": "rock crab, Cancer irroratus",
+    "120": "fiddler crab",
+    "121": "king crab, Alaska crab, Alaskan king crab, Alaska king crab, Paralithodes camtschatica",
+    "122": "American lobster, Northern lobster, Maine lobster, Homarus americanus",
+    "123": "spiny lobster, langouste, rock lobster, crawfish, crayfish, sea crawfish",
+    "124": "crayfish, crawfish, crawdad, crawdaddy",
+    "125": "hermit crab",
+    "126": "isopod",
+    "127": "white stork, Ciconia ciconia",
+    "128": "black stork, Ciconia nigra",
+    "129": "spoonbill",
+    "130": "flamingo",
+    "131": "little blue heron, Egretta caerulea",
+    "132": "American egret, great white heron, Egretta albus",
+    "133": "bittern",
+    "134": "crane",
+    "135": "limpkin, Aramus pictus",
+    "136": "European gallinule, Porphyrio porphyrio",
+    "137": "American coot, marsh hen, mud hen, water hen, Fulica americana",
+    "138": "bustard",
+    "139": "ruddy turnstone, Arenaria interpres",
+    "140": "red-backed sandpiper, dunlin, Erolia alpina",
+    "141": "redshank, Tringa totanus",
+    "142": "dowitcher",
+    "143": "oystercatcher, oyster catcher",
+    "144": "pelican",
+    "145": "king penguin, Aptenodytes patagonica",
+    "146": "albatross, mollymawk",
+    "147": "grey whale, gray whale, devilfish, Eschrichtius gibbosus, Eschrichtius robustus",
+    "148": "killer whale, killer, orca, grampus, sea wolf, Orcinus orca",
+    "149": "dugong, Dugong dugon",
+    "150": "sea lion",
+    "151": "Chihuahua",
+    "152": "Japanese spaniel",
+    "153": "Maltese dog, Maltese terrier, Maltese",
+    "154": "Pekinese, Pekingese, Peke",
+    "155": "Shih-Tzu",
+    "156": "Blenheim spaniel",
+    "157": "papillon",
+    "158": "toy terrier",
+    "159": "Rhodesian ridgeback",
+    "160": "Afghan hound, Afghan",
+    "161": "basset, basset hound",
+    "162": "beagle",
+    "163": "bloodhound, sleuthhound",
+    "164": "bluetick",
+    "165": "black-and-tan coonhound",
+    "166": "Walker hound, Walker foxhound",
+    "167": "English foxhound",
+    "168": "redbone",
+    "169": "borzoi, Russian wolfhound",
+    "170": "Irish wolfhound",
+    "171": "Italian greyhound",
+    "172": "whippet",
+    "173": "Ibizan hound, Ibizan Podenco",
+    "174": "Norwegian elkhound, elkhound",
+    "175": "otterhound, otter hound",
+    "176": "Saluki, gazelle hound",
+    "177": "Scottish deerhound, deerhound",
+    "178": "Weimaraner",
+    "179": "Staffordshire bullterrier, Staffordshire bull terrier",
+    "180": "American Staffordshire terrier, Staffordshire terrier, American pit bull terrier, pit bull terrier",
+    "181": "Bedlington terrier",
+    "182": "Border terrier",
+    "183": "Kerry blue terrier",
+    "184": "Irish terrier",
+    "185": "Norfolk terrier",
+    "186": "Norwich terrier",
+    "187": "Yorkshire terrier",
+    "188": "wire-haired fox terrier",
+    "189": "Lakeland terrier",
+    "190": "Sealyham terrier, Sealyham",
+    "191": "Airedale, Airedale terrier",
+    "192": "cairn, cairn terrier",
+    "193": "Australian terrier",
+    "194": "Dandie Dinmont, Dandie Dinmont terrier",
+    "195": "Boston bull, Boston terrier",
+    "196": "miniature schnauzer",
+    "197": "giant schnauzer",
+    "198": "standard schnauzer",
+    "199": "Scotch terrier, Scottish terrier, Scottie",
+    "200": "Tibetan terrier, chrysanthemum dog",
+    "201": "silky terrier, Sydney silky",
+    "202": "soft-coated wheaten terrier",
+    "203": "West Highland white terrier",
+    "204": "Lhasa, Lhasa apso",
+    "205": "flat-coated retriever",
+    "206": "curly-coated retriever",
+    "207": "golden retriever",
+    "208": "Labrador retriever",
+    "209": "Chesapeake Bay retriever",
+    "210": "German short-haired pointer",
+    "211": "vizsla, Hungarian pointer",
+    "212": "English setter",
+    "213": "Irish setter, red setter",
+    "214": "Gordon setter",
+    "215": "Brittany spaniel",
+    "216": "clumber, clumber spaniel",
+    "217": "English springer, English springer spaniel",
+    "218": "Welsh springer spaniel",
+    "219": "cocker spaniel, English cocker spaniel, cocker",
+    "220": "Sussex spaniel",
+    "221": "Irish water spaniel",
+    "222": "kuvasz",
+    "223": "schipperke",
+    "224": "groenendael",
+    "225": "malinois",
+    "226": "briard",
+    "227": "kelpie",
+    "228": "komondor",
+    "229": "Old English sheepdog, bobtail",
+    "230": "Shetland sheepdog, Shetland sheep dog, Shetland",
+    "231": "collie",
+    "232": "Border collie",
+    "233": "Bouvier des Flandres, Bouviers des Flandres",
+    "234": "Rottweiler",
+    "235": "German shepherd, German shepherd dog, German police dog, alsatian",
+    "236": "Doberman, Doberman pinscher",
+    "237": "miniature pinscher",
+    "238": "Greater Swiss Mountain dog",
+    "239": "Bernese mountain dog",
+    "240": "Appenzeller",
+    "241": "EntleBucher",
+    "242": "boxer",
+    "243": "bull mastiff",
+    "244": "Tibetan mastiff",
+    "245": "French bulldog",
+    "246": "Great Dane",
+    "247": "Saint Bernard, St Bernard",
+    "248": "Eskimo dog, husky",
+    "249": "malamute, malemute, Alaskan malamute",
+    "250": "Siberian husky",
+    "251": "dalmatian, coach dog, carriage dog",
+    "252": "affenpinscher, monkey pinscher, monkey dog",
+    "253": "basenji",
+    "254": "pug, pug-dog",
+    "255": "Leonberg",
+    "256": "Newfoundland, Newfoundland dog",
+    "257": "Great Pyrenees",
+    "258": "Samoyed, Samoyede",
+    "259": "Pomeranian",
+    "260": "chow, chow chow",
+    "261": "keeshond",
+    "262": "Brabancon griffon",
+    "263": "Pembroke, Pembroke Welsh corgi",
+    "264": "Cardigan, Cardigan Welsh corgi",
+    "265": "toy poodle",
+    "266": "miniature poodle",
+    "267": "standard poodle",
+    "268": "Mexican hairless",
+    "269": "timber wolf, grey wolf, gray wolf, Canis lupus",
+    "270": "white wolf, Arctic wolf, Canis lupus tundrarum",
+    "271": "red wolf, maned wolf, Canis rufus, Canis niger",
+    "272": "coyote, prairie wolf, brush wolf, Canis latrans",
+    "273": "dingo, warrigal, warragal, Canis dingo",
+    "274": "dhole, Cuon alpinus",
+    "275": "African hunting dog, hyena dog, Cape hunting dog, Lycaon pictus",
+    "276": "hyena, hyaena",
+    "277": "red fox, Vulpes vulpes",
+    "278": "kit fox, Vulpes macrotis",
+    "279": "Arctic fox, white fox, Alopex lagopus",
+    "280": "grey fox, gray fox, Urocyon cinereoargenteus",
+    "281": "tabby, tabby cat",
+    "282": "tiger cat",
+    "283": "Persian cat",
+    "284": "Siamese cat, Siamese",
+    "285": "Egyptian cat",
+    "286": "cougar, puma, catamount, mountain lion, painter, panther, Felis concolor",
+    "287": "lynx, catamount",
+    "288": "leopard, Panthera pardus",
+    "289": "snow leopard, ounce, Panthera uncia",
+    "290": "jaguar, panther, Panthera onca, Felis onca",
+    "291": "lion, king of beasts, Panthera leo",
+    "292": "tiger, Panthera tigris",
+    "293": "cheetah, chetah, Acinonyx jubatus",
+    "294": "brown bear, bruin, Ursus arctos",
+    "295": "American black bear, black bear, Ursus americanus, Euarctos americanus",
+    "296": "ice bear, polar bear, Ursus Maritimus, Thalarctos maritimus",
+    "297": "sloth bear, Melursus ursinus, Ursus ursinus",
+    "298": "mongoose",
+    "299": "meerkat, mierkat",
+    "300": "tiger beetle",
+    "301": "ladybug, ladybeetle, lady beetle, ladybird, ladybird beetle",
+    "302": "ground beetle, carabid beetle",
+    "303": "long-horned beetle, longicorn, longicorn beetle",
+    "304": "leaf beetle, chrysomelid",
+    "305": "dung beetle",
+    "306": "rhinoceros beetle",
+    "307": "weevil",
+    "308": "fly",
+    "309": "bee",
+    "310": "ant, emmet, pismire",
+    "311": "grasshopper, hopper",
+    "312": "cricket",
+    "313": "walking stick, walkingstick, stick insect",
+    "314": "cockroach, roach",
+    "315": "mantis, mantid",
+    "316": "cicada, cicala",
+    "317": "leafhopper",
+    "318": "lacewing, lacewing fly",
+    "319": "dragonfly, darning needle, devils darning needle, sewing needle, snake feeder, snake doctor, mosquito hawk, skeeter hawk",
+    "320": "damselfly",
+    "321": "admiral",
+    "322": "ringlet, ringlet butterfly",
+    "323": "monarch, monarch butterfly, milkweed butterfly, Danaus plexippus",
+    "324": "cabbage butterfly",
+    "325": "sulphur butterfly, sulfur butterfly",
+    "326": "lycaenid, lycaenid butterfly",
+    "327": "starfish, sea star",
+    "328": "sea urchin",
+    "329": "sea cucumber, holothurian",
+    "330": "wood rabbit, cottontail, cottontail rabbit",
+    "331": "hare",
+    "332": "Angora, Angora rabbit",
+    "333": "hamster",
+    "334": "porcupine, hedgehog",
+    "335": "fox squirrel, eastern fox squirrel, Sciurus niger",
+    "336": "marmot",
+    "337": "beaver",
+    "338": "guinea pig, Cavia cobaya",
+    "339": "sorrel",
+    "340": "zebra",
+    "341": "hog, pig, grunter, squealer, Sus scrofa",
+    "342": "wild boar, boar, Sus scrofa",
+    "343": "warthog",
+    "344": "hippopotamus, hippo, river horse, Hippopotamus amphibius",
+    "345": "ox",
+    "346": "water buffalo, water ox, Asiatic buffalo, Bubalus bubalis",
+    "347": "bison",
+    "348": "ram, tup",
+    "349": "bighorn, bighorn sheep, cimarron, Rocky Mountain bighorn, Rocky Mountain sheep, Ovis canadensis",
+    "350": "ibex, Capra ibex",
+    "351": "hartebeest",
+    "352": "impala, Aepyceros melampus",
+    "353": "gazelle",
+    "354": "Arabian camel, dromedary, Camelus dromedarius",
+    "355": "llama",
+    "356": "weasel",
+    "357": "mink",
+    "358": "polecat, fitch, foulmart, foumart, Mustela putorius",
+    "359": "black-footed ferret, ferret, Mustela nigripes",
+    "360": "otter",
+    "361": "skunk, polecat, wood pussy",
+    "362": "badger",
+    "363": "armadillo",
+    "364": "three-toed sloth, ai, Bradypus tridactylus",
+    "365": "orangutan, orang, orangutang, Pongo pygmaeus",
+    "366": "gorilla, Gorilla gorilla",
+    "367": "chimpanzee, chimp, Pan troglodytes",
+    "368": "gibbon, Hylobates lar",
+    "369": "siamang, Hylobates syndactylus, Symphalangus syndactylus",
+    "370": "guenon, guenon monkey",
+    "371": "patas, hussar monkey, Erythrocebus patas",
+    "372": "baboon",
+    "373": "macaque",
+    "374": "langur",
+    "375": "colobus, colobus monkey",
+    "376": "proboscis monkey, Nasalis larvatus",
+    "377": "marmoset",
+    "378": "capuchin, ringtail, Cebus capucinus",
+    "379": "howler monkey, howler",
+    "380": "titi, titi monkey",
+    "381": "spider monkey, Ateles geoffroyi",
+    "382": "squirrel monkey, Saimiri sciureus",
+    "383": "Madagascar cat, ring-tailed lemur, Lemur catta",
+    "384": "indri, indris, Indri indri, Indri brevicaudatus",
+    "385": "Indian elephant, Elephas maximus",
+    "386": "African elephant, Loxodonta africana",
+    "387": "lesser panda, red panda, panda, bear cat, cat bear, Ailurus fulgens",
+    "388": "giant panda, panda, panda bear, coon bear, Ailuropoda melanoleuca",
+    "389": "barracouta, snoek",
+    "390": "eel",
+    "391": "coho, cohoe, coho salmon, blue jack, silver salmon, Oncorhynchus kisutch",
+    "392": "rock beauty, Holocanthus tricolor",
+    "393": "anemone fish",
+    "394": "sturgeon",
+    "395": "gar, garfish, garpike, billfish, Lepisosteus osseus",
+    "396": "lionfish",
+    "397": "puffer, pufferfish, blowfish, globefish",
+    "398": "abacus",
+    "399": "abaya",
+    "400": "academic gown, academic robe, judge robe",
+    "401": "accordion, piano accordion, squeeze box",
+    "402": "acoustic guitar",
+    "403": "aircraft carrier, carrier, flattop, attack aircraft carrier",
+    "404": "airliner",
+    "405": "airship, dirigible",
+    "406": "altar",
+    "407": "ambulance",
+    "408": "amphibian, amphibious vehicle",
+    "409": "analog clock",
+    "410": "apiary, bee house",
+    "411": "apron",
+    "412": "ashcan, trash can, garbage can, wastebin, ash bin, ash-bin, ashbin, dustbin, trash barrel, trash bin",
+    "413": "assault rifle, assault gun",
+    "414": "backpack, back pack, knapsack, packsack, rucksack, haversack",
+    "415": "bakery, bakeshop, bakehouse",
+    "416": "balance beam, beam",
+    "417": "balloon",
+    "418": "ballpoint, ballpoint pen, ballpen, Biro",
+    "419": "Band Aid",
+    "420": "banjo",
+    "421": "bannister, banister, balustrade, balusters, handrail",
+    "422": "barbell",
+    "423": "barber chair",
+    "424": "barbershop",
+    "425": "barn",
+    "426": "barometer",
+    "427": "barrel, cask",
+    "428": "barrow, garden cart, lawn cart, wheelbarrow",
+    "429": "baseball",
+    "430": "basketball",
+    "431": "bassinet",
+    "432": "bassoon",
+    "433": "bathing cap, swimming cap",
+    "434": "bath towel",
+    "435": "bathtub, bathing tub, bath, tub",
+    "436": "beach wagon, station wagon, wagon, estate car, beach waggon, station waggon, waggon",
+    "437": "beacon, lighthouse, beacon light, pharos",
+    "438": "beaker",
+    "439": "bearskin, busby, shako",
+    "440": "beer bottle",
+    "441": "beer glass",
+    "442": "bell cote, bell cot",
+    "443": "bib",
+    "444": "bicycle-built-for-two, tandem bicycle, tandem",
+    "445": "bikini, two-piece",
+    "446": "binder, ring-binder",
+    "447": "binoculars, field glasses, opera glasses",
+    "448": "birdhouse",
+    "449": "boathouse",
+    "450": "bobsled, bobsleigh, bob",
+    "451": "bolo tie, bolo, bola tie, bola",
+    "452": "bonnet, poke bonnet",
+    "453": "bookcase",
+    "454": "bookshop, bookstore, bookstall",
+    "455": "bottlecap",
+    "456": "bow",
+    "457": "bow tie, bow-tie, bowtie",
+    "458": "brass, memorial tablet, plaque",
+    "459": "brassiere, bra, bandeau",
+    "460": "breakwater, groin, groyne, mole, bulwark, seawall, jetty",
+    "461": "breastplate, aegis, egis",
+    "462": "broom",
+    "463": "bucket, pail",
+    "464": "buckle",
+    "465": "bulletproof vest",
+    "466": "bullet train, bullet",
+    "467": "butcher shop, meat market",
+    "468": "cab, hack, taxi, taxicab",
+    "469": "caldron, cauldron",
+    "470": "candle, taper, wax light",
+    "471": "cannon",
+    "472": "canoe",
+    "473": "can opener, tin opener",
+    "474": "cardigan",
+    "475": "car mirror",
+    "476": "carousel, carrousel, merry-go-round, roundabout, whirligig",
+    "477": "carpenters kit, tool kit",
+    "478": "carton",
+    "479": "car wheel",
+    "480": "cash machine, cash dispenser, automated teller machine, automatic teller machine, automated teller, automatic teller, ATM",
+    "481": "cassette",
+    "482": "cassette player",
+    "483": "castle",
+    "484": "catamaran",
+    "485": "CD player",
+    "486": "cello, violoncello",
+    "487": "cellular telephone, cellular phone, cellphone, cell, mobile phone",
+    "488": "chain",
+    "489": "chainlink fence",
+    "490": "chain mail, ring mail, mail, chain armor, chain armour, ring armor, ring armour",
+    "491": "chain saw, chainsaw",
+    "492": "chest",
+    "493": "chiffonier, commode",
+    "494": "chime, bell, gong",
+    "495": "china cabinet, china closet",
+    "496": "Christmas stocking",
+    "497": "church, church building",
+    "498": "cinema, movie theater, movie theatre, movie house, picture palace",
+    "499": "cleaver, meat cleaver, chopper",
+    "500": "cliff dwelling",
+    "501": "cloak",
+    "502": "clog, geta, patten, sabot",
+    "503": "cocktail shaker",
+    "504": "coffee mug",
+    "505": "coffeepot",
+    "506": "coil, spiral, volute, whorl, helix",
+    "507": "combination lock",
+    "508": "computer keyboard, keypad",
+    "509": "confectionery, confectionary, candy store",
+    "510": "container ship, containership, container vessel",
+    "511": "convertible",
+    "512": "corkscrew, bottle screw",
+    "513": "cornet, horn, trumpet, trump",
+    "514": "cowboy boot",
+    "515": "cowboy hat, ten-gallon hat",
+    "516": "cradle",
+    "517": "crane",
+    "518": "crash helmet",
+    "519": "crate",
+    "520": "crib, cot",
+    "521": "Crock Pot",
+    "522": "croquet ball",
+    "523": "crutch",
+    "524": "cuirass",
+    "525": "dam, dike, dyke",
+    "526": "desk",
+    "527": "desktop computer",
+    "528": "dial telephone, dial phone",
+    "529": "diaper, nappy, napkin",
+    "530": "digital clock",
+    "531": "digital watch",
+    "532": "dining table, board",
+    "533": "dishrag, dishcloth",
+    "534": "dishwasher, dish washer, dishwashing machine",
+    "535": "disk brake, disc brake",
+    "536": "dock, dockage, docking facility",
+    "537": "dogsled, dog sled, dog sleigh",
+    "538": "dome",
+    "539": "doormat, welcome mat",
+    "540": "drilling platform, offshore rig",
+    "541": "drum, membranophone, tympan",
+    "542": "drumstick",
+    "543": "dumbbell",
+    "544": "Dutch oven",
+    "545": "electric fan, blower",
+    "546": "electric guitar",
+    "547": "electric locomotive",
+    "548": "entertainment center",
+    "549": "envelope",
+    "550": "espresso maker",
+    "551": "face powder",
+    "552": "feather boa, boa",
+    "553": "file, file cabinet, filing cabinet",
+    "554": "fireboat",
+    "555": "fire engine, fire truck",
+    "556": "fire screen, fireguard",
+    "557": "flagpole, flagstaff",
+    "558": "flute, transverse flute",
+    "559": "folding chair",
+    "560": "football helmet",
+    "561": "forklift",
+    "562": "fountain",
+    "563": "fountain pen",
+    "564": "four-poster",
+    "565": "freight car",
+    "566": "French horn, horn",
+    "567": "frying pan, frypan, skillet",
+    "568": "fur coat",
+    "569": "garbage truck, dustcart",
+    "570": "gasmask, respirator, gas helmet",
+    "571": "gas pump, gasoline pump, petrol pump, island dispenser",
+    "572": "goblet",
+    "573": "go-kart",
+    "574": "golf ball",
+    "575": "golfcart, golf cart",
+    "576": "gondola",
+    "577": "gong, tam-tam",
+    "578": "gown",
+    "579": "grand piano, grand",
+    "580": "greenhouse, nursery, glasshouse",
+    "581": "grille, radiator grille",
+    "582": "grocery store, grocery, food market, market",
+    "583": "guillotine",
+    "584": "hair slide",
+    "585": "hair spray",
+    "586": "half track",
+    "587": "hammer",
+    "588": "hamper",
+    "589": "hand blower, blow dryer, blow drier, hair dryer, hair drier",
+    "590": "hand-held computer, hand-held microcomputer",
+    "591": "handkerchief, hankie, hanky, hankey",
+    "592": "hard disc, hard disk, fixed disk",
+    "593": "harmonica, mouth organ, harp, mouth harp",
+    "594": "harp",
+    "595": "harvester, reaper",
+    "596": "hatchet",
+    "597": "holster",
+    "598": "home theater, home theatre",
+    "599": "honeycomb",
+    "600": "hook, claw",
+    "601": "hoopskirt, crinoline",
+    "602": "horizontal bar, high bar",
+    "603": "horse cart, horse-cart",
+    "604": "hourglass",
+    "605": "iPod",
+    "606": "iron, smoothing iron",
+    "607": "jack-o-lantern",
+    "608": "jean, blue jean, denim",
+    "609": "jeep, landrover",
+    "610": "jersey, T-shirt, tee shirt",
+    "611": "jigsaw puzzle",
+    "612": "jinrikisha, ricksha, rickshaw",
+    "613": "joystick",
+    "614": "kimono",
+    "615": "knee pad",
+    "616": "knot",
+    "617": "lab coat, laboratory coat",
+    "618": "ladle",
+    "619": "lampshade, lamp shade",
+    "620": "laptop, laptop computer",
+    "621": "lawn mower, mower",
+    "622": "lens cap, lens cover",
+    "623": "letter opener, paper knife, paperknife",
+    "624": "library",
+    "625": "lifeboat",
+    "626": "lighter, light, igniter, ignitor",
+    "627": "limousine, limo",
+    "628": "liner, ocean liner",
+    "629": "lipstick, lip rouge",
+    "630": "Loafer",
+    "631": "lotion",
+    "632": "loudspeaker, speaker, speaker unit, loudspeaker system, speaker system",
+    "633": "loupe, jewelers loupe",
+    "634": "lumbermill, sawmill",
+    "635": "magnetic compass",
+    "636": "mailbag, postbag",
+    "637": "mailbox, letter box",
+    "638": "maillot",
+    "639": "maillot, tank suit",
+    "640": "manhole cover",
+    "641": "maraca",
+    "642": "marimba, xylophone",
+    "643": "mask",
+    "644": "matchstick",
+    "645": "maypole",
+    "646": "maze, labyrinth",
+    "647": "measuring cup",
+    "648": "medicine chest, medicine cabinet",
+    "649": "megalith, megalithic structure",
+    "650": "microphone, mike",
+    "651": "microwave, microwave oven",
+    "652": "military uniform",
+    "653": "milk can",
+    "654": "minibus",
+    "655": "miniskirt, mini",
+    "656": "minivan",
+    "657": "missile",
+    "658": "mitten",
+    "659": "mixing bowl",
+    "660": "mobile home, manufactured home",
+    "661": "Model T",
+    "662": "modem",
+    "663": "monastery",
+    "664": "monitor",
+    "665": "moped",
+    "666": "mortar",
+    "667": "mortarboard",
+    "668": "mosque",
+    "669": "mosquito net",
+    "670": "motor scooter, scooter",
+    "671": "mountain bike, all-terrain bike, off-roader",
+    "672": "mountain tent",
+    "673": "mouse, computer mouse",
+    "674": "mousetrap",
+    "675": "moving van",
+    "676": "muzzle",
+    "677": "nail",
+    "678": "neck brace",
+    "679": "necklace",
+    "680": "nipple",
+    "681": "notebook, notebook computer",
+    "682": "obelisk",
+    "683": "oboe, hautboy, hautbois",
+    "684": "ocarina, sweet potato",
+    "685": "odometer, hodometer, mileometer, milometer",
+    "686": "oil filter",
+    "687": "organ, pipe organ",
+    "688": "oscilloscope, scope, cathode-ray oscilloscope, CRO",
+    "689": "overskirt",
+    "690": "oxcart",
+    "691": "oxygen mask",
+    "692": "packet",
+    "693": "paddle, boat paddle",
+    "694": "paddlewheel, paddle wheel",
+    "695": "padlock",
+    "696": "paintbrush",
+    "697": "pajama, pyjama, pjs, jammies",
+    "698": "palace",
+    "699": "panpipe, pandean pipe, syrinx",
+    "700": "paper towel",
+    "701": "parachute, chute",
+    "702": "parallel bars, bars",
+    "703": "park bench",
+    "704": "parking meter",
+    "705": "passenger car, coach, carriage",
+    "706": "patio, terrace",
+    "707": "pay-phone, pay-station",
+    "708": "pedestal, plinth, footstall",
+    "709": "pencil box, pencil case",
+    "710": "pencil sharpener",
+    "711": "perfume, essence",
+    "712": "Petri dish",
+    "713": "photocopier",
+    "714": "pick, plectrum, plectron",
+    "715": "pickelhaube",
+    "716": "picket fence, paling",
+    "717": "pickup, pickup truck",
+    "718": "pier",
+    "719": "piggy bank, penny bank",
+    "720": "pill bottle",
+    "721": "pillow",
+    "722": "ping-pong ball",
+    "723": "pinwheel",
+    "724": "pirate, pirate ship",
+    "725": "pitcher, ewer",
+    "726": "plane, carpenters plane, woodworking plane",
+    "727": "planetarium",
+    "728": "plastic bag",
+    "729": "plate rack",
+    "730": "plow, plough",
+    "731": "plunger, plumbers helper",
+    "732": "Polaroid camera, Polaroid Land camera",
+    "733": "pole",
+    "734": "police van, police wagon, paddy wagon, patrol wagon, wagon, black Maria",
+    "735": "poncho",
+    "736": "pool table, billiard table, snooker table",
+    "737": "pop bottle, soda bottle",
+    "738": "pot, flowerpot",
+    "739": "potters wheel",
+    "740": "power drill",
+    "741": "prayer rug, prayer mat",
+    "742": "printer",
+    "743": "prison, prison house",
+    "744": "projectile, missile",
+    "745": "projector",
+    "746": "puck, hockey puck",
+    "747": "punching bag, punch bag, punching ball, punchball",
+    "748": "purse",
+    "749": "quill, quill pen",
+    "750": "quilt, comforter, comfort, puff",
+    "751": "racer, race car, racing car",
+    "752": "racket, racquet",
+    "753": "radiator",
+    "754": "radio, wireless",
+    "755": "radio telescope, radio reflector",
+    "756": "rain barrel",
+    "757": "recreational vehicle, RV, R.V.",
+    "758": "reel",
+    "759": "reflex camera",
+    "760": "refrigerator, icebox",
+    "761": "remote control, remote",
+    "762": "restaurant, eating house, eating place, eatery",
+    "763": "revolver, six-gun, six-shooter",
+    "764": "rifle",
+    "765": "rocking chair, rocker",
+    "766": "rotisserie",
+    "767": "rubber eraser, rubber, pencil eraser",
+    "768": "rugby ball",
+    "769": "rule, ruler",
+    "770": "running shoe",
+    "771": "safe",
+    "772": "safety pin",
+    "773": "saltshaker, salt shaker",
+    "774": "sandal",
+    "775": "sarong",
+    "776": "sax, saxophone",
+    "777": "scabbard",
+    "778": "scale, weighing machine",
+    "779": "school bus",
+    "780": "schooner",
+    "781": "scoreboard",
+    "782": "screen, CRT screen",
+    "783": "screw",
+    "784": "screwdriver",
+    "785": "seat belt, seatbelt",
+    "786": "sewing machine",
+    "787": "shield, buckler",
+    "788": "shoe shop, shoe-shop, shoe store",
+    "789": "shoji",
+    "790": "shopping basket",
+    "791": "shopping cart",
+    "792": "shovel",
+    "793": "shower cap",
+    "794": "shower curtain",
+    "795": "ski",
+    "796": "ski mask",
+    "797": "sleeping bag",
+    "798": "slide rule, slipstick",
+    "799": "sliding door",
+    "800": "slot, one-armed bandit",
+    "801": "snorkel",
+    "802": "snowmobile",
+    "803": "snowplow, snowplough",
+    "804": "soap dispenser",
+    "805": "soccer ball",
+    "806": "sock",
+    "807": "solar dish, solar collector, solar furnace",
+    "808": "sombrero",
+    "809": "soup bowl",
+    "810": "space bar",
+    "811": "space heater",
+    "812": "space shuttle",
+    "813": "spatula",
+    "814": "speedboat",
+    "815": "spider web, spiders web",
+    "816": "spindle",
+    "817": "sports car, sport car",
+    "818": "spotlight, spot",
+    "819": "stage",
+    "820": "steam locomotive",
+    "821": "steel arch bridge",
+    "822": "steel drum",
+    "823": "stethoscope",
+    "824": "stole",
+    "825": "stone wall",
+    "826": "stopwatch, stop watch",
+    "827": "stove",
+    "828": "strainer",
+    "829": "streetcar, tram, tramcar, trolley, trolley car",
+    "830": "stretcher",
+    "831": "studio couch, day bed",
+    "832": "stupa, tope",
+    "833": "submarine, pigboat, sub, U-boat",
+    "834": "suit, suit of clothes",
+    "835": "sundial",
+    "836": "sunglass",
+    "837": "sunglasses, dark glasses, shades",
+    "838": "sunscreen, sunblock, sun blocker",
+    "839": "suspension bridge",
+    "840": "swab, swob, mop",
+    "841": "sweatshirt",
+    "842": "swimming trunks, bathing trunks",
+    "843": "swing",
+    "844": "switch, electric switch, electrical switch",
+    "845": "syringe",
+    "846": "table lamp",
+    "847": "tank, army tank, armored combat vehicle, armoured combat vehicle",
+    "848": "tape player",
+    "849": "teapot",
+    "850": "teddy, teddy bear",
+    "851": "television, television system",
+    "852": "tennis ball",
+    "853": "thatch, thatched roof",
+    "854": "theater curtain, theatre curtain",
+    "855": "thimble",
+    "856": "thresher, thrasher, threshing machine",
+    "857": "throne",
+    "858": "tile roof",
+    "859": "toaster",
+    "860": "tobacco shop, tobacconist shop, tobacconist",
+    "861": "toilet seat",
+    "862": "torch",
+    "863": "totem pole",
+    "864": "tow truck, tow car, wrecker",
+    "865": "toyshop",
+    "866": "tractor",
+    "867": "trailer truck, tractor trailer, trucking rig, rig, articulated lorry, semi",
+    "868": "tray",
+    "869": "trench coat",
+    "870": "tricycle, trike, velocipede",
+    "871": "trimaran",
+    "872": "tripod",
+    "873": "triumphal arch",
+    "874": "trolleybus, trolley coach, trackless trolley",
+    "875": "trombone",
+    "876": "tub, vat",
+    "877": "turnstile",
+    "878": "typewriter keyboard",
+    "879": "umbrella",
+    "880": "unicycle, monocycle",
+    "881": "upright, upright piano",
+    "882": "vacuum, vacuum cleaner",
+    "883": "vase",
+    "884": "vault",
+    "885": "velvet",
+    "886": "vending machine",
+    "887": "vestment",
+    "888": "viaduct",
+    "889": "violin, fiddle",
+    "890": "volleyball",
+    "891": "waffle iron",
+    "892": "wall clock",
+    "893": "wallet, billfold, notecase, pocketbook",
+    "894": "wardrobe, closet, press",
+    "895": "warplane, military plane",
+    "896": "washbasin, handbasin, washbowl, lavabo, wash-hand basin",
+    "897": "washer, automatic washer, washing machine",
+    "898": "water bottle",
+    "899": "water jug",
+    "900": "water tower",
+    "901": "whiskey jug",
+    "902": "whistle",
+    "903": "wig",
+    "904": "window screen",
+    "905": "window shade",
+    "906": "Windsor tie",
+    "907": "wine bottle",
+    "908": "wing",
+    "909": "wok",
+    "910": "wooden spoon",
+    "911": "wool, woolen, woollen",
+    "912": "worm fence, snake fence, snake-rail fence, Virginia fence",
+    "913": "wreck",
+    "914": "yawl",
+    "915": "yurt",
+    "916": "web site, website, internet site, site",
+    "917": "comic book",
+    "918": "crossword puzzle, crossword",
+    "919": "street sign",
+    "920": "traffic light, traffic signal, stoplight",
+    "921": "book jacket, dust cover, dust jacket, dust wrapper",
+    "922": "menu",
+    "923": "plate",
+    "924": "guacamole",
+    "925": "consomme",
+    "926": "hot pot, hotpot",
+    "927": "trifle",
+    "928": "ice cream, icecream",
+    "929": "ice lolly, lolly, lollipop, popsicle",
+    "930": "French loaf",
+    "931": "bagel, beigel",
+    "932": "pretzel",
+    "933": "cheeseburger",
+    "934": "hotdog, hot dog, red hot",
+    "935": "mashed potato",
+    "936": "head cabbage",
+    "937": "broccoli",
+    "938": "cauliflower",
+    "939": "zucchini, courgette",
+    "940": "spaghetti squash",
+    "941": "acorn squash",
+    "942": "butternut squash",
+    "943": "cucumber, cuke",
+    "944": "artichoke, globe artichoke",
+    "945": "bell pepper",
+    "946": "cardoon",
+    "947": "mushroom",
+    "948": "Granny Smith",
+    "949": "strawberry",
+    "950": "orange",
+    "951": "lemon",
+    "952": "fig",
+    "953": "pineapple, ananas",
+    "954": "banana",
+    "955": "jackfruit, jak, jack",
+    "956": "custard apple",
+    "957": "pomegranate",
+    "958": "hay",
+    "959": "carbonara",
+    "960": "chocolate sauce, chocolate syrup",
+    "961": "dough",
+    "962": "meat loaf, meatloaf",
+    "963": "pizza, pizza pie",
+    "964": "potpie",
+    "965": "burrito",
+    "966": "red wine",
+    "967": "espresso",
+    "968": "cup",
+    "969": "eggnog",
+    "970": "alp",
+    "971": "bubble",
+    "972": "cliff, drop, drop-off",
+    "973": "coral reef",
+    "974": "geyser",
+    "975": "lakeside, lakeshore",
+    "976": "promontory, headland, head, foreland",
+    "977": "sandbar, sand bar",
+    "978": "seashore, coast, seacoast, sea-coast",
+    "979": "valley, vale",
+    "980": "volcano",
+    "981": "ballplayer, baseball player",
+    "982": "groom, bridegroom",
+    "983": "scuba diver",
+    "984": "rapeseed",
+    "985": "daisy",
+    "986": "yellow ladys slipper, yellow lady-slipper, Cypripedium calceolus, Cypripedium parviflorum",
+    "987": "corn",
+    "988": "acorn",
+    "989": "hip, rose hip, rosehip",
+    "990": "buckeye, horse chestnut, conker",
+    "991": "coral fungus",
+    "992": "agaric",
+    "993": "gyromitra",
+    "994": "stinkhorn, carrion fungus",
+    "995": "earthstar",
+    "996": "hen-of-the-woods, hen of the woods, Polyporus frondosus, Grifola frondosa",
+    "997": "bolete",
+    "998": "ear, spike, capitulum",
+    "999": "toilet tissue, toilet paper, bathroom tissue"
+  }
+}

DiCo-S-256/pipeline.py

@@ -0,0 +1,398 @@
+"""Hub custom pipeline: DiCoPipeline.
+Load with native Hugging Face diffusers and trust_remote_code=True.
+"""
+
+# Copyright 2026 The HuggingFace Team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from __future__ import annotations
+
+import inspect
+import json
+from pathlib import Path
+from typing import Dict, List, Optional, Tuple, Union
+
+import torch
+from diffusers.image_processor import VaeImageProcessor
+from diffusers.models import AutoencoderKL
+from diffusers.pipelines.pipeline_utils import DiffusionPipeline, ImagePipelineOutput
+from diffusers.schedulers import DDIMScheduler, KarrasDiffusionSchedulers
+from diffusers.utils.torch_utils import randn_tensor
+
+
+EXAMPLE_DOC_STRING = """
+    Examples:
+        ```py
+        >>> from pathlib import Path
+        >>> from diffusers import DiffusionPipeline
+        >>> import torch
+
+        >>> model_dir = Path("./DiCo-XL-256").resolve()
+        >>> pipe = DiffusionPipeline.from_pretrained(
+        ...     str(model_dir),
+        ...     local_files_only=True,
+        ...     custom_pipeline=str(model_dir / "pipeline.py"),
+        ...     trust_remote_code=True,
+        ...     torch_dtype=torch.bfloat16,
+        ... )
+        >>> pipe.to("cuda")
+
+        >>> image = pipe(
+        ...     class_labels="golden retriever",
+        ...     num_inference_steps=250,
+        ...     guidance_scale=1.4,
+        ...     generator=torch.Generator("cuda").manual_seed(0),
+        ... ).images[0]
+        ```
+"""
+
+
+class DiCoPipeline(DiffusionPipeline):
+    r"""
+    Pipeline for class-conditional image generation with DiCo (Diffusion ConvNet).
+
+    Parameters:
+        transformer ([`DiCoTransformer2DModel`]):
+            Class-conditional DiCo denoiser operating in VAE latent space.
+        vae ([`AutoencoderKL`]):
+            Variational autoencoder used to decode latents to pixels.
+        scheduler ([`DDIMScheduler`]):
+            Diffusion scheduler. Other [`KarrasDiffusionSchedulers`] can be swapped at inference time.
+        id2label (`dict[int, str]`, *optional*):
+            ImageNet class id to English label mapping. Values may contain comma-separated synonyms.
+    """
+
+    model_cpu_offload_seq = "transformer->vae"
+
+    @staticmethod
+    def prepare_extra_step_kwargs(
+        scheduler: KarrasDiffusionSchedulers,
+        generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
+        eta: float = 0.0,
+    ) -> Dict[str, object]:
+        kwargs: Dict[str, object] = {}
+        step_params = set(inspect.signature(scheduler.step).parameters.keys())
+        if "generator" in step_params:
+            kwargs["generator"] = generator
+        if "eta" in step_params:
+            kwargs["eta"] = eta
+        return kwargs
+
+    def __init__(
+        self,
+        transformer,
+        vae: AutoencoderKL,
+        scheduler: KarrasDiffusionSchedulers,
+        id2label: Optional[Dict[Union[int, str], str]] = None,
+    ):
+        super().__init__()
+        if scheduler is None:
+            scheduler = DDIMScheduler(
+                num_train_timesteps=1000,
+                beta_start=0.0001,
+                beta_end=0.02,
+                beta_schedule="linear",
+                clip_sample=False,
+                set_alpha_to_one=True,
+                steps_offset=0,
+                prediction_type="epsilon",
+            )
+        self.register_modules(transformer=transformer, vae=vae, scheduler=scheduler)
+        self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1)
+        self.image_processor = VaeImageProcessor(vae_scale_factor=self.vae_scale_factor)
+        self._id2label = self._normalize_id2label(id2label)
+        self.labels = self._build_label2id(self._id2label)
+        self._labels_loaded_from_model_index = bool(self._id2label)
+
+    @classmethod
+    def from_pretrained(cls, pretrained_model_name_or_path: str, **kwargs):
+        model_kwargs = dict(kwargs)
+        transformer_subfolder = model_kwargs.pop("transformer_subfolder", None)
+        scheduler_subfolder = model_kwargs.pop("scheduler_subfolder", None)
+        vae_subfolder = model_kwargs.pop("vae_subfolder", None)
+        scheduler_kwargs = model_kwargs.pop("scheduler_kwargs", {})
+        base_path = Path(pretrained_model_name_or_path)
+
+        if transformer_subfolder is None and (base_path / "transformer").exists():
+            transformer_subfolder = "transformer"
+        if scheduler_subfolder is None and (base_path / "scheduler").exists():
+            scheduler_subfolder = "scheduler"
+        if vae_subfolder is None and (base_path / "vae").exists():
+            vae_subfolder = "vae"
+
+        try:
+            return super().from_pretrained(pretrained_model_name_or_path, **kwargs)
+        except Exception:
+            transformer_path = str(base_path / transformer_subfolder) if transformer_subfolder else pretrained_model_name_or_path
+            from transformer.transformer_dico import DiCoTransformer2DModel
+            transformer = DiCoTransformer2DModel.from_pretrained(transformer_path, **model_kwargs)
+            try:
+                scheduler = DDIMScheduler.from_pretrained(
+                    pretrained_model_name_or_path,
+                    subfolder=scheduler_subfolder,
+                    **scheduler_kwargs,
+                )
+            except Exception:
+                scheduler = DDIMScheduler(
+                    num_train_timesteps=1000,
+                    beta_start=0.0001,
+                    beta_end=0.02,
+                    beta_schedule="linear",
+                    clip_sample=False,
+                    set_alpha_to_one=True,
+                    steps_offset=0,
+                    prediction_type="epsilon",
+                    **scheduler_kwargs,
+                )
+            try:
+                vae = AutoencoderKL.from_pretrained(
+                    pretrained_model_name_or_path,
+                    subfolder=vae_subfolder,
+                    **model_kwargs,
+                )
+            except Exception:
+                vae = AutoencoderKL.from_pretrained("stabilityai/sd-vae-ft-ema", **model_kwargs)
+            id2label = cls._read_id2label_from_model_index(str(base_path))
+            return cls(transformer=transformer, vae=vae, scheduler=scheduler, id2label=id2label)
+
+    def _ensure_labels_loaded(self) -> None:
+        if self._labels_loaded_from_model_index:
+            return
+        loaded = self._read_id2label_from_model_index(getattr(self.config, "_name_or_path", None))
+        if loaded:
+            self._id2label = loaded
+            self.labels = self._build_label2id(self._id2label)
+        self._labels_loaded_from_model_index = True
+
+    @staticmethod
+    def _normalize_id2label(id2label: Optional[Dict[Union[int, str], str]]) -> Dict[int, str]:
+        if not id2label:
+            return {}
+        return {int(key): value for key, value in id2label.items()}
+
+    @staticmethod
+    def _read_id2label_from_model_index(variant_path: Optional[str]) -> Dict[int, str]:
+        if not variant_path:
+            return {}
+        model_index_path = Path(variant_path).resolve() / "model_index.json"
+        if not model_index_path.exists():
+            return {}
+        raw = json.loads(model_index_path.read_text(encoding="utf-8"))
+        id2label = raw.get("id2label")
+        if not isinstance(id2label, dict):
+            return {}
+        return {int(key): value for key, value in id2label.items()}
+
+    @staticmethod
+    def _build_label2id(id2label: Dict[int, str]) -> Dict[str, int]:
+        label2id: Dict[str, int] = {}
+        for class_id, value in id2label.items():
+            for synonym in value.split(","):
+                synonym = synonym.strip()
+                if synonym:
+                    label2id[synonym] = int(class_id)
+        return dict(sorted(label2id.items()))
+
+    @property
+    def id2label(self) -> Dict[int, str]:
+        self._ensure_labels_loaded()
+        return self._id2label
+
+    def get_label_ids(self, label: Union[str, List[str]]) -> List[int]:
+        self._ensure_labels_loaded()
+        if not self.labels:
+            raise ValueError("No English labels loaded. Ensure `id2label` exists in model_index.json.")
+        if isinstance(label, str):
+            label = [label]
+        missing = [item for item in label if item not in self.labels]
+        if missing:
+            preview = ", ".join(list(self.labels.keys())[:8])
+            raise ValueError(f"Unknown English label(s): {missing}. Example valid labels: {preview}, ...")
+        return [self.labels[item] for item in label]
+
+    def _normalize_class_labels(
+        self,
+        class_labels: Union[int, str, List[Union[int, str]], torch.LongTensor],
+    ) -> torch.LongTensor:
+        if torch.is_tensor(class_labels):
+            return class_labels.to(device=self._execution_device, dtype=torch.long).reshape(-1)
+        if isinstance(class_labels, int):
+            class_label_ids = [class_labels]
+        elif isinstance(class_labels, str):
+            class_label_ids = self.get_label_ids(class_labels)
+        elif class_labels and isinstance(class_labels[0], str):
+            class_label_ids = self.get_label_ids(class_labels)
+        else:
+            class_label_ids = list(class_labels)
+        return torch.tensor(class_label_ids, device=self._execution_device, dtype=torch.long).reshape(-1)
+
+    def _default_image_size(self) -> int:
+        return int(self.transformer.config.input_size) * self.vae_scale_factor
+
+    def check_inputs(
+        self,
+        height: int,
+        width: int,
+        num_inference_steps: int,
+        output_type: str,
+    ) -> None:
+        if num_inference_steps < 1:
+            raise ValueError("num_inference_steps must be >= 1.")
+        if output_type not in {"pil", "np", "pt", "latent"}:
+            raise ValueError("output_type must be one of: 'pil', 'np', 'pt', 'latent'.")
+        if height % self.vae_scale_factor != 0 or width % self.vae_scale_factor != 0:
+            raise ValueError(
+                f"height and width must be divisible by the VAE downsample factor {self.vae_scale_factor}."
+            )
+        latent_height = height // self.vae_scale_factor
+        latent_width = width // self.vae_scale_factor
+        expected_size = int(self.transformer.config.input_size)
+        if latent_height != expected_size or latent_width != expected_size:
+            raise ValueError(
+                f"Requested latent size {(latent_height, latent_width)} does not match the pretrained "
+                f"transformer input_size={expected_size}. Use height=width={self._default_image_size()}."
+            )
+
+    def prepare_latents(
+        self,
+        batch_size: int,
+        height: int,
+        width: int,
+        dtype: torch.dtype,
+        device: torch.device,
+        generator: Optional[Union[torch.Generator, List[torch.Generator]]],
+    ) -> torch.Tensor:
+        latent_height = height // self.vae_scale_factor
+        latent_width = width // self.vae_scale_factor
+        return randn_tensor(
+            (batch_size, self.transformer.config.in_channels, latent_height, latent_width),
+            generator=generator,
+            device=device,
+            dtype=dtype,
+        )
+
+    @staticmethod
+    def _expand_timestep(timestep, batch: int, device: torch.device) -> torch.Tensor:
+        if not torch.is_tensor(timestep):
+            timestep = torch.tensor([timestep], dtype=torch.long, device=device)
+        elif timestep.ndim == 0:
+            timestep = timestep[None].to(device=device)
+        return timestep.expand(batch)
+
+    @staticmethod
+    def _prepare_model_output_for_scheduler(
+        model_output: torch.Tensor,
+        latent_channels: int,
+        scheduler: KarrasDiffusionSchedulers,
+    ) -> torch.Tensor:
+        if model_output.shape[1] != 2 * latent_channels:
+            return model_output
+        variance_type = getattr(scheduler.config, "variance_type", None)
+        if scheduler.__class__.__name__ == "DDPMScheduler" and variance_type in ("learned", "learned_range"):
+            return model_output
+        model_output, _ = torch.split(model_output, latent_channels, dim=1)
+        return model_output
+
+    def decode_latents(self, latents: torch.Tensor, output_type: str = "pil"):
+        if output_type == "latent":
+            return latents
+        scaling_factor = getattr(self.vae.config, "scaling_factor", 0.18215)
+        image = self.vae.decode(latents / scaling_factor).sample
+        if output_type == "pt":
+            return image
+        return self.image_processor.postprocess(image, output_type=output_type)
+
+    @torch.inference_mode()
+    def __call__(
+        self,
+        class_labels: Union[int, str, List[Union[int, str]], torch.LongTensor],
+        height: Optional[int] = None,
+        width: Optional[int] = None,
+        num_inference_steps: int = 250,
+        guidance_scale: float = 1.0,
+        eta: float = 0.0,
+        generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
+        output_type: str = "pil",
+        return_dict: bool = True,
+    ) -> Union[ImagePipelineOutput, Tuple]:
+        default_size = self._default_image_size()
+        height = int(height or default_size)
+        width = int(width or default_size)
+        self.check_inputs(height, width, num_inference_steps, output_type)
+
+        device = self._execution_device
+        model_dtype = next(self.transformer.parameters()).dtype
+        class_labels_tensor = self._normalize_class_labels(class_labels)
+        batch_size = class_labels_tensor.numel()
+        latent_channels = int(self.transformer.config.in_channels)
+        null_class_val = int(self.transformer.config.num_classes)
+        do_cfg = guidance_scale > 1.0
+
+        latents = self.prepare_latents(
+            batch_size=batch_size,
+            height=height,
+            width=width,
+            dtype=model_dtype,
+            device=device,
+            generator=generator,
+        )
+        latent_model_input = torch.cat([latents] * 2) if do_cfg else latents
+
+        class_labels_input = class_labels_tensor
+        if do_cfg:
+            class_null = torch.full_like(class_labels_tensor, null_class_val)
+            class_labels_input = torch.cat([class_labels_tensor, class_null], dim=0)
+
+        self.scheduler.set_timesteps(num_inference_steps, device=device)
+        extra_step_kwargs = self.prepare_extra_step_kwargs(self.scheduler, generator=generator, eta=eta)
+
+        for t in self.progress_bar(self.scheduler.timesteps):
+            if do_cfg:
+                half = latent_model_input[: len(latent_model_input) // 2]
+                latent_model_input = torch.cat([half, half], dim=0)
+            latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)
+            timesteps = self._expand_timestep(t, latent_model_input.shape[0], latent_model_input.device)
+
+            noise_pred = self.transformer(
+                hidden_states=latent_model_input,
+                timestep=timesteps,
+                class_labels=class_labels_input,
+                return_dict=True,
+            ).sample
+
+            if do_cfg:
+                eps, rest = noise_pred[:, :latent_channels], noise_pred[:, latent_channels:]
+                cond_eps, uncond_eps = torch.split(eps, len(eps) // 2, dim=0)
+                half_eps = uncond_eps + guidance_scale * (cond_eps - uncond_eps)
+                eps = torch.cat([half_eps, half_eps], dim=0)
+                noise_pred = torch.cat([eps, rest], dim=1)
+
+            model_output = self._prepare_model_output_for_scheduler(noise_pred, latent_channels, self.scheduler)
+            latent_model_input = self.scheduler.step(
+                model_output, t, latent_model_input, return_dict=True, **extra_step_kwargs
+            ).prev_sample
+
+        if do_cfg:
+            latents, _ = latent_model_input.chunk(2, dim=0)
+        else:
+            latents = latent_model_input
+
+        image = self.decode_latents(latents, output_type=output_type)
+        self.maybe_free_model_hooks()
+        if not return_dict:
+            return (image,)
+        return ImagePipelineOutput(images=image)
+
+
+DiCoPipelineOutput = ImagePipelineOutput

DiCo-S-256/scheduler/scheduler_config.json

@@ -0,0 +1,12 @@
+{
+  "_class_name": "DDIMScheduler",
+  "_diffusers_version": "0.35.1",
+  "num_train_timesteps": 1000,
+  "beta_start": 0.0001,
+  "beta_end": 0.02,
+  "beta_schedule": "linear",
+  "clip_sample": false,
+  "set_alpha_to_one": true,
+  "steps_offset": 0,
+  "prediction_type": "epsilon"
+}

DiCo-S-256/transformer/config.json

@@ -0,0 +1,14 @@
+{
+  "_class_name": "DiCoTransformer2DModel",
+  "_diffusers_version": "0.38.0",
+  "class_dropout_prob": 0.1,
+  "depth": null,
+  "hidden_size": 416,
+  "in_channels": 4,
+  "input_size": 32,
+  "learn_sigma": true,
+  "mlp_ratio": 2.0,
+  "model_type": "DiCo-S",
+  "num_class_embeds": null,
+  "num_classes": 1000
+}

DiCo-S-256/transformer/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a6965a778752599a0eef69505c7b603340ce74073d88e6c5dc7bb0ce4580e99a
+size 132583104

DiCo-S-256/transformer/transformer_dico.py

@@ -0,0 +1,479 @@
+# Copyright 2026 The HuggingFace Team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from __future__ import annotations
+
+import argparse
+import math
+from collections.abc import Mapping
+from typing import Dict, Literal, Optional, Tuple
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+from diffusers.configuration_utils import ConfigMixin, register_to_config
+from diffusers.models.modeling_outputs import Transformer2DModelOutput
+from diffusers.models.modeling_utils import ModelMixin
+
+
+DICO_PRESET_CONFIGS: Dict[str, Dict[str, object]] = {
+    "DiCo-S": {
+        "hidden_size": 128,
+        "depth": [5, 4, 4, 4, 4],
+        "mlp_ratio": 2.0,
+    },
+    "DiCo-B": {
+        "hidden_size": 256,
+        "depth": [5, 4, 4, 4, 4],
+        "mlp_ratio": 2.0,
+    },
+    "DiCo-L": {
+        "hidden_size": 352,
+        "depth": [9, 8, 9, 8, 9],
+        "mlp_ratio": 2.0,
+    },
+    "DiCo-XL": {
+        "hidden_size": 416,
+        "depth": [9, 9, 10, 9, 9],
+        "mlp_ratio": 2.0,
+    },
+    "DiCo-H": {
+        "hidden_size": 416,
+        "depth": [14, 12, 10, 12, 14],
+        "mlp_ratio": 4.0,
+    },
+}
+
+
+def remap_legacy_state_dict(state_dict: Dict[str, torch.Tensor]) -> Dict[str, torch.Tensor]:
+    """Map wrapper/backbone keys from legacy checkpoints to native model keys."""
+    remapped: Dict[str, torch.Tensor] = {}
+    for key, value in state_dict.items():
+        new_key = key
+        for prefix in ("transformer.", "model.", "net."):
+            if new_key.startswith(prefix):
+                new_key = new_key[len(prefix) :]
+                break
+        remapped[new_key] = value
+    return remapped
+
+
+def infer_learn_sigma(state_dict: Dict[str, torch.Tensor], in_channels: int = 4) -> bool:
+    weight = state_dict.get("final_layer.out_proj.weight")
+    if weight is None:
+        return True
+    return int(weight.shape[0]) == in_channels * 2
+
+
+def config_from_legacy(config: Dict[str, object]) -> Dict[str, object]:
+    """Build native config kwargs from a legacy config.json dict."""
+    model_type = config.get("model_type") or config.get("model_name") or config.get("model")
+    if model_type not in DICO_PRESET_CONFIGS:
+        raise ValueError(f"Unknown DiCo preset '{model_type}'. Known: {list(DICO_PRESET_CONFIGS)}")
+
+    preset = dict(DICO_PRESET_CONFIGS[model_type])
+    preset["num_classes"] = int(config.get("num_class_embeds") or config.get("num_classes") or 1000)
+    preset["model_type"] = model_type
+    preset["input_size"] = int(config.get("input_size") or config.get("sample_size") or 32)
+    if config.get("learn_sigma") is not None:
+        preset["learn_sigma"] = bool(config["learn_sigma"])
+    return preset
+
+
+def modulate(x: torch.Tensor, shift: torch.Tensor, scale: torch.Tensor) -> torch.Tensor:
+    return x * (1 + scale.unsqueeze(-1).unsqueeze(-1)) + shift.unsqueeze(-1).unsqueeze(-1)
+
+
+class LayerNorm2d(nn.LayerNorm):
+    def __init__(self, num_channels: int, eps: float = 1e-6, affine: bool = True):
+        super().__init__(num_channels, eps=eps, elementwise_affine=affine)
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        x = x.permute(0, 2, 3, 1)
+        x = F.layer_norm(x, self.normalized_shape, self.weight, self.bias, self.eps)
+        return x.permute(0, 3, 1, 2)
+
+
+class DiCoTimestepEmbedder(nn.Module):
+    def __init__(self, hidden_size: int, frequency_embedding_size: int = 256):
+        super().__init__()
+        self.mlp = nn.Sequential(
+            nn.Linear(frequency_embedding_size, hidden_size, bias=True),
+            nn.SiLU(),
+            nn.Linear(hidden_size, hidden_size, bias=True),
+        )
+        self.frequency_embedding_size = frequency_embedding_size
+
+    @staticmethod
+    def timestep_embedding(t: torch.Tensor, dim: int, max_period: int = 10000) -> torch.Tensor:
+        half = dim // 2
+        freqs = torch.exp(
+            -math.log(max_period) * torch.arange(start=0, end=half, dtype=torch.float32) / half
+        ).to(device=t.device)
+        args = t[:, None].float() * freqs[None]
+        embedding = torch.cat([torch.cos(args), torch.sin(args)], dim=-1)
+        if dim % 2:
+            embedding = torch.cat([embedding, torch.zeros_like(embedding[:, :1])], dim=-1)
+        return embedding
+
+    def forward(self, t: torch.Tensor) -> torch.Tensor:
+        t_freq = self.timestep_embedding(t, self.frequency_embedding_size)
+        weight_dtype = self.mlp[0].weight.dtype
+        return self.mlp(t_freq.to(dtype=weight_dtype))
+
+
+class DiCoLabelEmbedder(nn.Module):
+    def __init__(self, num_classes: int, hidden_size: int, dropout_prob: float):
+        super().__init__()
+        use_cfg_embedding = dropout_prob > 0
+        self.embedding_table = nn.Embedding(num_classes + use_cfg_embedding, hidden_size)
+        self.num_classes = num_classes
+        self.dropout_prob = dropout_prob
+
+    def token_drop(self, labels: torch.Tensor, force_drop_ids: Optional[torch.Tensor] = None) -> torch.Tensor:
+        if force_drop_ids is None:
+            drop_ids = torch.rand(labels.shape[0], device=labels.device) < self.dropout_prob
+        else:
+            drop_ids = force_drop_ids == 1
+        return torch.where(drop_ids, self.num_classes, labels)
+
+    def forward(
+        self,
+        labels: torch.Tensor,
+        train: bool,
+        force_drop_ids: Optional[torch.Tensor] = None,
+    ) -> torch.Tensor:
+        use_dropout = self.dropout_prob > 0
+        if (train and use_dropout) or (force_drop_ids is not None):
+            labels = self.token_drop(labels, force_drop_ids)
+        return self.embedding_table(labels)
+
+
+class DiCoMultiScaleLabelEmbedder(nn.Module):
+    def __init__(
+        self,
+        num_classes: int,
+        hidden_size_0: int,
+        hidden_size_1: int,
+        hidden_size_2: int,
+        dropout_prob: float,
+    ):
+        super().__init__()
+        use_cfg_embedding = dropout_prob > 0
+        self.embedding_table_0 = nn.Embedding(num_classes + use_cfg_embedding, hidden_size_0)
+        self.embedding_table_1 = nn.Embedding(num_classes + use_cfg_embedding, hidden_size_1)
+        self.embedding_table_2 = nn.Embedding(num_classes + use_cfg_embedding, hidden_size_2)
+        self.num_classes = num_classes
+        self.dropout_prob = dropout_prob
+
+    def token_drop(self, labels: torch.Tensor, force_drop_ids: Optional[torch.Tensor] = None) -> torch.Tensor:
+        if force_drop_ids is None:
+            drop_ids = torch.rand(labels.shape[0], device=labels.device) < self.dropout_prob
+        else:
+            drop_ids = force_drop_ids == 1
+        return torch.where(drop_ids, self.num_classes, labels)
+
+    def forward(
+        self,
+        labels: torch.Tensor,
+        train: bool,
+        force_drop_ids: Optional[torch.Tensor] = None,
+    ) -> Tuple[torch.Tensor, torch.Tensor, torch.Tensor]:
+        use_dropout = self.dropout_prob > 0
+        if (train and use_dropout) or (force_drop_ids is not None):
+            labels = self.token_drop(labels, force_drop_ids)
+        return (
+            self.embedding_table_0(labels),
+            self.embedding_table_1(labels),
+            self.embedding_table_2(labels),
+        )
+
+
+class DiCoBlock(nn.Module):
+    def __init__(self, hidden_size: int, mlp_ratio: float = 4.0):
+        super().__init__()
+        self.conv1 = nn.Conv2d(hidden_size, hidden_size, kernel_size=1, padding=0, stride=1, groups=1, bias=True)
+        self.conv2 = nn.Conv2d(
+            hidden_size, hidden_size, kernel_size=3, padding=1, stride=1, groups=hidden_size, bias=True
+        )
+        self.conv3 = nn.Conv2d(hidden_size, hidden_size, kernel_size=1, padding=0, stride=1, groups=1, bias=True)
+        self.ca = nn.Sequential(
+            nn.AdaptiveAvgPool2d(1),
+            nn.Conv2d(hidden_size, hidden_size, kernel_size=1, padding=0, stride=1, groups=1, bias=True),
+            nn.Sigmoid(),
+        )
+        ffn_channel = int(mlp_ratio * hidden_size)
+        self.conv4 = nn.Conv2d(hidden_size, ffn_channel, kernel_size=1, padding=0, stride=1, groups=1, bias=True)
+        self.conv5 = nn.Conv2d(ffn_channel, hidden_size, kernel_size=1, padding=0, stride=1, groups=1, bias=True)
+        self.norm1 = LayerNorm2d(hidden_size, affine=False, eps=1e-6)
+        self.norm2 = LayerNorm2d(hidden_size, affine=False, eps=1e-6)
+        self.adaLN_modulation = nn.Sequential(nn.SiLU(), nn.Linear(hidden_size, 6 * hidden_size, bias=True))
+
+    def forward(self, inp: torch.Tensor, c: torch.Tensor) -> torch.Tensor:
+        shift_msa, scale_msa, gate_msa, shift_mlp, scale_mlp, gate_mlp = self.adaLN_modulation(c).chunk(6, dim=1)
+        x = modulate(self.norm1(inp), shift_msa, scale_msa)
+        x = F.gelu(self.conv2(self.conv1(x)))
+        x = x * self.ca(x)
+        x = self.conv3(x)
+        x = inp + gate_msa.unsqueeze(-1).unsqueeze(-1) * x
+        x = x + gate_mlp.unsqueeze(-1).unsqueeze(-1) * self.conv5(
+            F.gelu(self.conv4(modulate(self.norm2(x), shift_mlp, scale_mlp)))
+        )
+        return x
+
+
+class DiCoFinalLayer(nn.Module):
+    def __init__(self, hidden_size: int, out_channels: int):
+        super().__init__()
+        self.norm_final = LayerNorm2d(hidden_size, affine=False, eps=1e-6)
+        self.out_proj = nn.Conv2d(hidden_size, out_channels, kernel_size=3, stride=1, padding=1, bias=True)
+        self.adaLN_modulation = nn.Sequential(nn.SiLU(), nn.Linear(hidden_size, 2 * hidden_size, bias=True))
+
+    def forward(self, x: torch.Tensor, c: torch.Tensor) -> torch.Tensor:
+        shift, scale = self.adaLN_modulation(c).chunk(2, dim=1)
+        x = modulate(self.norm_final(x), shift, scale)
+        return self.out_proj(x)
+
+
+class OverlapPatchEmbed(nn.Module):
+    def __init__(self, in_c: int = 3, embed_dim: int = 48, bias: bool = False):
+        super().__init__()
+        self.proj = nn.Conv2d(in_c, embed_dim, kernel_size=3, stride=1, padding=1, bias=bias)
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        return self.proj(x)
+
+
+class Downsample(nn.Module):
+    def __init__(self, n_feat: int):
+        super().__init__()
+        self.body = nn.Sequential(
+            nn.Conv2d(n_feat, n_feat // 2, kernel_size=3, stride=1, padding=1, bias=False),
+            nn.PixelUnshuffle(2),
+        )
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        return self.body(x)
+
+
+class Upsample(nn.Module):
+    def __init__(self, n_feat: int):
+        super().__init__()
+        self.body = nn.Sequential(
+            nn.Conv2d(n_feat, n_feat * 2, kernel_size=3, stride=1, padding=1, bias=False),
+            nn.PixelShuffle(2),
+        )
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        return self.body(x)
+
+
+class DiCoTransformer2DModel(ModelMixin, ConfigMixin):
+    r"""
+    DiCo (Diffusion ConvNet) denoiser for class-conditional latent diffusion.
+
+    ConvNet U-Net backbone with multi-scale adaLN conditioning, operating on VAE latents.
+    """
+
+    _supports_gradient_checkpointing = True
+
+    @register_to_config
+    def __init__(
+        self,
+        input_size: int = 32,
+        in_channels: int = 4,
+        hidden_size: int = 416,
+        depth: Optional[list[int]] = None,
+        mlp_ratio: float = 2.0,
+        class_dropout_prob: float = 0.1,
+        num_classes: int = 1000,
+        learn_sigma: bool = True,
+        model_type: str | None = None,
+        num_class_embeds: int | None = None,
+    ):
+        super().__init__()
+        if num_class_embeds is not None:
+            num_classes = int(num_class_embeds)
+        if model_type in DICO_PRESET_CONFIGS:
+            preset = DICO_PRESET_CONFIGS[model_type]
+            hidden_size = int(preset["hidden_size"])
+            depth = list(preset["depth"])
+            mlp_ratio = float(preset["mlp_ratio"])
+
+        if depth is None:
+            depth = [9, 9, 10, 9, 9]
+
+        self.learn_sigma = learn_sigma
+        self.in_channels = in_channels
+        self.out_channels = in_channels * 2 if learn_sigma else in_channels
+        self.num_classes = num_classes
+        self.gradient_checkpointing = False
+
+        self.x_embedder = OverlapPatchEmbed(in_channels, hidden_size, bias=True)
+        self.t_embedder_1 = DiCoTimestepEmbedder(hidden_size)
+        self.y_embedder = DiCoMultiScaleLabelEmbedder(
+            num_classes, hidden_size, hidden_size * 2, hidden_size * 4, class_dropout_prob
+        )
+        self.t_embedder_2 = DiCoTimestepEmbedder(hidden_size * 2)
+        self.t_embedder_3 = DiCoTimestepEmbedder(hidden_size * 4)
+
+        self.encoder_level_1 = nn.ModuleList([DiCoBlock(hidden_size, mlp_ratio) for _ in range(depth[0])])
+        self.down1_2 = Downsample(hidden_size)
+        self.encoder_level_2 = nn.ModuleList([DiCoBlock(hidden_size * 2, mlp_ratio) for _ in range(depth[1])])
+        self.down2_3 = Downsample(hidden_size * 2)
+        self.latent = nn.ModuleList([DiCoBlock(hidden_size * 4, mlp_ratio) for _ in range(depth[2])])
+        self.up3_2 = Upsample(int(hidden_size * 4))
+        self.reduce_chan_level2 = nn.Conv2d(int(hidden_size * 4), int(hidden_size * 2), kernel_size=1, bias=True)
+        self.decoder_level_2 = nn.ModuleList([DiCoBlock(hidden_size * 2, mlp_ratio) for _ in range(depth[3])])
+        self.up2_1 = Upsample(int(hidden_size * 2))
+        self.reduce_chan_level1 = nn.Conv2d(int(hidden_size * 2), int(hidden_size * 2), kernel_size=1, bias=True)
+        self.decoder_level_1 = nn.ModuleList([DiCoBlock(hidden_size * 2, mlp_ratio) for _ in range(depth[4])])
+        self.final_layer = DiCoFinalLayer(hidden_size * 2, self.out_channels)
+        self.initialize_weights()
+
+    def initialize_weights(self) -> None:
+        def _basic_init(module: nn.Module):
+            if isinstance(module, (nn.Linear, nn.Conv2d)):
+                torch.nn.init.xavier_uniform_(module.weight)
+                if module.bias is not None:
+                    nn.init.constant_(module.bias, 0)
+
+        self.apply(_basic_init)
+        w = self.x_embedder.proj.weight.data
+        nn.init.xavier_uniform_(w.view([w.shape[0], -1]))
+        nn.init.constant_(self.x_embedder.proj.bias, 0)
+        nn.init.normal_(self.y_embedder.embedding_table_0.weight, std=0.02)
+        nn.init.normal_(self.y_embedder.embedding_table_1.weight, std=0.02)
+        nn.init.normal_(self.y_embedder.embedding_table_2.weight, std=0.02)
+        for embedder in (self.t_embedder_1, self.t_embedder_2, self.t_embedder_3):
+            nn.init.normal_(embedder.mlp[0].weight, std=0.02)
+            nn.init.normal_(embedder.mlp[2].weight, std=0.02)
+
+        blocks = (
+            self.encoder_level_1
+            + self.encoder_level_2
+            + self.latent
+            + self.decoder_level_2
+            + self.decoder_level_1
+        )
+        for block in blocks:
+            nn.init.constant_(block.adaLN_modulation[-1].weight, 0)
+            nn.init.constant_(block.adaLN_modulation[-1].bias, 0)
+        nn.init.constant_(self.final_layer.adaLN_modulation[-1].weight, 0)
+        nn.init.constant_(self.final_layer.adaLN_modulation[-1].bias, 0)
+        nn.init.constant_(self.final_layer.out_proj.weight, 0)
+        nn.init.constant_(self.final_layer.out_proj.bias, 0)
+
+    def _run_block(self, block: DiCoBlock, x: torch.Tensor, c: torch.Tensor) -> torch.Tensor:
+        if self.training and self.gradient_checkpointing:
+            return torch.utils.checkpoint.checkpoint(block, x, c, use_reentrant=False)
+        return block(x, c)
+
+    def forward(
+        self,
+        hidden_states: torch.Tensor,
+        timestep: torch.LongTensor,
+        class_labels: torch.LongTensor,
+        force_drop_ids: Optional[torch.Tensor] = None,
+        return_dict: bool = True,
+    ) -> Transformer2DModelOutput | Tuple:
+        timestep = torch.as_tensor(timestep, device=hidden_states.device)
+        if timestep.ndim == 0:
+            timestep = timestep.repeat(hidden_states.shape[0])
+        else:
+            timestep = timestep.reshape(-1)
+            if timestep.shape[0] == 1 and hidden_states.shape[0] > 1:
+                timestep = timestep.repeat(hidden_states.shape[0])
+
+        x = self.x_embedder(hidden_states)
+        t1 = self.t_embedder_1(timestep)
+        y1, y2, y3 = self.y_embedder(class_labels, self.training, force_drop_ids=force_drop_ids)
+        c1 = t1 + y1
+        c2 = self.t_embedder_2(timestep) + y2
+        c3 = self.t_embedder_3(timestep) + y3
+
+        out_enc_level1 = x
+        for block in self.encoder_level_1:
+            out_enc_level1 = self._run_block(block, out_enc_level1, c1)
+        out_enc_level2 = self.down1_2(out_enc_level1)
+        for block in self.encoder_level_2:
+            out_enc_level2 = self._run_block(block, out_enc_level2, c2)
+        latent = self.down2_3(out_enc_level2)
+        for block in self.latent:
+            latent = self._run_block(block, latent, c3)
+
+        inp_dec_level2 = self.reduce_chan_level2(torch.cat([self.up3_2(latent), out_enc_level2], dim=1))
+        for block in self.decoder_level_2:
+            inp_dec_level2 = self._run_block(block, inp_dec_level2, c2)
+        inp_dec_level1 = self.reduce_chan_level1(torch.cat([self.up2_1(inp_dec_level2), out_enc_level1], dim=1))
+        for block in self.decoder_level_1:
+            inp_dec_level1 = self._run_block(block, inp_dec_level1, c2)
+
+        output = self.final_layer(inp_dec_level1, c2)
+        if not return_dict:
+            return (output,)
+        return Transformer2DModelOutput(sample=output)
+
+    @classmethod
+    def from_dico_checkpoint(
+        cls,
+        checkpoint_path: str,
+        weights: Literal["model", "ema"] = "ema",
+        map_location: str = "cpu",
+        strict: bool = True,
+        model_type: str | None = None,
+    ) -> Tuple["DiCoTransformer2DModel", Dict[str, object]]:
+        checkpoint = torch.load(checkpoint_path, map_location=map_location, weights_only=False)
+        state_dict = checkpoint
+        if isinstance(checkpoint, Mapping):
+            if weights in checkpoint:
+                state_dict = checkpoint[weights]
+            elif "state_dict" in checkpoint:
+                state_dict = checkpoint["state_dict"]
+
+        state_dict = remap_legacy_state_dict(state_dict)
+
+        ckpt_args = checkpoint.get("args") if isinstance(checkpoint, Mapping) else None
+        args_dict: Dict[str, object] = {}
+        if ckpt_args is not None:
+            if isinstance(ckpt_args, argparse.Namespace):
+                args_dict = vars(ckpt_args)
+            elif isinstance(ckpt_args, Mapping):
+                args_dict = dict(ckpt_args)
+
+        resolved_model_type = model_type or args_dict.get("model") or args_dict.get("model_type")
+        image_size = int(args_dict.get("image_size") or 256)
+        num_classes = int(args_dict.get("num_classes") or 1000)
+
+        config: Dict[str, object] = {
+            "input_size": image_size // 8,
+            "num_classes": num_classes,
+            "learn_sigma": infer_learn_sigma(state_dict),
+        }
+        if resolved_model_type in DICO_PRESET_CONFIGS:
+            config["model_type"] = resolved_model_type
+
+        model = cls(**config)
+        model.load_state_dict(state_dict, strict=strict)
+        metadata = {
+            "checkpoint_path": checkpoint_path,
+            "weights": weights,
+            "model_type": resolved_model_type,
+            "source_args": ckpt_args,
+        }
+        return model, metadata
+
+
+DiCoDiffusersModel = DiCoTransformer2DModel

DiCo-S-256/vae/config.json

@@ -0,0 +1,38 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.38.0",
+  "_name_or_path": "stabilityai/sd-vae-ft-ema",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "force_upcast": true,
+  "in_channels": 3,
+  "latent_channels": 4,
+  "latents_mean": null,
+  "latents_std": null,
+  "layers_per_block": 2,
+  "mid_block_add_attention": true,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 256,
+  "scaling_factor": 0.18215,
+  "shift_factor": null,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ],
+  "use_post_quant_conv": true,
+  "use_quant_conv": true
+}

DiCo-S-256/vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:703abdcd7c389316b5128faa9b750a530ea1680b453170b27afebac5e4db30c4
+size 334643268

DiCo-XL-256/model_index.json

@@ -0,0 +1,1021 @@
+{
+  "_class_name": [
+    "pipeline",
+    "DiCoPipeline"
+  ],
+  "_diffusers_version": "0.38.0",
+  "scheduler": [
+    "diffusers",
+    "DDIMScheduler"
+  ],
+  "transformer": [
+    "transformer_dico",
+    "DiCoTransformer2DModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ],
+  "id2label": {
+    "0": "tench, Tinca tinca",
+    "1": "goldfish, Carassius auratus",
+    "2": "great white shark, white shark, man-eater, man-eating shark, Carcharodon carcharias",
+    "3": "tiger shark, Galeocerdo cuvieri",
+    "4": "hammerhead, hammerhead shark",
+    "5": "electric ray, crampfish, numbfish, torpedo",
+    "6": "stingray",
+    "7": "cock",
+    "8": "hen",
+    "9": "ostrich, Struthio camelus",
+    "10": "brambling, Fringilla montifringilla",
+    "11": "goldfinch, Carduelis carduelis",
+    "12": "house finch, linnet, Carpodacus mexicanus",
+    "13": "junco, snowbird",
+    "14": "indigo bunting, indigo finch, indigo bird, Passerina cyanea",
+    "15": "robin, American robin, Turdus migratorius",
+    "16": "bulbul",
+    "17": "jay",
+    "18": "magpie",
+    "19": "chickadee",
+    "20": "water ouzel, dipper",
+    "21": "kite",
+    "22": "bald eagle, American eagle, Haliaeetus leucocephalus",
+    "23": "vulture",
+    "24": "great grey owl, great gray owl, Strix nebulosa",
+    "25": "European fire salamander, Salamandra salamandra",
+    "26": "common newt, Triturus vulgaris",
+    "27": "eft",
+    "28": "spotted salamander, Ambystoma maculatum",
+    "29": "axolotl, mud puppy, Ambystoma mexicanum",
+    "30": "bullfrog, Rana catesbeiana",
+    "31": "tree frog, tree-frog",
+    "32": "tailed frog, bell toad, ribbed toad, tailed toad, Ascaphus trui",
+    "33": "loggerhead, loggerhead turtle, Caretta caretta",
+    "34": "leatherback turtle, leatherback, leathery turtle, Dermochelys coriacea",
+    "35": "mud turtle",
+    "36": "terrapin",
+    "37": "box turtle, box tortoise",
+    "38": "banded gecko",
+    "39": "common iguana, iguana, Iguana iguana",
+    "40": "American chameleon, anole, Anolis carolinensis",
+    "41": "whiptail, whiptail lizard",
+    "42": "agama",
+    "43": "frilled lizard, Chlamydosaurus kingi",
+    "44": "alligator lizard",
+    "45": "Gila monster, Heloderma suspectum",
+    "46": "green lizard, Lacerta viridis",
+    "47": "African chameleon, Chamaeleo chamaeleon",
+    "48": "Komodo dragon, Komodo lizard, dragon lizard, giant lizard, Varanus komodoensis",
+    "49": "African crocodile, Nile crocodile, Crocodylus niloticus",
+    "50": "American alligator, Alligator mississipiensis",
+    "51": "triceratops",
+    "52": "thunder snake, worm snake, Carphophis amoenus",
+    "53": "ringneck snake, ring-necked snake, ring snake",
+    "54": "hognose snake, puff adder, sand viper",
+    "55": "green snake, grass snake",
+    "56": "king snake, kingsnake",
+    "57": "garter snake, grass snake",
+    "58": "water snake",
+    "59": "vine snake",
+    "60": "night snake, Hypsiglena torquata",
+    "61": "boa constrictor, Constrictor constrictor",
+    "62": "rock python, rock snake, Python sebae",
+    "63": "Indian cobra, Naja naja",
+    "64": "green mamba",
+    "65": "sea snake",
+    "66": "horned viper, cerastes, sand viper, horned asp, Cerastes cornutus",
+    "67": "diamondback, diamondback rattlesnake, Crotalus adamanteus",
+    "68": "sidewinder, horned rattlesnake, Crotalus cerastes",
+    "69": "trilobite",
+    "70": "harvestman, daddy longlegs, Phalangium opilio",
+    "71": "scorpion",
+    "72": "black and gold garden spider, Argiope aurantia",
+    "73": "barn spider, Araneus cavaticus",
+    "74": "garden spider, Aranea diademata",
+    "75": "black widow, Latrodectus mactans",
+    "76": "tarantula",
+    "77": "wolf spider, hunting spider",
+    "78": "tick",
+    "79": "centipede",
+    "80": "black grouse",
+    "81": "ptarmigan",
+    "82": "ruffed grouse, partridge, Bonasa umbellus",
+    "83": "prairie chicken, prairie grouse, prairie fowl",
+    "84": "peacock",
+    "85": "quail",
+    "86": "partridge",
+    "87": "African grey, African gray, Psittacus erithacus",
+    "88": "macaw",
+    "89": "sulphur-crested cockatoo, Kakatoe galerita, Cacatua galerita",
+    "90": "lorikeet",
+    "91": "coucal",
+    "92": "bee eater",
+    "93": "hornbill",
+    "94": "hummingbird",
+    "95": "jacamar",
+    "96": "toucan",
+    "97": "drake",
+    "98": "red-breasted merganser, Mergus serrator",
+    "99": "goose",
+    "100": "black swan, Cygnus atratus",
+    "101": "tusker",
+    "102": "echidna, spiny anteater, anteater",
+    "103": "platypus, duckbill, duckbilled platypus, duck-billed platypus, Ornithorhynchus anatinus",
+    "104": "wallaby, brush kangaroo",
+    "105": "koala, koala bear, kangaroo bear, native bear, Phascolarctos cinereus",
+    "106": "wombat",
+    "107": "jellyfish",
+    "108": "sea anemone, anemone",
+    "109": "brain coral",
+    "110": "flatworm, platyhelminth",
+    "111": "nematode, nematode worm, roundworm",
+    "112": "conch",
+    "113": "snail",
+    "114": "slug",
+    "115": "sea slug, nudibranch",
+    "116": "chiton, coat-of-mail shell, sea cradle, polyplacophore",
+    "117": "chambered nautilus, pearly nautilus, nautilus",
+    "118": "Dungeness crab, Cancer magister",
+    "119": "rock crab, Cancer irroratus",
+    "120": "fiddler crab",
+    "121": "king crab, Alaska crab, Alaskan king crab, Alaska king crab, Paralithodes camtschatica",
+    "122": "American lobster, Northern lobster, Maine lobster, Homarus americanus",
+    "123": "spiny lobster, langouste, rock lobster, crawfish, crayfish, sea crawfish",
+    "124": "crayfish, crawfish, crawdad, crawdaddy",
+    "125": "hermit crab",
+    "126": "isopod",
+    "127": "white stork, Ciconia ciconia",
+    "128": "black stork, Ciconia nigra",
+    "129": "spoonbill",
+    "130": "flamingo",
+    "131": "little blue heron, Egretta caerulea",
+    "132": "American egret, great white heron, Egretta albus",
+    "133": "bittern",
+    "134": "crane",
+    "135": "limpkin, Aramus pictus",
+    "136": "European gallinule, Porphyrio porphyrio",
+    "137": "American coot, marsh hen, mud hen, water hen, Fulica americana",
+    "138": "bustard",
+    "139": "ruddy turnstone, Arenaria interpres",
+    "140": "red-backed sandpiper, dunlin, Erolia alpina",
+    "141": "redshank, Tringa totanus",
+    "142": "dowitcher",
+    "143": "oystercatcher, oyster catcher",
+    "144": "pelican",
+    "145": "king penguin, Aptenodytes patagonica",
+    "146": "albatross, mollymawk",
+    "147": "grey whale, gray whale, devilfish, Eschrichtius gibbosus, Eschrichtius robustus",
+    "148": "killer whale, killer, orca, grampus, sea wolf, Orcinus orca",
+    "149": "dugong, Dugong dugon",
+    "150": "sea lion",
+    "151": "Chihuahua",
+    "152": "Japanese spaniel",
+    "153": "Maltese dog, Maltese terrier, Maltese",
+    "154": "Pekinese, Pekingese, Peke",
+    "155": "Shih-Tzu",
+    "156": "Blenheim spaniel",
+    "157": "papillon",
+    "158": "toy terrier",
+    "159": "Rhodesian ridgeback",
+    "160": "Afghan hound, Afghan",
+    "161": "basset, basset hound",
+    "162": "beagle",
+    "163": "bloodhound, sleuthhound",
+    "164": "bluetick",
+    "165": "black-and-tan coonhound",
+    "166": "Walker hound, Walker foxhound",
+    "167": "English foxhound",
+    "168": "redbone",
+    "169": "borzoi, Russian wolfhound",
+    "170": "Irish wolfhound",
+    "171": "Italian greyhound",
+    "172": "whippet",
+    "173": "Ibizan hound, Ibizan Podenco",
+    "174": "Norwegian elkhound, elkhound",
+    "175": "otterhound, otter hound",
+    "176": "Saluki, gazelle hound",
+    "177": "Scottish deerhound, deerhound",
+    "178": "Weimaraner",
+    "179": "Staffordshire bullterrier, Staffordshire bull terrier",
+    "180": "American Staffordshire terrier, Staffordshire terrier, American pit bull terrier, pit bull terrier",
+    "181": "Bedlington terrier",
+    "182": "Border terrier",
+    "183": "Kerry blue terrier",
+    "184": "Irish terrier",
+    "185": "Norfolk terrier",
+    "186": "Norwich terrier",
+    "187": "Yorkshire terrier",
+    "188": "wire-haired fox terrier",
+    "189": "Lakeland terrier",
+    "190": "Sealyham terrier, Sealyham",
+    "191": "Airedale, Airedale terrier",
+    "192": "cairn, cairn terrier",
+    "193": "Australian terrier",
+    "194": "Dandie Dinmont, Dandie Dinmont terrier",
+    "195": "Boston bull, Boston terrier",
+    "196": "miniature schnauzer",
+    "197": "giant schnauzer",
+    "198": "standard schnauzer",
+    "199": "Scotch terrier, Scottish terrier, Scottie",
+    "200": "Tibetan terrier, chrysanthemum dog",
+    "201": "silky terrier, Sydney silky",
+    "202": "soft-coated wheaten terrier",
+    "203": "West Highland white terrier",
+    "204": "Lhasa, Lhasa apso",
+    "205": "flat-coated retriever",
+    "206": "curly-coated retriever",
+    "207": "golden retriever",
+    "208": "Labrador retriever",
+    "209": "Chesapeake Bay retriever",
+    "210": "German short-haired pointer",
+    "211": "vizsla, Hungarian pointer",
+    "212": "English setter",
+    "213": "Irish setter, red setter",
+    "214": "Gordon setter",
+    "215": "Brittany spaniel",
+    "216": "clumber, clumber spaniel",
+    "217": "English springer, English springer spaniel",
+    "218": "Welsh springer spaniel",
+    "219": "cocker spaniel, English cocker spaniel, cocker",
+    "220": "Sussex spaniel",
+    "221": "Irish water spaniel",
+    "222": "kuvasz",
+    "223": "schipperke",
+    "224": "groenendael",
+    "225": "malinois",
+    "226": "briard",
+    "227": "kelpie",
+    "228": "komondor",
+    "229": "Old English sheepdog, bobtail",
+    "230": "Shetland sheepdog, Shetland sheep dog, Shetland",
+    "231": "collie",
+    "232": "Border collie",
+    "233": "Bouvier des Flandres, Bouviers des Flandres",
+    "234": "Rottweiler",
+    "235": "German shepherd, German shepherd dog, German police dog, alsatian",
+    "236": "Doberman, Doberman pinscher",
+    "237": "miniature pinscher",
+    "238": "Greater Swiss Mountain dog",
+    "239": "Bernese mountain dog",
+    "240": "Appenzeller",
+    "241": "EntleBucher",
+    "242": "boxer",
+    "243": "bull mastiff",
+    "244": "Tibetan mastiff",
+    "245": "French bulldog",
+    "246": "Great Dane",
+    "247": "Saint Bernard, St Bernard",
+    "248": "Eskimo dog, husky",
+    "249": "malamute, malemute, Alaskan malamute",
+    "250": "Siberian husky",
+    "251": "dalmatian, coach dog, carriage dog",
+    "252": "affenpinscher, monkey pinscher, monkey dog",
+    "253": "basenji",
+    "254": "pug, pug-dog",
+    "255": "Leonberg",
+    "256": "Newfoundland, Newfoundland dog",
+    "257": "Great Pyrenees",
+    "258": "Samoyed, Samoyede",
+    "259": "Pomeranian",
+    "260": "chow, chow chow",
+    "261": "keeshond",
+    "262": "Brabancon griffon",
+    "263": "Pembroke, Pembroke Welsh corgi",
+    "264": "Cardigan, Cardigan Welsh corgi",
+    "265": "toy poodle",
+    "266": "miniature poodle",
+    "267": "standard poodle",
+    "268": "Mexican hairless",
+    "269": "timber wolf, grey wolf, gray wolf, Canis lupus",
+    "270": "white wolf, Arctic wolf, Canis lupus tundrarum",
+    "271": "red wolf, maned wolf, Canis rufus, Canis niger",
+    "272": "coyote, prairie wolf, brush wolf, Canis latrans",
+    "273": "dingo, warrigal, warragal, Canis dingo",
+    "274": "dhole, Cuon alpinus",
+    "275": "African hunting dog, hyena dog, Cape hunting dog, Lycaon pictus",
+    "276": "hyena, hyaena",
+    "277": "red fox, Vulpes vulpes",
+    "278": "kit fox, Vulpes macrotis",
+    "279": "Arctic fox, white fox, Alopex lagopus",
+    "280": "grey fox, gray fox, Urocyon cinereoargenteus",
+    "281": "tabby, tabby cat",
+    "282": "tiger cat",
+    "283": "Persian cat",
+    "284": "Siamese cat, Siamese",
+    "285": "Egyptian cat",
+    "286": "cougar, puma, catamount, mountain lion, painter, panther, Felis concolor",
+    "287": "lynx, catamount",
+    "288": "leopard, Panthera pardus",
+    "289": "snow leopard, ounce, Panthera uncia",
+    "290": "jaguar, panther, Panthera onca, Felis onca",
+    "291": "lion, king of beasts, Panthera leo",
+    "292": "tiger, Panthera tigris",
+    "293": "cheetah, chetah, Acinonyx jubatus",
+    "294": "brown bear, bruin, Ursus arctos",
+    "295": "American black bear, black bear, Ursus americanus, Euarctos americanus",
+    "296": "ice bear, polar bear, Ursus Maritimus, Thalarctos maritimus",
+    "297": "sloth bear, Melursus ursinus, Ursus ursinus",
+    "298": "mongoose",
+    "299": "meerkat, mierkat",
+    "300": "tiger beetle",
+    "301": "ladybug, ladybeetle, lady beetle, ladybird, ladybird beetle",
+    "302": "ground beetle, carabid beetle",
+    "303": "long-horned beetle, longicorn, longicorn beetle",
+    "304": "leaf beetle, chrysomelid",
+    "305": "dung beetle",
+    "306": "rhinoceros beetle",
+    "307": "weevil",
+    "308": "fly",
+    "309": "bee",
+    "310": "ant, emmet, pismire",
+    "311": "grasshopper, hopper",
+    "312": "cricket",
+    "313": "walking stick, walkingstick, stick insect",
+    "314": "cockroach, roach",
+    "315": "mantis, mantid",
+    "316": "cicada, cicala",
+    "317": "leafhopper",
+    "318": "lacewing, lacewing fly",
+    "319": "dragonfly, darning needle, devils darning needle, sewing needle, snake feeder, snake doctor, mosquito hawk, skeeter hawk",
+    "320": "damselfly",
+    "321": "admiral",
+    "322": "ringlet, ringlet butterfly",
+    "323": "monarch, monarch butterfly, milkweed butterfly, Danaus plexippus",
+    "324": "cabbage butterfly",
+    "325": "sulphur butterfly, sulfur butterfly",
+    "326": "lycaenid, lycaenid butterfly",
+    "327": "starfish, sea star",
+    "328": "sea urchin",
+    "329": "sea cucumber, holothurian",
+    "330": "wood rabbit, cottontail, cottontail rabbit",
+    "331": "hare",
+    "332": "Angora, Angora rabbit",
+    "333": "hamster",
+    "334": "porcupine, hedgehog",
+    "335": "fox squirrel, eastern fox squirrel, Sciurus niger",
+    "336": "marmot",
+    "337": "beaver",
+    "338": "guinea pig, Cavia cobaya",
+    "339": "sorrel",
+    "340": "zebra",
+    "341": "hog, pig, grunter, squealer, Sus scrofa",
+    "342": "wild boar, boar, Sus scrofa",
+    "343": "warthog",
+    "344": "hippopotamus, hippo, river horse, Hippopotamus amphibius",
+    "345": "ox",
+    "346": "water buffalo, water ox, Asiatic buffalo, Bubalus bubalis",
+    "347": "bison",
+    "348": "ram, tup",
+    "349": "bighorn, bighorn sheep, cimarron, Rocky Mountain bighorn, Rocky Mountain sheep, Ovis canadensis",
+    "350": "ibex, Capra ibex",
+    "351": "hartebeest",
+    "352": "impala, Aepyceros melampus",
+    "353": "gazelle",
+    "354": "Arabian camel, dromedary, Camelus dromedarius",
+    "355": "llama",
+    "356": "weasel",
+    "357": "mink",
+    "358": "polecat, fitch, foulmart, foumart, Mustela putorius",
+    "359": "black-footed ferret, ferret, Mustela nigripes",
+    "360": "otter",
+    "361": "skunk, polecat, wood pussy",
+    "362": "badger",
+    "363": "armadillo",
+    "364": "three-toed sloth, ai, Bradypus tridactylus",
+    "365": "orangutan, orang, orangutang, Pongo pygmaeus",
+    "366": "gorilla, Gorilla gorilla",
+    "367": "chimpanzee, chimp, Pan troglodytes",
+    "368": "gibbon, Hylobates lar",
+    "369": "siamang, Hylobates syndactylus, Symphalangus syndactylus",
+    "370": "guenon, guenon monkey",
+    "371": "patas, hussar monkey, Erythrocebus patas",
+    "372": "baboon",
+    "373": "macaque",
+    "374": "langur",
+    "375": "colobus, colobus monkey",
+    "376": "proboscis monkey, Nasalis larvatus",
+    "377": "marmoset",
+    "378": "capuchin, ringtail, Cebus capucinus",
+    "379": "howler monkey, howler",
+    "380": "titi, titi monkey",
+    "381": "spider monkey, Ateles geoffroyi",
+    "382": "squirrel monkey, Saimiri sciureus",
+    "383": "Madagascar cat, ring-tailed lemur, Lemur catta",
+    "384": "indri, indris, Indri indri, Indri brevicaudatus",
+    "385": "Indian elephant, Elephas maximus",
+    "386": "African elephant, Loxodonta africana",
+    "387": "lesser panda, red panda, panda, bear cat, cat bear, Ailurus fulgens",
+    "388": "giant panda, panda, panda bear, coon bear, Ailuropoda melanoleuca",
+    "389": "barracouta, snoek",
+    "390": "eel",
+    "391": "coho, cohoe, coho salmon, blue jack, silver salmon, Oncorhynchus kisutch",
+    "392": "rock beauty, Holocanthus tricolor",
+    "393": "anemone fish",
+    "394": "sturgeon",
+    "395": "gar, garfish, garpike, billfish, Lepisosteus osseus",
+    "396": "lionfish",
+    "397": "puffer, pufferfish, blowfish, globefish",
+    "398": "abacus",
+    "399": "abaya",
+    "400": "academic gown, academic robe, judge robe",
+    "401": "accordion, piano accordion, squeeze box",
+    "402": "acoustic guitar",
+    "403": "aircraft carrier, carrier, flattop, attack aircraft carrier",
+    "404": "airliner",
+    "405": "airship, dirigible",
+    "406": "altar",
+    "407": "ambulance",
+    "408": "amphibian, amphibious vehicle",
+    "409": "analog clock",
+    "410": "apiary, bee house",
+    "411": "apron",
+    "412": "ashcan, trash can, garbage can, wastebin, ash bin, ash-bin, ashbin, dustbin, trash barrel, trash bin",
+    "413": "assault rifle, assault gun",
+    "414": "backpack, back pack, knapsack, packsack, rucksack, haversack",
+    "415": "bakery, bakeshop, bakehouse",
+    "416": "balance beam, beam",
+    "417": "balloon",
+    "418": "ballpoint, ballpoint pen, ballpen, Biro",
+    "419": "Band Aid",
+    "420": "banjo",
+    "421": "bannister, banister, balustrade, balusters, handrail",
+    "422": "barbell",
+    "423": "barber chair",
+    "424": "barbershop",
+    "425": "barn",
+    "426": "barometer",
+    "427": "barrel, cask",
+    "428": "barrow, garden cart, lawn cart, wheelbarrow",
+    "429": "baseball",
+    "430": "basketball",
+    "431": "bassinet",
+    "432": "bassoon",
+    "433": "bathing cap, swimming cap",
+    "434": "bath towel",
+    "435": "bathtub, bathing tub, bath, tub",
+    "436": "beach wagon, station wagon, wagon, estate car, beach waggon, station waggon, waggon",
+    "437": "beacon, lighthouse, beacon light, pharos",
+    "438": "beaker",
+    "439": "bearskin, busby, shako",
+    "440": "beer bottle",
+    "441": "beer glass",
+    "442": "bell cote, bell cot",
+    "443": "bib",
+    "444": "bicycle-built-for-two, tandem bicycle, tandem",
+    "445": "bikini, two-piece",
+    "446": "binder, ring-binder",
+    "447": "binoculars, field glasses, opera glasses",
+    "448": "birdhouse",
+    "449": "boathouse",
+    "450": "bobsled, bobsleigh, bob",
+    "451": "bolo tie, bolo, bola tie, bola",
+    "452": "bonnet, poke bonnet",
+    "453": "bookcase",
+    "454": "bookshop, bookstore, bookstall",
+    "455": "bottlecap",
+    "456": "bow",
+    "457": "bow tie, bow-tie, bowtie",
+    "458": "brass, memorial tablet, plaque",
+    "459": "brassiere, bra, bandeau",
+    "460": "breakwater, groin, groyne, mole, bulwark, seawall, jetty",
+    "461": "breastplate, aegis, egis",
+    "462": "broom",
+    "463": "bucket, pail",
+    "464": "buckle",
+    "465": "bulletproof vest",
+    "466": "bullet train, bullet",
+    "467": "butcher shop, meat market",
+    "468": "cab, hack, taxi, taxicab",
+    "469": "caldron, cauldron",
+    "470": "candle, taper, wax light",
+    "471": "cannon",
+    "472": "canoe",
+    "473": "can opener, tin opener",
+    "474": "cardigan",
+    "475": "car mirror",
+    "476": "carousel, carrousel, merry-go-round, roundabout, whirligig",
+    "477": "carpenters kit, tool kit",
+    "478": "carton",
+    "479": "car wheel",
+    "480": "cash machine, cash dispenser, automated teller machine, automatic teller machine, automated teller, automatic teller, ATM",
+    "481": "cassette",
+    "482": "cassette player",
+    "483": "castle",
+    "484": "catamaran",
+    "485": "CD player",
+    "486": "cello, violoncello",
+    "487": "cellular telephone, cellular phone, cellphone, cell, mobile phone",
+    "488": "chain",
+    "489": "chainlink fence",
+    "490": "chain mail, ring mail, mail, chain armor, chain armour, ring armor, ring armour",
+    "491": "chain saw, chainsaw",
+    "492": "chest",
+    "493": "chiffonier, commode",
+    "494": "chime, bell, gong",
+    "495": "china cabinet, china closet",
+    "496": "Christmas stocking",
+    "497": "church, church building",
+    "498": "cinema, movie theater, movie theatre, movie house, picture palace",
+    "499": "cleaver, meat cleaver, chopper",
+    "500": "cliff dwelling",
+    "501": "cloak",
+    "502": "clog, geta, patten, sabot",
+    "503": "cocktail shaker",
+    "504": "coffee mug",
+    "505": "coffeepot",
+    "506": "coil, spiral, volute, whorl, helix",
+    "507": "combination lock",
+    "508": "computer keyboard, keypad",
+    "509": "confectionery, confectionary, candy store",
+    "510": "container ship, containership, container vessel",
+    "511": "convertible",
+    "512": "corkscrew, bottle screw",
+    "513": "cornet, horn, trumpet, trump",
+    "514": "cowboy boot",
+    "515": "cowboy hat, ten-gallon hat",
+    "516": "cradle",
+    "517": "crane",
+    "518": "crash helmet",
+    "519": "crate",
+    "520": "crib, cot",
+    "521": "Crock Pot",
+    "522": "croquet ball",
+    "523": "crutch",
+    "524": "cuirass",
+    "525": "dam, dike, dyke",
+    "526": "desk",
+    "527": "desktop computer",
+    "528": "dial telephone, dial phone",
+    "529": "diaper, nappy, napkin",
+    "530": "digital clock",
+    "531": "digital watch",
+    "532": "dining table, board",
+    "533": "dishrag, dishcloth",
+    "534": "dishwasher, dish washer, dishwashing machine",
+    "535": "disk brake, disc brake",
+    "536": "dock, dockage, docking facility",
+    "537": "dogsled, dog sled, dog sleigh",
+    "538": "dome",
+    "539": "doormat, welcome mat",
+    "540": "drilling platform, offshore rig",
+    "541": "drum, membranophone, tympan",
+    "542": "drumstick",
+    "543": "dumbbell",
+    "544": "Dutch oven",
+    "545": "electric fan, blower",
+    "546": "electric guitar",
+    "547": "electric locomotive",
+    "548": "entertainment center",
+    "549": "envelope",
+    "550": "espresso maker",
+    "551": "face powder",
+    "552": "feather boa, boa",
+    "553": "file, file cabinet, filing cabinet",
+    "554": "fireboat",
+    "555": "fire engine, fire truck",
+    "556": "fire screen, fireguard",
+    "557": "flagpole, flagstaff",
+    "558": "flute, transverse flute",
+    "559": "folding chair",
+    "560": "football helmet",
+    "561": "forklift",
+    "562": "fountain",
+    "563": "fountain pen",
+    "564": "four-poster",
+    "565": "freight car",
+    "566": "French horn, horn",
+    "567": "frying pan, frypan, skillet",
+    "568": "fur coat",
+    "569": "garbage truck, dustcart",
+    "570": "gasmask, respirator, gas helmet",
+    "571": "gas pump, gasoline pump, petrol pump, island dispenser",
+    "572": "goblet",
+    "573": "go-kart",
+    "574": "golf ball",
+    "575": "golfcart, golf cart",
+    "576": "gondola",
+    "577": "gong, tam-tam",
+    "578": "gown",
+    "579": "grand piano, grand",
+    "580": "greenhouse, nursery, glasshouse",
+    "581": "grille, radiator grille",
+    "582": "grocery store, grocery, food market, market",
+    "583": "guillotine",
+    "584": "hair slide",
+    "585": "hair spray",
+    "586": "half track",
+    "587": "hammer",
+    "588": "hamper",
+    "589": "hand blower, blow dryer, blow drier, hair dryer, hair drier",
+    "590": "hand-held computer, hand-held microcomputer",
+    "591": "handkerchief, hankie, hanky, hankey",
+    "592": "hard disc, hard disk, fixed disk",
+    "593": "harmonica, mouth organ, harp, mouth harp",
+    "594": "harp",
+    "595": "harvester, reaper",
+    "596": "hatchet",
+    "597": "holster",
+    "598": "home theater, home theatre",
+    "599": "honeycomb",
+    "600": "hook, claw",
+    "601": "hoopskirt, crinoline",
+    "602": "horizontal bar, high bar",
+    "603": "horse cart, horse-cart",
+    "604": "hourglass",
+    "605": "iPod",
+    "606": "iron, smoothing iron",
+    "607": "jack-o-lantern",
+    "608": "jean, blue jean, denim",
+    "609": "jeep, landrover",
+    "610": "jersey, T-shirt, tee shirt",
+    "611": "jigsaw puzzle",
+    "612": "jinrikisha, ricksha, rickshaw",
+    "613": "joystick",
+    "614": "kimono",
+    "615": "knee pad",
+    "616": "knot",
+    "617": "lab coat, laboratory coat",
+    "618": "ladle",
+    "619": "lampshade, lamp shade",
+    "620": "laptop, laptop computer",
+    "621": "lawn mower, mower",
+    "622": "lens cap, lens cover",
+    "623": "letter opener, paper knife, paperknife",
+    "624": "library",
+    "625": "lifeboat",
+    "626": "lighter, light, igniter, ignitor",
+    "627": "limousine, limo",
+    "628": "liner, ocean liner",
+    "629": "lipstick, lip rouge",
+    "630": "Loafer",
+    "631": "lotion",
+    "632": "loudspeaker, speaker, speaker unit, loudspeaker system, speaker system",
+    "633": "loupe, jewelers loupe",
+    "634": "lumbermill, sawmill",
+    "635": "magnetic compass",
+    "636": "mailbag, postbag",
+    "637": "mailbox, letter box",
+    "638": "maillot",
+    "639": "maillot, tank suit",
+    "640": "manhole cover",
+    "641": "maraca",
+    "642": "marimba, xylophone",
+    "643": "mask",
+    "644": "matchstick",
+    "645": "maypole",
+    "646": "maze, labyrinth",
+    "647": "measuring cup",
+    "648": "medicine chest, medicine cabinet",
+    "649": "megalith, megalithic structure",
+    "650": "microphone, mike",
+    "651": "microwave, microwave oven",
+    "652": "military uniform",
+    "653": "milk can",
+    "654": "minibus",
+    "655": "miniskirt, mini",
+    "656": "minivan",
+    "657": "missile",
+    "658": "mitten",
+    "659": "mixing bowl",
+    "660": "mobile home, manufactured home",
+    "661": "Model T",
+    "662": "modem",
+    "663": "monastery",
+    "664": "monitor",
+    "665": "moped",
+    "666": "mortar",
+    "667": "mortarboard",
+    "668": "mosque",
+    "669": "mosquito net",
+    "670": "motor scooter, scooter",
+    "671": "mountain bike, all-terrain bike, off-roader",
+    "672": "mountain tent",
+    "673": "mouse, computer mouse",
+    "674": "mousetrap",
+    "675": "moving van",
+    "676": "muzzle",
+    "677": "nail",
+    "678": "neck brace",
+    "679": "necklace",
+    "680": "nipple",
+    "681": "notebook, notebook computer",
+    "682": "obelisk",
+    "683": "oboe, hautboy, hautbois",
+    "684": "ocarina, sweet potato",
+    "685": "odometer, hodometer, mileometer, milometer",
+    "686": "oil filter",
+    "687": "organ, pipe organ",
+    "688": "oscilloscope, scope, cathode-ray oscilloscope, CRO",
+    "689": "overskirt",
+    "690": "oxcart",
+    "691": "oxygen mask",
+    "692": "packet",
+    "693": "paddle, boat paddle",
+    "694": "paddlewheel, paddle wheel",
+    "695": "padlock",
+    "696": "paintbrush",
+    "697": "pajama, pyjama, pjs, jammies",
+    "698": "palace",
+    "699": "panpipe, pandean pipe, syrinx",
+    "700": "paper towel",
+    "701": "parachute, chute",
+    "702": "parallel bars, bars",
+    "703": "park bench",
+    "704": "parking meter",
+    "705": "passenger car, coach, carriage",
+    "706": "patio, terrace",
+    "707": "pay-phone, pay-station",
+    "708": "pedestal, plinth, footstall",
+    "709": "pencil box, pencil case",
+    "710": "pencil sharpener",
+    "711": "perfume, essence",
+    "712": "Petri dish",
+    "713": "photocopier",
+    "714": "pick, plectrum, plectron",
+    "715": "pickelhaube",
+    "716": "picket fence, paling",
+    "717": "pickup, pickup truck",
+    "718": "pier",
+    "719": "piggy bank, penny bank",
+    "720": "pill bottle",
+    "721": "pillow",
+    "722": "ping-pong ball",
+    "723": "pinwheel",
+    "724": "pirate, pirate ship",
+    "725": "pitcher, ewer",
+    "726": "plane, carpenters plane, woodworking plane",
+    "727": "planetarium",
+    "728": "plastic bag",
+    "729": "plate rack",
+    "730": "plow, plough",
+    "731": "plunger, plumbers helper",
+    "732": "Polaroid camera, Polaroid Land camera",
+    "733": "pole",
+    "734": "police van, police wagon, paddy wagon, patrol wagon, wagon, black Maria",
+    "735": "poncho",
+    "736": "pool table, billiard table, snooker table",
+    "737": "pop bottle, soda bottle",
+    "738": "pot, flowerpot",
+    "739": "potters wheel",
+    "740": "power drill",
+    "741": "prayer rug, prayer mat",
+    "742": "printer",
+    "743": "prison, prison house",
+    "744": "projectile, missile",
+    "745": "projector",
+    "746": "puck, hockey puck",
+    "747": "punching bag, punch bag, punching ball, punchball",
+    "748": "purse",
+    "749": "quill, quill pen",
+    "750": "quilt, comforter, comfort, puff",
+    "751": "racer, race car, racing car",
+    "752": "racket, racquet",
+    "753": "radiator",
+    "754": "radio, wireless",
+    "755": "radio telescope, radio reflector",
+    "756": "rain barrel",
+    "757": "recreational vehicle, RV, R.V.",
+    "758": "reel",
+    "759": "reflex camera",
+    "760": "refrigerator, icebox",
+    "761": "remote control, remote",
+    "762": "restaurant, eating house, eating place, eatery",
+    "763": "revolver, six-gun, six-shooter",
+    "764": "rifle",
+    "765": "rocking chair, rocker",
+    "766": "rotisserie",
+    "767": "rubber eraser, rubber, pencil eraser",
+    "768": "rugby ball",
+    "769": "rule, ruler",
+    "770": "running shoe",
+    "771": "safe",
+    "772": "safety pin",
+    "773": "saltshaker, salt shaker",
+    "774": "sandal",
+    "775": "sarong",
+    "776": "sax, saxophone",
+    "777": "scabbard",
+    "778": "scale, weighing machine",
+    "779": "school bus",
+    "780": "schooner",
+    "781": "scoreboard",
+    "782": "screen, CRT screen",
+    "783": "screw",
+    "784": "screwdriver",
+    "785": "seat belt, seatbelt",
+    "786": "sewing machine",
+    "787": "shield, buckler",
+    "788": "shoe shop, shoe-shop, shoe store",
+    "789": "shoji",
+    "790": "shopping basket",
+    "791": "shopping cart",
+    "792": "shovel",
+    "793": "shower cap",
+    "794": "shower curtain",
+    "795": "ski",
+    "796": "ski mask",
+    "797": "sleeping bag",
+    "798": "slide rule, slipstick",
+    "799": "sliding door",
+    "800": "slot, one-armed bandit",
+    "801": "snorkel",
+    "802": "snowmobile",
+    "803": "snowplow, snowplough",
+    "804": "soap dispenser",
+    "805": "soccer ball",
+    "806": "sock",
+    "807": "solar dish, solar collector, solar furnace",
+    "808": "sombrero",
+    "809": "soup bowl",
+    "810": "space bar",
+    "811": "space heater",
+    "812": "space shuttle",
+    "813": "spatula",
+    "814": "speedboat",
+    "815": "spider web, spiders web",
+    "816": "spindle",
+    "817": "sports car, sport car",
+    "818": "spotlight, spot",
+    "819": "stage",
+    "820": "steam locomotive",
+    "821": "steel arch bridge",
+    "822": "steel drum",
+    "823": "stethoscope",
+    "824": "stole",
+    "825": "stone wall",
+    "826": "stopwatch, stop watch",
+    "827": "stove",
+    "828": "strainer",
+    "829": "streetcar, tram, tramcar, trolley, trolley car",
+    "830": "stretcher",
+    "831": "studio couch, day bed",
+    "832": "stupa, tope",
+    "833": "submarine, pigboat, sub, U-boat",
+    "834": "suit, suit of clothes",
+    "835": "sundial",
+    "836": "sunglass",
+    "837": "sunglasses, dark glasses, shades",
+    "838": "sunscreen, sunblock, sun blocker",
+    "839": "suspension bridge",
+    "840": "swab, swob, mop",
+    "841": "sweatshirt",
+    "842": "swimming trunks, bathing trunks",
+    "843": "swing",
+    "844": "switch, electric switch, electrical switch",
+    "845": "syringe",
+    "846": "table lamp",
+    "847": "tank, army tank, armored combat vehicle, armoured combat vehicle",
+    "848": "tape player",
+    "849": "teapot",
+    "850": "teddy, teddy bear",
+    "851": "television, television system",
+    "852": "tennis ball",
+    "853": "thatch, thatched roof",
+    "854": "theater curtain, theatre curtain",
+    "855": "thimble",
+    "856": "thresher, thrasher, threshing machine",
+    "857": "throne",
+    "858": "tile roof",
+    "859": "toaster",
+    "860": "tobacco shop, tobacconist shop, tobacconist",
+    "861": "toilet seat",
+    "862": "torch",
+    "863": "totem pole",
+    "864": "tow truck, tow car, wrecker",
+    "865": "toyshop",
+    "866": "tractor",
+    "867": "trailer truck, tractor trailer, trucking rig, rig, articulated lorry, semi",
+    "868": "tray",
+    "869": "trench coat",
+    "870": "tricycle, trike, velocipede",
+    "871": "trimaran",
+    "872": "tripod",
+    "873": "triumphal arch",
+    "874": "trolleybus, trolley coach, trackless trolley",
+    "875": "trombone",
+    "876": "tub, vat",
+    "877": "turnstile",
+    "878": "typewriter keyboard",
+    "879": "umbrella",
+    "880": "unicycle, monocycle",
+    "881": "upright, upright piano",
+    "882": "vacuum, vacuum cleaner",
+    "883": "vase",
+    "884": "vault",
+    "885": "velvet",
+    "886": "vending machine",
+    "887": "vestment",
+    "888": "viaduct",
+    "889": "violin, fiddle",
+    "890": "volleyball",
+    "891": "waffle iron",
+    "892": "wall clock",
+    "893": "wallet, billfold, notecase, pocketbook",
+    "894": "wardrobe, closet, press",
+    "895": "warplane, military plane",
+    "896": "washbasin, handbasin, washbowl, lavabo, wash-hand basin",
+    "897": "washer, automatic washer, washing machine",
+    "898": "water bottle",
+    "899": "water jug",
+    "900": "water tower",
+    "901": "whiskey jug",
+    "902": "whistle",
+    "903": "wig",
+    "904": "window screen",
+    "905": "window shade",
+    "906": "Windsor tie",
+    "907": "wine bottle",
+    "908": "wing",
+    "909": "wok",
+    "910": "wooden spoon",
+    "911": "wool, woolen, woollen",
+    "912": "worm fence, snake fence, snake-rail fence, Virginia fence",
+    "913": "wreck",
+    "914": "yawl",
+    "915": "yurt",
+    "916": "web site, website, internet site, site",
+    "917": "comic book",
+    "918": "crossword puzzle, crossword",
+    "919": "street sign",
+    "920": "traffic light, traffic signal, stoplight",
+    "921": "book jacket, dust cover, dust jacket, dust wrapper",
+    "922": "menu",
+    "923": "plate",
+    "924": "guacamole",
+    "925": "consomme",
+    "926": "hot pot, hotpot",
+    "927": "trifle",
+    "928": "ice cream, icecream",
+    "929": "ice lolly, lolly, lollipop, popsicle",
+    "930": "French loaf",
+    "931": "bagel, beigel",
+    "932": "pretzel",
+    "933": "cheeseburger",
+    "934": "hotdog, hot dog, red hot",
+    "935": "mashed potato",
+    "936": "head cabbage",
+    "937": "broccoli",
+    "938": "cauliflower",
+    "939": "zucchini, courgette",
+    "940": "spaghetti squash",
+    "941": "acorn squash",
+    "942": "butternut squash",
+    "943": "cucumber, cuke",
+    "944": "artichoke, globe artichoke",
+    "945": "bell pepper",
+    "946": "cardoon",
+    "947": "mushroom",
+    "948": "Granny Smith",
+    "949": "strawberry",
+    "950": "orange",
+    "951": "lemon",
+    "952": "fig",
+    "953": "pineapple, ananas",
+    "954": "banana",
+    "955": "jackfruit, jak, jack",
+    "956": "custard apple",
+    "957": "pomegranate",
+    "958": "hay",
+    "959": "carbonara",
+    "960": "chocolate sauce, chocolate syrup",
+    "961": "dough",
+    "962": "meat loaf, meatloaf",
+    "963": "pizza, pizza pie",
+    "964": "potpie",
+    "965": "burrito",
+    "966": "red wine",
+    "967": "espresso",
+    "968": "cup",
+    "969": "eggnog",
+    "970": "alp",
+    "971": "bubble",
+    "972": "cliff, drop, drop-off",
+    "973": "coral reef",
+    "974": "geyser",
+    "975": "lakeside, lakeshore",
+    "976": "promontory, headland, head, foreland",
+    "977": "sandbar, sand bar",
+    "978": "seashore, coast, seacoast, sea-coast",
+    "979": "valley, vale",
+    "980": "volcano",
+    "981": "ballplayer, baseball player",
+    "982": "groom, bridegroom",
+    "983": "scuba diver",
+    "984": "rapeseed",
+    "985": "daisy",
+    "986": "yellow ladys slipper, yellow lady-slipper, Cypripedium calceolus, Cypripedium parviflorum",
+    "987": "corn",
+    "988": "acorn",
+    "989": "hip, rose hip, rosehip",
+    "990": "buckeye, horse chestnut, conker",
+    "991": "coral fungus",
+    "992": "agaric",
+    "993": "gyromitra",
+    "994": "stinkhorn, carrion fungus",
+    "995": "earthstar",
+    "996": "hen-of-the-woods, hen of the woods, Polyporus frondosus, Grifola frondosa",
+    "997": "bolete",
+    "998": "ear, spike, capitulum",
+    "999": "toilet tissue, toilet paper, bathroom tissue"
+  }
+}

DiCo-XL-256/pipeline.py

@@ -0,0 +1,398 @@
+"""Hub custom pipeline: DiCoPipeline.
+Load with native Hugging Face diffusers and trust_remote_code=True.
+"""
+
+# Copyright 2026 The HuggingFace Team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from __future__ import annotations
+
+import inspect
+import json
+from pathlib import Path
+from typing import Dict, List, Optional, Tuple, Union
+
+import torch
+from diffusers.image_processor import VaeImageProcessor
+from diffusers.models import AutoencoderKL
+from diffusers.pipelines.pipeline_utils import DiffusionPipeline, ImagePipelineOutput
+from diffusers.schedulers import DDIMScheduler, KarrasDiffusionSchedulers
+from diffusers.utils.torch_utils import randn_tensor
+
+
+EXAMPLE_DOC_STRING = """
+    Examples:
+        ```py
+        >>> from pathlib import Path
+        >>> from diffusers import DiffusionPipeline
+        >>> import torch
+
+        >>> model_dir = Path("./DiCo-XL-256").resolve()
+        >>> pipe = DiffusionPipeline.from_pretrained(
+        ...     str(model_dir),
+        ...     local_files_only=True,
+        ...     custom_pipeline=str(model_dir / "pipeline.py"),
+        ...     trust_remote_code=True,
+        ...     torch_dtype=torch.bfloat16,
+        ... )
+        >>> pipe.to("cuda")
+
+        >>> image = pipe(
+        ...     class_labels="golden retriever",
+        ...     num_inference_steps=250,
+        ...     guidance_scale=1.4,
+        ...     generator=torch.Generator("cuda").manual_seed(0),
+        ... ).images[0]
+        ```
+"""
+
+
+class DiCoPipeline(DiffusionPipeline):
+    r"""
+    Pipeline for class-conditional image generation with DiCo (Diffusion ConvNet).
+
+    Parameters:
+        transformer ([`DiCoTransformer2DModel`]):
+            Class-conditional DiCo denoiser operating in VAE latent space.
+        vae ([`AutoencoderKL`]):
+            Variational autoencoder used to decode latents to pixels.
+        scheduler ([`DDIMScheduler`]):
+            Diffusion scheduler. Other [`KarrasDiffusionSchedulers`] can be swapped at inference time.
+        id2label (`dict[int, str]`, *optional*):
+            ImageNet class id to English label mapping. Values may contain comma-separated synonyms.
+    """
+
+    model_cpu_offload_seq = "transformer->vae"
+
+    @staticmethod
+    def prepare_extra_step_kwargs(
+        scheduler: KarrasDiffusionSchedulers,
+        generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
+        eta: float = 0.0,
+    ) -> Dict[str, object]:
+        kwargs: Dict[str, object] = {}
+        step_params = set(inspect.signature(scheduler.step).parameters.keys())
+        if "generator" in step_params:
+            kwargs["generator"] = generator
+        if "eta" in step_params:
+            kwargs["eta"] = eta
+        return kwargs
+
+    def __init__(
+        self,
+        transformer,
+        vae: AutoencoderKL,
+        scheduler: KarrasDiffusionSchedulers,
+        id2label: Optional[Dict[Union[int, str], str]] = None,
+    ):
+        super().__init__()
+        if scheduler is None:
+            scheduler = DDIMScheduler(
+                num_train_timesteps=1000,
+                beta_start=0.0001,
+                beta_end=0.02,
+                beta_schedule="linear",
+                clip_sample=False,
+                set_alpha_to_one=True,
+                steps_offset=0,
+                prediction_type="epsilon",
+            )
+        self.register_modules(transformer=transformer, vae=vae, scheduler=scheduler)
+        self.vae_scale_factor = 2 ** (len(self.vae.config.block_out_channels) - 1)
+        self.image_processor = VaeImageProcessor(vae_scale_factor=self.vae_scale_factor)
+        self._id2label = self._normalize_id2label(id2label)
+        self.labels = self._build_label2id(self._id2label)
+        self._labels_loaded_from_model_index = bool(self._id2label)
+
+    @classmethod
+    def from_pretrained(cls, pretrained_model_name_or_path: str, **kwargs):
+        model_kwargs = dict(kwargs)
+        transformer_subfolder = model_kwargs.pop("transformer_subfolder", None)
+        scheduler_subfolder = model_kwargs.pop("scheduler_subfolder", None)
+        vae_subfolder = model_kwargs.pop("vae_subfolder", None)
+        scheduler_kwargs = model_kwargs.pop("scheduler_kwargs", {})
+        base_path = Path(pretrained_model_name_or_path)
+
+        if transformer_subfolder is None and (base_path / "transformer").exists():
+            transformer_subfolder = "transformer"
+        if scheduler_subfolder is None and (base_path / "scheduler").exists():
+            scheduler_subfolder = "scheduler"
+        if vae_subfolder is None and (base_path / "vae").exists():
+            vae_subfolder = "vae"
+
+        try:
+            return super().from_pretrained(pretrained_model_name_or_path, **kwargs)
+        except Exception:
+            transformer_path = str(base_path / transformer_subfolder) if transformer_subfolder else pretrained_model_name_or_path
+            from transformer.transformer_dico import DiCoTransformer2DModel
+            transformer = DiCoTransformer2DModel.from_pretrained(transformer_path, **model_kwargs)
+            try:
+                scheduler = DDIMScheduler.from_pretrained(
+                    pretrained_model_name_or_path,
+                    subfolder=scheduler_subfolder,
+                    **scheduler_kwargs,
+                )
+            except Exception:
+                scheduler = DDIMScheduler(
+                    num_train_timesteps=1000,
+                    beta_start=0.0001,
+                    beta_end=0.02,
+                    beta_schedule="linear",
+                    clip_sample=False,
+                    set_alpha_to_one=True,
+                    steps_offset=0,
+                    prediction_type="epsilon",
+                    **scheduler_kwargs,
+                )
+            try:
+                vae = AutoencoderKL.from_pretrained(
+                    pretrained_model_name_or_path,
+                    subfolder=vae_subfolder,
+                    **model_kwargs,
+                )
+            except Exception:
+                vae = AutoencoderKL.from_pretrained("stabilityai/sd-vae-ft-ema", **model_kwargs)
+            id2label = cls._read_id2label_from_model_index(str(base_path))
+            return cls(transformer=transformer, vae=vae, scheduler=scheduler, id2label=id2label)
+
+    def _ensure_labels_loaded(self) -> None:
+        if self._labels_loaded_from_model_index:
+            return
+        loaded = self._read_id2label_from_model_index(getattr(self.config, "_name_or_path", None))
+        if loaded:
+            self._id2label = loaded
+            self.labels = self._build_label2id(self._id2label)
+        self._labels_loaded_from_model_index = True
+
+    @staticmethod
+    def _normalize_id2label(id2label: Optional[Dict[Union[int, str], str]]) -> Dict[int, str]:
+        if not id2label:
+            return {}
+        return {int(key): value for key, value in id2label.items()}
+
+    @staticmethod
+    def _read_id2label_from_model_index(variant_path: Optional[str]) -> Dict[int, str]:
+        if not variant_path:
+            return {}
+        model_index_path = Path(variant_path).resolve() / "model_index.json"
+        if not model_index_path.exists():
+            return {}
+        raw = json.loads(model_index_path.read_text(encoding="utf-8"))
+        id2label = raw.get("id2label")
+        if not isinstance(id2label, dict):
+            return {}
+        return {int(key): value for key, value in id2label.items()}
+
+    @staticmethod
+    def _build_label2id(id2label: Dict[int, str]) -> Dict[str, int]:
+        label2id: Dict[str, int] = {}
+        for class_id, value in id2label.items():
+            for synonym in value.split(","):
+                synonym = synonym.strip()
+                if synonym:
+                    label2id[synonym] = int(class_id)
+        return dict(sorted(label2id.items()))
+
+    @property
+    def id2label(self) -> Dict[int, str]:
+        self._ensure_labels_loaded()
+        return self._id2label
+
+    def get_label_ids(self, label: Union[str, List[str]]) -> List[int]:
+        self._ensure_labels_loaded()
+        if not self.labels:
+            raise ValueError("No English labels loaded. Ensure `id2label` exists in model_index.json.")
+        if isinstance(label, str):
+            label = [label]
+        missing = [item for item in label if item not in self.labels]
+        if missing:
+            preview = ", ".join(list(self.labels.keys())[:8])
+            raise ValueError(f"Unknown English label(s): {missing}. Example valid labels: {preview}, ...")
+        return [self.labels[item] for item in label]
+
+    def _normalize_class_labels(
+        self,
+        class_labels: Union[int, str, List[Union[int, str]], torch.LongTensor],
+    ) -> torch.LongTensor:
+        if torch.is_tensor(class_labels):
+            return class_labels.to(device=self._execution_device, dtype=torch.long).reshape(-1)
+        if isinstance(class_labels, int):
+            class_label_ids = [class_labels]
+        elif isinstance(class_labels, str):
+            class_label_ids = self.get_label_ids(class_labels)
+        elif class_labels and isinstance(class_labels[0], str):
+            class_label_ids = self.get_label_ids(class_labels)
+        else:
+            class_label_ids = list(class_labels)
+        return torch.tensor(class_label_ids, device=self._execution_device, dtype=torch.long).reshape(-1)
+
+    def _default_image_size(self) -> int:
+        return int(self.transformer.config.input_size) * self.vae_scale_factor
+
+    def check_inputs(
+        self,
+        height: int,
+        width: int,
+        num_inference_steps: int,
+        output_type: str,
+    ) -> None:
+        if num_inference_steps < 1:
+            raise ValueError("num_inference_steps must be >= 1.")
+        if output_type not in {"pil", "np", "pt", "latent"}:
+            raise ValueError("output_type must be one of: 'pil', 'np', 'pt', 'latent'.")
+        if height % self.vae_scale_factor != 0 or width % self.vae_scale_factor != 0:
+            raise ValueError(
+                f"height and width must be divisible by the VAE downsample factor {self.vae_scale_factor}."
+            )
+        latent_height = height // self.vae_scale_factor
+        latent_width = width // self.vae_scale_factor
+        expected_size = int(self.transformer.config.input_size)
+        if latent_height != expected_size or latent_width != expected_size:
+            raise ValueError(
+                f"Requested latent size {(latent_height, latent_width)} does not match the pretrained "
+                f"transformer input_size={expected_size}. Use height=width={self._default_image_size()}."
+            )
+
+    def prepare_latents(
+        self,
+        batch_size: int,
+        height: int,
+        width: int,
+        dtype: torch.dtype,
+        device: torch.device,
+        generator: Optional[Union[torch.Generator, List[torch.Generator]]],
+    ) -> torch.Tensor:
+        latent_height = height // self.vae_scale_factor
+        latent_width = width // self.vae_scale_factor
+        return randn_tensor(
+            (batch_size, self.transformer.config.in_channels, latent_height, latent_width),
+            generator=generator,
+            device=device,
+            dtype=dtype,
+        )
+
+    @staticmethod
+    def _expand_timestep(timestep, batch: int, device: torch.device) -> torch.Tensor:
+        if not torch.is_tensor(timestep):
+            timestep = torch.tensor([timestep], dtype=torch.long, device=device)
+        elif timestep.ndim == 0:
+            timestep = timestep[None].to(device=device)
+        return timestep.expand(batch)
+
+    @staticmethod
+    def _prepare_model_output_for_scheduler(
+        model_output: torch.Tensor,
+        latent_channels: int,
+        scheduler: KarrasDiffusionSchedulers,
+    ) -> torch.Tensor:
+        if model_output.shape[1] != 2 * latent_channels:
+            return model_output
+        variance_type = getattr(scheduler.config, "variance_type", None)
+        if scheduler.__class__.__name__ == "DDPMScheduler" and variance_type in ("learned", "learned_range"):
+            return model_output
+        model_output, _ = torch.split(model_output, latent_channels, dim=1)
+        return model_output
+
+    def decode_latents(self, latents: torch.Tensor, output_type: str = "pil"):
+        if output_type == "latent":
+            return latents
+        scaling_factor = getattr(self.vae.config, "scaling_factor", 0.18215)
+        image = self.vae.decode(latents / scaling_factor).sample
+        if output_type == "pt":
+            return image
+        return self.image_processor.postprocess(image, output_type=output_type)
+
+    @torch.inference_mode()
+    def __call__(
+        self,
+        class_labels: Union[int, str, List[Union[int, str]], torch.LongTensor],
+        height: Optional[int] = None,
+        width: Optional[int] = None,
+        num_inference_steps: int = 250,
+        guidance_scale: float = 1.0,
+        eta: float = 0.0,
+        generator: Optional[Union[torch.Generator, List[torch.Generator]]] = None,
+        output_type: str = "pil",
+        return_dict: bool = True,
+    ) -> Union[ImagePipelineOutput, Tuple]:
+        default_size = self._default_image_size()
+        height = int(height or default_size)
+        width = int(width or default_size)
+        self.check_inputs(height, width, num_inference_steps, output_type)
+
+        device = self._execution_device
+        model_dtype = next(self.transformer.parameters()).dtype
+        class_labels_tensor = self._normalize_class_labels(class_labels)
+        batch_size = class_labels_tensor.numel()
+        latent_channels = int(self.transformer.config.in_channels)
+        null_class_val = int(self.transformer.config.num_classes)
+        do_cfg = guidance_scale > 1.0
+
+        latents = self.prepare_latents(
+            batch_size=batch_size,
+            height=height,
+            width=width,
+            dtype=model_dtype,
+            device=device,
+            generator=generator,
+        )
+        latent_model_input = torch.cat([latents] * 2) if do_cfg else latents
+
+        class_labels_input = class_labels_tensor
+        if do_cfg:
+            class_null = torch.full_like(class_labels_tensor, null_class_val)
+            class_labels_input = torch.cat([class_labels_tensor, class_null], dim=0)
+
+        self.scheduler.set_timesteps(num_inference_steps, device=device)
+        extra_step_kwargs = self.prepare_extra_step_kwargs(self.scheduler, generator=generator, eta=eta)
+
+        for t in self.progress_bar(self.scheduler.timesteps):
+            if do_cfg:
+                half = latent_model_input[: len(latent_model_input) // 2]
+                latent_model_input = torch.cat([half, half], dim=0)
+            latent_model_input = self.scheduler.scale_model_input(latent_model_input, t)
+            timesteps = self._expand_timestep(t, latent_model_input.shape[0], latent_model_input.device)
+
+            noise_pred = self.transformer(
+                hidden_states=latent_model_input,
+                timestep=timesteps,
+                class_labels=class_labels_input,
+                return_dict=True,
+            ).sample
+
+            if do_cfg:
+                eps, rest = noise_pred[:, :latent_channels], noise_pred[:, latent_channels:]
+                cond_eps, uncond_eps = torch.split(eps, len(eps) // 2, dim=0)
+                half_eps = uncond_eps + guidance_scale * (cond_eps - uncond_eps)
+                eps = torch.cat([half_eps, half_eps], dim=0)
+                noise_pred = torch.cat([eps, rest], dim=1)
+
+            model_output = self._prepare_model_output_for_scheduler(noise_pred, latent_channels, self.scheduler)
+            latent_model_input = self.scheduler.step(
+                model_output, t, latent_model_input, return_dict=True, **extra_step_kwargs
+            ).prev_sample
+
+        if do_cfg:
+            latents, _ = latent_model_input.chunk(2, dim=0)
+        else:
+            latents = latent_model_input
+
+        image = self.decode_latents(latents, output_type=output_type)
+        self.maybe_free_model_hooks()
+        if not return_dict:
+            return (image,)
+        return ImagePipelineOutput(images=image)
+
+
+DiCoPipelineOutput = ImagePipelineOutput

DiCo-XL-256/scheduler/scheduler_config.json

@@ -0,0 +1,12 @@
+{
+  "_class_name": "DDIMScheduler",
+  "_diffusers_version": "0.35.1",
+  "num_train_timesteps": 1000,
+  "beta_start": 0.0001,
+  "beta_end": 0.02,
+  "beta_schedule": "linear",
+  "clip_sample": false,
+  "set_alpha_to_one": true,
+  "steps_offset": 0,
+  "prediction_type": "epsilon"
+}

DiCo-XL-256/transformer/config.json

@@ -0,0 +1,14 @@
+{
+  "_class_name": "DiCoTransformer2DModel",
+  "_diffusers_version": "0.38.0",
+  "class_dropout_prob": 0.1,
+  "depth": null,
+  "hidden_size": 416,
+  "in_channels": 4,
+  "input_size": 32,
+  "learn_sigma": true,
+  "mlp_ratio": 2.0,
+  "model_type": "DiCo-XL",
+  "num_class_embeds": null,
+  "num_classes": 1000
+}

DiCo-XL-256/transformer/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1359b801751ee014cc0ec44912f28a1d9972f359eac05c659cd449dfa9856a8
+size 2804674944

DiCo-XL-256/transformer/transformer_dico.py

@@ -0,0 +1,479 @@
+# Copyright 2026 The HuggingFace Team. All rights reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from __future__ import annotations
+
+import argparse
+import math
+from collections.abc import Mapping
+from typing import Dict, Literal, Optional, Tuple
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+from diffusers.configuration_utils import ConfigMixin, register_to_config
+from diffusers.models.modeling_outputs import Transformer2DModelOutput
+from diffusers.models.modeling_utils import ModelMixin
+
+
+DICO_PRESET_CONFIGS: Dict[str, Dict[str, object]] = {
+    "DiCo-S": {
+        "hidden_size": 128,
+        "depth": [5, 4, 4, 4, 4],
+        "mlp_ratio": 2.0,
+    },
+    "DiCo-B": {
+        "hidden_size": 256,
+        "depth": [5, 4, 4, 4, 4],
+        "mlp_ratio": 2.0,
+    },
+    "DiCo-L": {
+        "hidden_size": 352,
+        "depth": [9, 8, 9, 8, 9],
+        "mlp_ratio": 2.0,
+    },
+    "DiCo-XL": {
+        "hidden_size": 416,
+        "depth": [9, 9, 10, 9, 9],
+        "mlp_ratio": 2.0,
+    },
+    "DiCo-H": {
+        "hidden_size": 416,
+        "depth": [14, 12, 10, 12, 14],
+        "mlp_ratio": 4.0,
+    },
+}
+
+
+def remap_legacy_state_dict(state_dict: Dict[str, torch.Tensor]) -> Dict[str, torch.Tensor]:
+    """Map wrapper/backbone keys from legacy checkpoints to native model keys."""
+    remapped: Dict[str, torch.Tensor] = {}
+    for key, value in state_dict.items():
+        new_key = key
+        for prefix in ("transformer.", "model.", "net."):
+            if new_key.startswith(prefix):
+                new_key = new_key[len(prefix) :]
+                break
+        remapped[new_key] = value
+    return remapped
+
+
+def infer_learn_sigma(state_dict: Dict[str, torch.Tensor], in_channels: int = 4) -> bool:
+    weight = state_dict.get("final_layer.out_proj.weight")
+    if weight is None:
+        return True
+    return int(weight.shape[0]) == in_channels * 2
+
+
+def config_from_legacy(config: Dict[str, object]) -> Dict[str, object]:
+    """Build native config kwargs from a legacy config.json dict."""
+    model_type = config.get("model_type") or config.get("model_name") or config.get("model")
+    if model_type not in DICO_PRESET_CONFIGS:
+        raise ValueError(f"Unknown DiCo preset '{model_type}'. Known: {list(DICO_PRESET_CONFIGS)}")
+
+    preset = dict(DICO_PRESET_CONFIGS[model_type])
+    preset["num_classes"] = int(config.get("num_class_embeds") or config.get("num_classes") or 1000)
+    preset["model_type"] = model_type
+    preset["input_size"] = int(config.get("input_size") or config.get("sample_size") or 32)
+    if config.get("learn_sigma") is not None:
+        preset["learn_sigma"] = bool(config["learn_sigma"])
+    return preset
+
+
+def modulate(x: torch.Tensor, shift: torch.Tensor, scale: torch.Tensor) -> torch.Tensor:
+    return x * (1 + scale.unsqueeze(-1).unsqueeze(-1)) + shift.unsqueeze(-1).unsqueeze(-1)
+
+
+class LayerNorm2d(nn.LayerNorm):
+    def __init__(self, num_channels: int, eps: float = 1e-6, affine: bool = True):
+        super().__init__(num_channels, eps=eps, elementwise_affine=affine)
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        x = x.permute(0, 2, 3, 1)
+        x = F.layer_norm(x, self.normalized_shape, self.weight, self.bias, self.eps)
+        return x.permute(0, 3, 1, 2)
+
+
+class DiCoTimestepEmbedder(nn.Module):
+    def __init__(self, hidden_size: int, frequency_embedding_size: int = 256):
+        super().__init__()
+        self.mlp = nn.Sequential(
+            nn.Linear(frequency_embedding_size, hidden_size, bias=True),
+            nn.SiLU(),
+            nn.Linear(hidden_size, hidden_size, bias=True),
+        )
+        self.frequency_embedding_size = frequency_embedding_size
+
+    @staticmethod
+    def timestep_embedding(t: torch.Tensor, dim: int, max_period: int = 10000) -> torch.Tensor:
+        half = dim // 2
+        freqs = torch.exp(
+            -math.log(max_period) * torch.arange(start=0, end=half, dtype=torch.float32) / half
+        ).to(device=t.device)
+        args = t[:, None].float() * freqs[None]
+        embedding = torch.cat([torch.cos(args), torch.sin(args)], dim=-1)
+        if dim % 2:
+            embedding = torch.cat([embedding, torch.zeros_like(embedding[:, :1])], dim=-1)
+        return embedding
+
+    def forward(self, t: torch.Tensor) -> torch.Tensor:
+        t_freq = self.timestep_embedding(t, self.frequency_embedding_size)
+        weight_dtype = self.mlp[0].weight.dtype
+        return self.mlp(t_freq.to(dtype=weight_dtype))
+
+
+class DiCoLabelEmbedder(nn.Module):
+    def __init__(self, num_classes: int, hidden_size: int, dropout_prob: float):
+        super().__init__()
+        use_cfg_embedding = dropout_prob > 0
+        self.embedding_table = nn.Embedding(num_classes + use_cfg_embedding, hidden_size)
+        self.num_classes = num_classes
+        self.dropout_prob = dropout_prob
+
+    def token_drop(self, labels: torch.Tensor, force_drop_ids: Optional[torch.Tensor] = None) -> torch.Tensor:
+        if force_drop_ids is None:
+            drop_ids = torch.rand(labels.shape[0], device=labels.device) < self.dropout_prob
+        else:
+            drop_ids = force_drop_ids == 1
+        return torch.where(drop_ids, self.num_classes, labels)
+
+    def forward(
+        self,
+        labels: torch.Tensor,
+        train: bool,
+        force_drop_ids: Optional[torch.Tensor] = None,
+    ) -> torch.Tensor:
+        use_dropout = self.dropout_prob > 0
+        if (train and use_dropout) or (force_drop_ids is not None):
+            labels = self.token_drop(labels, force_drop_ids)
+        return self.embedding_table(labels)
+
+
+class DiCoMultiScaleLabelEmbedder(nn.Module):
+    def __init__(
+        self,
+        num_classes: int,
+        hidden_size_0: int,
+        hidden_size_1: int,
+        hidden_size_2: int,
+        dropout_prob: float,
+    ):
+        super().__init__()
+        use_cfg_embedding = dropout_prob > 0
+        self.embedding_table_0 = nn.Embedding(num_classes + use_cfg_embedding, hidden_size_0)
+        self.embedding_table_1 = nn.Embedding(num_classes + use_cfg_embedding, hidden_size_1)
+        self.embedding_table_2 = nn.Embedding(num_classes + use_cfg_embedding, hidden_size_2)
+        self.num_classes = num_classes
+        self.dropout_prob = dropout_prob
+
+    def token_drop(self, labels: torch.Tensor, force_drop_ids: Optional[torch.Tensor] = None) -> torch.Tensor:
+        if force_drop_ids is None:
+            drop_ids = torch.rand(labels.shape[0], device=labels.device) < self.dropout_prob
+        else:
+            drop_ids = force_drop_ids == 1
+        return torch.where(drop_ids, self.num_classes, labels)
+
+    def forward(
+        self,
+        labels: torch.Tensor,
+        train: bool,
+        force_drop_ids: Optional[torch.Tensor] = None,
+    ) -> Tuple[torch.Tensor, torch.Tensor, torch.Tensor]:
+        use_dropout = self.dropout_prob > 0
+        if (train and use_dropout) or (force_drop_ids is not None):
+            labels = self.token_drop(labels, force_drop_ids)
+        return (
+            self.embedding_table_0(labels),
+            self.embedding_table_1(labels),
+            self.embedding_table_2(labels),
+        )
+
+
+class DiCoBlock(nn.Module):
+    def __init__(self, hidden_size: int, mlp_ratio: float = 4.0):
+        super().__init__()
+        self.conv1 = nn.Conv2d(hidden_size, hidden_size, kernel_size=1, padding=0, stride=1, groups=1, bias=True)
+        self.conv2 = nn.Conv2d(
+            hidden_size, hidden_size, kernel_size=3, padding=1, stride=1, groups=hidden_size, bias=True
+        )
+        self.conv3 = nn.Conv2d(hidden_size, hidden_size, kernel_size=1, padding=0, stride=1, groups=1, bias=True)
+        self.ca = nn.Sequential(
+            nn.AdaptiveAvgPool2d(1),
+            nn.Conv2d(hidden_size, hidden_size, kernel_size=1, padding=0, stride=1, groups=1, bias=True),
+            nn.Sigmoid(),
+        )
+        ffn_channel = int(mlp_ratio * hidden_size)
+        self.conv4 = nn.Conv2d(hidden_size, ffn_channel, kernel_size=1, padding=0, stride=1, groups=1, bias=True)
+        self.conv5 = nn.Conv2d(ffn_channel, hidden_size, kernel_size=1, padding=0, stride=1, groups=1, bias=True)
+        self.norm1 = LayerNorm2d(hidden_size, affine=False, eps=1e-6)
+        self.norm2 = LayerNorm2d(hidden_size, affine=False, eps=1e-6)
+        self.adaLN_modulation = nn.Sequential(nn.SiLU(), nn.Linear(hidden_size, 6 * hidden_size, bias=True))
+
+    def forward(self, inp: torch.Tensor, c: torch.Tensor) -> torch.Tensor:
+        shift_msa, scale_msa, gate_msa, shift_mlp, scale_mlp, gate_mlp = self.adaLN_modulation(c).chunk(6, dim=1)
+        x = modulate(self.norm1(inp), shift_msa, scale_msa)
+        x = F.gelu(self.conv2(self.conv1(x)))
+        x = x * self.ca(x)
+        x = self.conv3(x)
+        x = inp + gate_msa.unsqueeze(-1).unsqueeze(-1) * x
+        x = x + gate_mlp.unsqueeze(-1).unsqueeze(-1) * self.conv5(
+            F.gelu(self.conv4(modulate(self.norm2(x), shift_mlp, scale_mlp)))
+        )
+        return x
+
+
+class DiCoFinalLayer(nn.Module):
+    def __init__(self, hidden_size: int, out_channels: int):
+        super().__init__()
+        self.norm_final = LayerNorm2d(hidden_size, affine=False, eps=1e-6)
+        self.out_proj = nn.Conv2d(hidden_size, out_channels, kernel_size=3, stride=1, padding=1, bias=True)
+        self.adaLN_modulation = nn.Sequential(nn.SiLU(), nn.Linear(hidden_size, 2 * hidden_size, bias=True))
+
+    def forward(self, x: torch.Tensor, c: torch.Tensor) -> torch.Tensor:
+        shift, scale = self.adaLN_modulation(c).chunk(2, dim=1)
+        x = modulate(self.norm_final(x), shift, scale)
+        return self.out_proj(x)
+
+
+class OverlapPatchEmbed(nn.Module):
+    def __init__(self, in_c: int = 3, embed_dim: int = 48, bias: bool = False):
+        super().__init__()
+        self.proj = nn.Conv2d(in_c, embed_dim, kernel_size=3, stride=1, padding=1, bias=bias)
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        return self.proj(x)
+
+
+class Downsample(nn.Module):
+    def __init__(self, n_feat: int):
+        super().__init__()
+        self.body = nn.Sequential(
+            nn.Conv2d(n_feat, n_feat // 2, kernel_size=3, stride=1, padding=1, bias=False),
+            nn.PixelUnshuffle(2),
+        )
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        return self.body(x)
+
+
+class Upsample(nn.Module):
+    def __init__(self, n_feat: int):
+        super().__init__()
+        self.body = nn.Sequential(
+            nn.Conv2d(n_feat, n_feat * 2, kernel_size=3, stride=1, padding=1, bias=False),
+            nn.PixelShuffle(2),
+        )
+
+    def forward(self, x: torch.Tensor) -> torch.Tensor:
+        return self.body(x)
+
+
+class DiCoTransformer2DModel(ModelMixin, ConfigMixin):
+    r"""
+    DiCo (Diffusion ConvNet) denoiser for class-conditional latent diffusion.
+
+    ConvNet U-Net backbone with multi-scale adaLN conditioning, operating on VAE latents.
+    """
+
+    _supports_gradient_checkpointing = True
+
+    @register_to_config
+    def __init__(
+        self,
+        input_size: int = 32,
+        in_channels: int = 4,
+        hidden_size: int = 416,
+        depth: Optional[list[int]] = None,
+        mlp_ratio: float = 2.0,
+        class_dropout_prob: float = 0.1,
+        num_classes: int = 1000,
+        learn_sigma: bool = True,
+        model_type: str | None = None,
+        num_class_embeds: int | None = None,
+    ):
+        super().__init__()
+        if num_class_embeds is not None:
+            num_classes = int(num_class_embeds)
+        if model_type in DICO_PRESET_CONFIGS:
+            preset = DICO_PRESET_CONFIGS[model_type]
+            hidden_size = int(preset["hidden_size"])
+            depth = list(preset["depth"])
+            mlp_ratio = float(preset["mlp_ratio"])
+
+        if depth is None:
+            depth = [9, 9, 10, 9, 9]
+
+        self.learn_sigma = learn_sigma
+        self.in_channels = in_channels
+        self.out_channels = in_channels * 2 if learn_sigma else in_channels
+        self.num_classes = num_classes
+        self.gradient_checkpointing = False
+
+        self.x_embedder = OverlapPatchEmbed(in_channels, hidden_size, bias=True)
+        self.t_embedder_1 = DiCoTimestepEmbedder(hidden_size)
+        self.y_embedder = DiCoMultiScaleLabelEmbedder(
+            num_classes, hidden_size, hidden_size * 2, hidden_size * 4, class_dropout_prob
+        )
+        self.t_embedder_2 = DiCoTimestepEmbedder(hidden_size * 2)
+        self.t_embedder_3 = DiCoTimestepEmbedder(hidden_size * 4)
+
+        self.encoder_level_1 = nn.ModuleList([DiCoBlock(hidden_size, mlp_ratio) for _ in range(depth[0])])
+        self.down1_2 = Downsample(hidden_size)
+        self.encoder_level_2 = nn.ModuleList([DiCoBlock(hidden_size * 2, mlp_ratio) for _ in range(depth[1])])
+        self.down2_3 = Downsample(hidden_size * 2)
+        self.latent = nn.ModuleList([DiCoBlock(hidden_size * 4, mlp_ratio) for _ in range(depth[2])])
+        self.up3_2 = Upsample(int(hidden_size * 4))
+        self.reduce_chan_level2 = nn.Conv2d(int(hidden_size * 4), int(hidden_size * 2), kernel_size=1, bias=True)
+        self.decoder_level_2 = nn.ModuleList([DiCoBlock(hidden_size * 2, mlp_ratio) for _ in range(depth[3])])
+        self.up2_1 = Upsample(int(hidden_size * 2))
+        self.reduce_chan_level1 = nn.Conv2d(int(hidden_size * 2), int(hidden_size * 2), kernel_size=1, bias=True)
+        self.decoder_level_1 = nn.ModuleList([DiCoBlock(hidden_size * 2, mlp_ratio) for _ in range(depth[4])])
+        self.final_layer = DiCoFinalLayer(hidden_size * 2, self.out_channels)
+        self.initialize_weights()
+
+    def initialize_weights(self) -> None:
+        def _basic_init(module: nn.Module):
+            if isinstance(module, (nn.Linear, nn.Conv2d)):
+                torch.nn.init.xavier_uniform_(module.weight)
+                if module.bias is not None:
+                    nn.init.constant_(module.bias, 0)
+
+        self.apply(_basic_init)
+        w = self.x_embedder.proj.weight.data
+        nn.init.xavier_uniform_(w.view([w.shape[0], -1]))
+        nn.init.constant_(self.x_embedder.proj.bias, 0)
+        nn.init.normal_(self.y_embedder.embedding_table_0.weight, std=0.02)
+        nn.init.normal_(self.y_embedder.embedding_table_1.weight, std=0.02)
+        nn.init.normal_(self.y_embedder.embedding_table_2.weight, std=0.02)
+        for embedder in (self.t_embedder_1, self.t_embedder_2, self.t_embedder_3):
+            nn.init.normal_(embedder.mlp[0].weight, std=0.02)
+            nn.init.normal_(embedder.mlp[2].weight, std=0.02)
+
+        blocks = (
+            self.encoder_level_1
+            + self.encoder_level_2
+            + self.latent
+            + self.decoder_level_2
+            + self.decoder_level_1
+        )
+        for block in blocks:
+            nn.init.constant_(block.adaLN_modulation[-1].weight, 0)
+            nn.init.constant_(block.adaLN_modulation[-1].bias, 0)
+        nn.init.constant_(self.final_layer.adaLN_modulation[-1].weight, 0)
+        nn.init.constant_(self.final_layer.adaLN_modulation[-1].bias, 0)
+        nn.init.constant_(self.final_layer.out_proj.weight, 0)
+        nn.init.constant_(self.final_layer.out_proj.bias, 0)
+
+    def _run_block(self, block: DiCoBlock, x: torch.Tensor, c: torch.Tensor) -> torch.Tensor:
+        if self.training and self.gradient_checkpointing:
+            return torch.utils.checkpoint.checkpoint(block, x, c, use_reentrant=False)
+        return block(x, c)
+
+    def forward(
+        self,
+        hidden_states: torch.Tensor,
+        timestep: torch.LongTensor,
+        class_labels: torch.LongTensor,
+        force_drop_ids: Optional[torch.Tensor] = None,
+        return_dict: bool = True,
+    ) -> Transformer2DModelOutput | Tuple:
+        timestep = torch.as_tensor(timestep, device=hidden_states.device)
+        if timestep.ndim == 0:
+            timestep = timestep.repeat(hidden_states.shape[0])
+        else:
+            timestep = timestep.reshape(-1)
+            if timestep.shape[0] == 1 and hidden_states.shape[0] > 1:
+                timestep = timestep.repeat(hidden_states.shape[0])
+
+        x = self.x_embedder(hidden_states)
+        t1 = self.t_embedder_1(timestep)
+        y1, y2, y3 = self.y_embedder(class_labels, self.training, force_drop_ids=force_drop_ids)
+        c1 = t1 + y1
+        c2 = self.t_embedder_2(timestep) + y2
+        c3 = self.t_embedder_3(timestep) + y3
+
+        out_enc_level1 = x
+        for block in self.encoder_level_1:
+            out_enc_level1 = self._run_block(block, out_enc_level1, c1)
+        out_enc_level2 = self.down1_2(out_enc_level1)
+        for block in self.encoder_level_2:
+            out_enc_level2 = self._run_block(block, out_enc_level2, c2)
+        latent = self.down2_3(out_enc_level2)
+        for block in self.latent:
+            latent = self._run_block(block, latent, c3)
+
+        inp_dec_level2 = self.reduce_chan_level2(torch.cat([self.up3_2(latent), out_enc_level2], dim=1))
+        for block in self.decoder_level_2:
+            inp_dec_level2 = self._run_block(block, inp_dec_level2, c2)
+        inp_dec_level1 = self.reduce_chan_level1(torch.cat([self.up2_1(inp_dec_level2), out_enc_level1], dim=1))
+        for block in self.decoder_level_1:
+            inp_dec_level1 = self._run_block(block, inp_dec_level1, c2)
+
+        output = self.final_layer(inp_dec_level1, c2)
+        if not return_dict:
+            return (output,)
+        return Transformer2DModelOutput(sample=output)
+
+    @classmethod
+    def from_dico_checkpoint(
+        cls,
+        checkpoint_path: str,
+        weights: Literal["model", "ema"] = "ema",
+        map_location: str = "cpu",
+        strict: bool = True,
+        model_type: str | None = None,
+    ) -> Tuple["DiCoTransformer2DModel", Dict[str, object]]:
+        checkpoint = torch.load(checkpoint_path, map_location=map_location, weights_only=False)
+        state_dict = checkpoint
+        if isinstance(checkpoint, Mapping):
+            if weights in checkpoint:
+                state_dict = checkpoint[weights]
+            elif "state_dict" in checkpoint:
+                state_dict = checkpoint["state_dict"]
+
+        state_dict = remap_legacy_state_dict(state_dict)
+
+        ckpt_args = checkpoint.get("args") if isinstance(checkpoint, Mapping) else None
+        args_dict: Dict[str, object] = {}
+        if ckpt_args is not None:
+            if isinstance(ckpt_args, argparse.Namespace):
+                args_dict = vars(ckpt_args)
+            elif isinstance(ckpt_args, Mapping):
+                args_dict = dict(ckpt_args)
+
+        resolved_model_type = model_type or args_dict.get("model") or args_dict.get("model_type")
+        image_size = int(args_dict.get("image_size") or 256)
+        num_classes = int(args_dict.get("num_classes") or 1000)
+
+        config: Dict[str, object] = {
+            "input_size": image_size // 8,
+            "num_classes": num_classes,
+            "learn_sigma": infer_learn_sigma(state_dict),
+        }
+        if resolved_model_type in DICO_PRESET_CONFIGS:
+            config["model_type"] = resolved_model_type
+
+        model = cls(**config)
+        model.load_state_dict(state_dict, strict=strict)
+        metadata = {
+            "checkpoint_path": checkpoint_path,
+            "weights": weights,
+            "model_type": resolved_model_type,
+            "source_args": ckpt_args,
+        }
+        return model, metadata
+
+
+DiCoDiffusersModel = DiCoTransformer2DModel

DiCo-XL-256/vae/config.json

@@ -0,0 +1,38 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.38.0",
+  "_name_or_path": "stabilityai/sd-vae-ft-ema",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "force_upcast": true,
+  "in_channels": 3,
+  "latent_channels": 4,
+  "latents_mean": null,
+  "latents_std": null,
+  "layers_per_block": 2,
+  "mid_block_add_attention": true,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 256,
+  "scaling_factor": 0.18215,
+  "shift_factor": null,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ],
+  "use_post_quant_conv": true,
+  "use_quant_conv": true
+}

DiCo-XL-256/vae/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:703abdcd7c389316b5128faa9b750a530ea1680b453170b27afebac5e4db30c4
+size 334643268

README.md

@@ -0,0 +1,150 @@
+---
+license: apache-2.0
+library_name: diffusers
+pipeline_tag: unconditional-image-generation
+tags:
+  - diffusers
+  - image-generation
+  - class-conditional
+  - imagenet
+  - dico
+  - latent-diffusion
+  - convnet
+widget:
+  - text: golden retriever
+    output:
+      url: DiCo-XL-256/demo.png
+inference: true
+---
+
+# BiliSakura/DiCo-diffusers
+
+Self-contained DiCo checkpoints for Hugging Face diffusers. Each variant folder ships its own `pipeline.py`, component modules, and weights.
+
+Converted from [shallowdream204/DiCo](https://huggingface.co/shallowdream204/DiCo) using [DiCo-diffusers](https://github.com/Bili-Sakura/Visual-Generative-Foundation-Model-Collection/tree/main/libs/DiCo-diffusers).
+
+## Available checkpoints
+
+| Subfolder | Pipeline | Resolution | Source checkpoint | CFG | FID | IS | Params |
+| --- | --- | ---: | --- | ---: | ---: | ---: | ---: |
+| [`DiCo-S-256/`](DiCo-S-256/) | `DiCoPipeline` | 256×256 | `DiCo-S-400K-256x256.pt` | 1.0 | 49.97 | 31.38 | 33M |
+| [`DiCo-B-256/`](DiCo-B-256/) | `DiCoPipeline` | 256×256 | `DiCo-B-400K-256x256.pt` | 1.0 | 27.20 | 56.52 | 130M |
+| [`DiCo-L-256/`](DiCo-L-256/) | `DiCoPipeline` | 256×256 | `DiCo-L-400K-256x256.pt` | 1.0 | 13.66 | 91.37 | 464M |
+| [`DiCo-XL-256/`](DiCo-XL-256/) | `DiCoPipeline` | 256×256 | `DiCo-XL-3750K-256x256.pt` | 1.4 | 2.05 | 282.17 | 701M |
+
+DiCo denoises **VAE latents** (4 channels, 32×32 for 256×256 images) with a ConvNet U-Net and multi-scale adaLN conditioning. VAE: `stabilityai/sd-vae-ft-ema`. Scheduler: `DDIMScheduler` (1000 train steps, linear betas).
+
+## Repo layout
+
+```text
+BiliSakura/DiCo-diffusers/
+├── README.md
+├── demo_inference.py
+├── DiCo-S-256/
+├── DiCo-B-256/
+├── DiCo-L-256/
+└── DiCo-XL-256/
+    ├── pipeline.py
+    ├── model_index.json
+    ├── demo.png
+    ├── scheduler/scheduler_config.json
+    ├── transformer/
+    └── vae/
+```
+
+Each variant is self-contained. The `scheduler/` folder uses built-in `DDIMScheduler` from PyPI diffusers.
+
+## ImageNet class labels
+
+`id2label` is embedded in each variant's `model_index.json` (DiT-style).
+
+- `pipe.id2label` — inspect id → English label correspondence
+- `pipe.labels` — reverse map (English synonym → id)
+- `pipe.get_label_ids("golden retriever")`
+- `pipe(class_labels="golden retriever", ...)` — string labels resolved automatically
+
+## Demo
+
+![DiCo-XL-256 demo](DiCo-XL-256/demo.png)
+
+Class 207 — golden retriever, 256×256, 250 steps, `guidance_scale=1.4`.
+
+```bash
+python demo_inference.py
+python demo_inference.py --variant s   # DiCo-S-256, CFG 1.0
+```
+
+## Load from a local clone
+
+### ImageNet 256×256 (`DiCo-XL-256`)
+
+```python
+from pathlib import Path
+import torch
+from diffusers import DiffusionPipeline
+
+model_dir = Path("./DiCo-XL-256").resolve()
+pipe = DiffusionPipeline.from_pretrained(
+    str(model_dir),
+    local_files_only=True,
+    custom_pipeline=str(model_dir / "pipeline.py"),
+    trust_remote_code=True,
+    torch_dtype=torch.bfloat16,
+)
+pipe.to("cuda")
+
+print(pipe.id2label[207])
+print(pipe.get_label_ids("golden retriever"))
+
+generator = torch.Generator(device="cuda").manual_seed(0)
+image = pipe(
+    class_labels="golden retriever",
+    height=256,
+    width=256,
+    num_inference_steps=250,
+    guidance_scale=1.4,
+    generator=generator,
+).images[0]
+image.save("demo.png")
+```
+
+## Recommended inference settings
+
+| Variant | Steps | CFG scale |
+| --- | ---: | ---: |
+| `DiCo-S-256` | 250 | 1.0 |
+| `DiCo-B-256` | 250 | 1.0 |
+| `DiCo-L-256` | 250 | 1.0 |
+| `DiCo-XL-256` | 250 | 1.4 |
+
+Classifier-free guidance applies to the first 3 latent channels only (DiT reproducibility convention).
+
+## Conversion
+
+```bash
+cd libs/DiCo-diffusers
+
+python scripts/convert_dico_to_diffusers.py \
+  --checkpoint /path/to/DiCo-XL-3750K-256x256.pt \
+  --output /path/to/DiCo-XL-256 \
+  --model-type DiCo-XL \
+  --weights ema \
+  --safe-serialization \
+  --id2label ../../src/labels/id2label_en.json
+```
+
+## Citation
+
+```bibtex
+@inproceedings{ai2025dico,
+    title={DiCo: Revitalizing ConvNets for Scalable and Efficient Diffusion Modeling},
+    author={Yuang Ai and Qihang Fan and Xuefeng Hu and Zhenheng Yang and Ran He and Huaibo Huang},
+    booktitle={The Thirty-ninth Annual Conference on Neural Information Processing Systems},
+    year={2025},
+    url={https://openreview.net/forum?id=UnslcaZSnb}
+}
+```
+
+## License
+
+Weights are converted from checkpoints released under the [Apache 2.0 license](https://huggingface.co/shallowdream204/DiCo).

demo_inference.py

@@ -0,0 +1,88 @@
+#!/usr/bin/env python3
+"""Generate a demo image with DiCo class-conditional checkpoints."""
+
+from __future__ import annotations
+
+import argparse
+from pathlib import Path
+
+import torch
+from diffusers import DiffusionPipeline
+
+REPO_ROOT = Path(__file__).resolve().parent
+
+VARIANTS = {
+    "xl": {
+        "dir": REPO_ROOT / "DiCo-XL-256",
+        "class_label": "golden retriever",
+        "num_inference_steps": 250,
+        "guidance_scale": 1.4,
+        "seed": 0,
+    },
+    "s": {
+        "dir": REPO_ROOT / "DiCo-S-256",
+        "class_label": "golden retriever",
+        "num_inference_steps": 250,
+        "guidance_scale": 1.0,
+        "seed": 0,
+    },
+    "b": {
+        "dir": REPO_ROOT / "DiCo-B-256",
+        "class_label": "golden retriever",
+        "num_inference_steps": 250,
+        "guidance_scale": 1.0,
+        "seed": 0,
+    },
+    "l": {
+        "dir": REPO_ROOT / "DiCo-L-256",
+        "class_label": "golden retriever",
+        "num_inference_steps": 250,
+        "guidance_scale": 1.0,
+        "seed": 0,
+    },
+}
+
+
+def parse_args() -> argparse.Namespace:
+    parser = argparse.ArgumentParser(description="Run DiCo demo inference.")
+    parser.add_argument(
+        "--variant",
+        choices=sorted(VARIANTS),
+        default="xl",
+        help="Checkpoint variant to sample (default: xl).",
+    )
+    return parser.parse_args()
+
+
+def main() -> None:
+    args = parse_args()
+    settings = VARIANTS[args.variant]
+    model_dir = settings["dir"]
+    output_path = model_dir / "demo.png"
+
+    pipe = DiffusionPipeline.from_pretrained(
+        str(model_dir),
+        local_files_only=True,
+        custom_pipeline=str(model_dir / "pipeline.py"),
+        trust_remote_code=True,
+        torch_dtype=torch.bfloat16,
+    )
+    pipe.to("cuda")
+
+    print(f"[{args.variant}] {settings['class_label']} -> {pipe.get_label_ids(settings['class_label'])}")
+
+    generator = torch.Generator(device="cuda").manual_seed(settings["seed"])
+    image = pipe(
+        class_labels=settings["class_label"],
+        height=256,
+        width=256,
+        num_inference_steps=settings["num_inference_steps"],
+        guidance_scale=settings["guidance_scale"],
+        generator=generator,
+    ).images[0]
+    image.save(output_path)
+    print(f"Saved demo image to {output_path}")
+
+
+if __name__ == "__main__":
+    main()