Duplicate from PixArt-alpha/PixArt-alpha

Co-authored-by: Chen <Lawrence-cj@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

ControlNetHED.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ca93762ffd68a29fee1af9d495bf6aab80ae86f08905fb35472a083a4c7a8fa
+size 29444406

PixArt-XL-2-1024-MS.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecb2827e2a7d3c266ba035d9c0360994d02cc474106428a6be7b055c9f99890f
+size 2466406406

PixArt-XL-2-256x256-MSCOCO-FID732.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee13db351738eed9948a56496cbf40f97a83ef2c89797f1a4d00d60946acf6aa
+size 9780801823

PixArt-XL-2-256x256.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9b64edfa871e0cb9163254779a567a1ac8b7ab89548817d071716f012b0a043
+size 2446736089

PixArt-XL-2-512x512.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1e101f812e1e4d7d4ebe69a897945f7317e3f9073b9a311b48b4fa3af5757c8
+size 2450274612

PixArt-XL-2-SAM-256x256.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17c85de0aa5eb536ceed0798ab3d722d2716312017e2c36b27d3ac37e0cf28fa
+size 2446733391

PixArt-image-to-image-workflow.json

@@ -0,0 +1,717 @@
+{
+  "last_node_id": 36,
+  "last_link_id": 49,
+  "nodes": [
+    {
+      "id": 8,
+      "type": "VAEDecode",
+      "pos": [
+        1237,
+        153
+      ],
+      "size": {
+        "0": 210,
+        "1": 46
+      },
+      "flags": {},
+      "order": 13,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "link": 7
+        },
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": 26
+        }
+      ],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            9
+          ],
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "VAEDecode"
+      }
+    },
+    {
+      "id": 26,
+      "type": "Reroute",
+      "pos": [
+        671,
+        769
+      ],
+      "size": [
+        75,
+        26
+      ],
+      "flags": {},
+      "order": 8,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "",
+          "type": "*",
+          "link": 33,
+          "slot_index": 0
+        }
+      ],
+      "outputs": [
+        {
+          "name": "",
+          "type": "VAE",
+          "links": [
+            32
+          ]
+        }
+      ],
+      "properties": {
+        "showOutputText": false,
+        "horizontal": false
+      }
+    },
+    {
+      "id": 25,
+      "type": "Reroute",
+      "pos": [
+        1249,
+        774
+      ],
+      "size": [
+        75,
+        26
+      ],
+      "flags": {},
+      "order": 6,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "",
+          "type": "*",
+          "link": 34,
+          "slot_index": 0
+        }
+      ],
+      "outputs": [
+        {
+          "name": "",
+          "type": "VAE",
+          "links": [
+            33
+          ],
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "showOutputText": false,
+        "horizontal": false
+      }
+    },
+    {
+      "id": 11,
+      "type": "T5v11Loader",
+      "pos": [
+        33,
+        280
+      ],
+      "size": {
+        "0": 315,
+        "1": 154
+      },
+      "flags": {},
+      "order": 0,
+      "mode": 0,
+      "outputs": [
+        {
+          "name": "T5",
+          "type": "T5",
+          "links": [
+            10,
+            36
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "T5v11Loader"
+      },
+      "widgets_values": [
+        "pytorch_model-00001-of-00002.bin",
+        "xxl",
+        "folder",
+        "cpu",
+        "default"
+      ]
+    },
+    {
+      "id": 19,
+      "type": "VAELoader",
+      "pos": [
+        881,
+        579
+      ],
+      "size": {
+        "0": 315,
+        "1": 58
+      },
+      "flags": {
+        "collapsed": false
+      },
+      "order": 1,
+      "mode": 0,
+      "outputs": [
+        {
+          "name": "VAE",
+          "type": "VAE",
+          "links": [
+            26,
+            34
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "VAELoader"
+      },
+      "widgets_values": [
+        "diffusion_pytorch_model.bin"
+      ]
+    },
+    {
+      "id": 18,
+      "type": "VAEEncode",
+      "pos": [
+        632,
+        618
+      ],
+      "size": {
+        "0": 210,
+        "1": 46
+      },
+      "flags": {},
+      "order": 11,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "pixels",
+          "type": "IMAGE",
+          "link": 40
+        },
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": 32,
+          "slot_index": 1
+        }
+      ],
+      "outputs": [
+        {
+          "name": "LATENT",
+          "type": "LATENT",
+          "links": [
+            24
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "VAEEncode"
+      }
+    },
+    {
+      "id": 30,
+      "type": "ImageCrop",
+      "pos": [
+        287,
+        619
+      ],
+      "size": {
+        "0": 315,
+        "1": 130
+      },
+      "flags": {},
+      "order": 9,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "link": 45
+        }
+      ],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            40
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "ImageCrop"
+      },
+      "widgets_values": [
+        1024,
+        1024,
+        0,
+        0
+      ]
+    },
+    {
+      "id": 33,
+      "type": "ImageScale",
+      "pos": [
+        296,
+        801
+      ],
+      "size": {
+        "0": 315,
+        "1": 130
+      },
+      "flags": {},
+      "order": 7,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "link": 44
+        }
+      ],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            45,
+            49
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "ImageScale"
+      },
+      "widgets_values": [
+        "nearest-exact",
+        1024,
+        1024,
+        "center"
+      ]
+    },
+    {
+      "id": 34,
+      "type": "SaveImage",
+      "pos": [
+        670,
+        897
+      ],
+      "size": {
+        "0": 353.9128723144531,
+        "1": 285.49249267578125
+      },
+      "flags": {},
+      "order": 10,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "link": 49
+        }
+      ],
+      "properties": {},
+      "widgets_values": [
+        "ComfyUI"
+      ]
+    },
+    {
+      "id": 29,
+      "type": "T5TextEncode",
+      "pos": [
+        408,
+        436
+      ],
+      "size": {
+        "0": 353.7359924316406,
+        "1": 122.41075897216797
+      },
+      "flags": {},
+      "order": 5,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "T5",
+          "type": "T5",
+          "link": 36
+        }
+      ],
+      "outputs": [
+        {
+          "name": "CONDITIONING",
+          "type": "CONDITIONING",
+          "links": [
+            37
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "T5TextEncode"
+      },
+      "widgets_values": [
+        "photo, depth of field"
+      ]
+    },
+    {
+      "id": 24,
+      "type": "PixArtCheckpointLoader",
+      "pos": [
+        184,
+        105
+      ],
+      "size": {
+        "0": 315,
+        "1": 82
+      },
+      "flags": {},
+      "order": 2,
+      "mode": 0,
+      "outputs": [
+        {
+          "name": "model",
+          "type": "MODEL",
+          "links": [
+            25
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "PixArtCheckpointLoader"
+      },
+      "widgets_values": [
+        "PixArt-XL-2-1024-MS.pth",
+        "PixArtMS_XL_2"
+      ]
+    },
+    {
+      "id": 9,
+      "type": "SaveImage",
+      "pos": [
+        1244,
+        251
+      ],
+      "size": {
+        "0": 353.9128723144531,
+        "1": 285.49249267578125
+      },
+      "flags": {},
+      "order": 14,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "link": 9
+        }
+      ],
+      "properties": {},
+      "widgets_values": [
+        "ComfyUI"
+      ]
+    },
+    {
+      "id": 10,
+      "type": "T5TextEncode",
+      "pos": [
+        409,
+        270
+      ],
+      "size": {
+        "0": 353.7359924316406,
+        "1": 122.41075897216797
+      },
+      "flags": {},
+      "order": 4,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "T5",
+          "type": "T5",
+          "link": 10
+        }
+      ],
+      "outputs": [
+        {
+          "name": "CONDITIONING",
+          "type": "CONDITIONING",
+          "links": [
+            14
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "T5TextEncode"
+      },
+      "widgets_values": [
+        "pixel art style of a man"
+      ]
+    },
+    {
+      "id": 3,
+      "type": "KSampler",
+      "pos": [
+        866,
+        151
+      ],
+      "size": {
+        "0": 315,
+        "1": 262
+      },
+      "flags": {},
+      "order": 12,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "model",
+          "type": "MODEL",
+          "link": 25
+        },
+        {
+          "name": "positive",
+          "type": "CONDITIONING",
+          "link": 14
+        },
+        {
+          "name": "negative",
+          "type": "CONDITIONING",
+          "link": 37
+        },
+        {
+          "name": "latent_image",
+          "type": "LATENT",
+          "link": 24
+        }
+      ],
+      "outputs": [
+        {
+          "name": "LATENT",
+          "type": "LATENT",
+          "links": [
+            7
+          ],
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "KSampler"
+      },
+      "widgets_values": [
+        160,
+        "fixed",
+        20,
+        4.5,
+        "dpmpp_2m",
+        "normal",
+        0.7000000000000001
+      ],
+      "color": "#322",
+      "bgcolor": "#533",
+      "shape": 1
+    },
+    {
+      "id": 28,
+      "type": "LoadImage",
+      "pos": [
+        -62,
+        620
+      ],
+      "size": {
+        "0": 315,
+        "1": 314
+      },
+      "flags": {},
+      "order": 3,
+      "mode": 0,
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            44
+          ],
+          "shape": 3,
+          "slot_index": 0
+        },
+        {
+          "name": "MASK",
+          "type": "MASK",
+          "links": null,
+          "shape": 3,
+          "slot_index": 1
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "LoadImage"
+      },
+      "widgets_values": [
+        "example.png",
+        "image"
+      ]
+    }
+  ],
+  "links": [
+    [
+      7,
+      3,
+      0,
+      8,
+      0,
+      "LATENT"
+    ],
+    [
+      9,
+      8,
+      0,
+      9,
+      0,
+      "IMAGE"
+    ],
+    [
+      10,
+      11,
+      0,
+      10,
+      0,
+      "T5"
+    ],
+    [
+      14,
+      10,
+      0,
+      3,
+      1,
+      "CONDITIONING"
+    ],
+    [
+      24,
+      18,
+      0,
+      3,
+      3,
+      "LATENT"
+    ],
+    [
+      25,
+      24,
+      0,
+      3,
+      0,
+      "MODEL"
+    ],
+    [
+      26,
+      19,
+      0,
+      8,
+      1,
+      "VAE"
+    ],
+    [
+      32,
+      26,
+      0,
+      18,
+      1,
+      "VAE"
+    ],
+    [
+      33,
+      25,
+      0,
+      26,
+      0,
+      "*"
+    ],
+    [
+      34,
+      19,
+      0,
+      25,
+      0,
+      "*"
+    ],
+    [
+      36,
+      11,
+      0,
+      29,
+      0,
+      "T5"
+    ],
+    [
+      37,
+      29,
+      0,
+      3,
+      2,
+      "CONDITIONING"
+    ],
+    [
+      40,
+      30,
+      0,
+      18,
+      0,
+      "IMAGE"
+    ],
+    [
+      44,
+      28,
+      0,
+      33,
+      0,
+      "IMAGE"
+    ],
+    [
+      45,
+      33,
+      0,
+      30,
+      0,
+      "IMAGE"
+    ],
+    [
+      49,
+      33,
+      0,
+      34,
+      0,
+      "IMAGE"
+    ]
+  ],
+  "groups": [],
+  "config": {},
+  "extra": {},
+  "version": 0.4
+}

PixArt-text-to-image-workflow.json

@@ -0,0 +1,501 @@
+{
+  "last_node_id": 156,
+  "last_link_id": 292,
+  "nodes": [
+    {
+      "id": 65,
+      "type": "VAEDecode",
+      "pos": [
+        940,
+        30
+      ],
+      "size": {
+        "0": 200,
+        "1": 50
+      },
+      "flags": {},
+      "order": 8,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "link": 292
+        },
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": 89
+        }
+      ],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            87
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "VAEDecode"
+      }
+    },
+    {
+      "id": 66,
+      "type": "SaveImage",
+      "pos": [
+        940,
+        120
+      ],
+      "size": {
+        "0": 500,
+        "1": 460
+      },
+      "flags": {},
+      "order": 9,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "link": 87
+        }
+      ],
+      "properties": {},
+      "widgets_values": [
+        "ComfyUI_PixArt"
+      ]
+    },
+    {
+      "id": 128,
+      "type": "PixArtResolutionSelect",
+      "pos": [
+        0,
+        150
+      ],
+      "size": {
+        "0": 220,
+        "1": 102
+      },
+      "flags": {},
+      "order": 0,
+      "mode": 0,
+      "outputs": [
+        {
+          "name": "width",
+          "type": "INT",
+          "links": [
+            236
+          ],
+          "shape": 3,
+          "slot_index": 0
+        },
+        {
+          "name": "height",
+          "type": "INT",
+          "links": [
+            237
+          ],
+          "shape": 3,
+          "slot_index": 1
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "PixArtResolutionSelect"
+      },
+      "widgets_values": [
+        "PixArtMS_XL_2",
+        "1.21"
+      ]
+    },
+    {
+      "id": 113,
+      "type": "T5TextEncode",
+      "pos": [
+        260,
+        290
+      ],
+      "size": {
+        "0": 280,
+        "1": 120
+      },
+      "flags": {},
+      "order": 5,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "T5",
+          "type": "T5",
+          "link": 263
+        }
+      ],
+      "outputs": [
+        {
+          "name": "CONDITIONING",
+          "type": "CONDITIONING",
+          "links": [
+            290
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "T5TextEncode"
+      },
+      "widgets_values": [
+        "pixelart drawing of a tank with a (blue:0.8) camo pattern"
+      ]
+    },
+    {
+      "id": 125,
+      "type": "T5TextEncode",
+      "pos": [
+        260,
+        450
+      ],
+      "size": {
+        "0": 280,
+        "1": 80
+      },
+      "flags": {},
+      "order": 6,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "T5",
+          "type": "T5",
+          "link": 264
+        }
+      ],
+      "outputs": [
+        {
+          "name": "CONDITIONING",
+          "type": "CONDITIONING",
+          "links": [
+            291
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "T5TextEncode"
+      },
+      "widgets_values": [
+        "photo, depth of field"
+      ]
+    },
+    {
+      "id": 20,
+      "type": "PixArtCheckpointLoader",
+      "pos": [
+        0,
+        30
+      ],
+      "size": {
+        "0": 400,
+        "1": 82
+      },
+      "flags": {},
+      "order": 1,
+      "mode": 0,
+      "outputs": [
+        {
+          "name": "model",
+          "type": "MODEL",
+          "links": [
+            288
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "PixArtCheckpointLoader"
+      },
+      "widgets_values": [
+        "PixArt-XL-2-1024-MS.pth",
+        "PixArtMS_XL_2"
+      ]
+    },
+    {
+      "id": 144,
+      "type": "T5v11Loader",
+      "pos": [
+        -160,
+        290
+      ],
+      "size": {
+        "0": 380,
+        "1": 154
+      },
+      "flags": {},
+      "order": 2,
+      "mode": 0,
+      "outputs": [
+        {
+          "name": "T5",
+          "type": "T5",
+          "links": [
+            263,
+            264
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "T5v11Loader"
+      },
+      "widgets_values": [
+        "pytorch_model-00001-of-00002.bin",
+        "xxl",
+        "folder",
+        "cpu",
+        "default"
+      ]
+    },
+    {
+      "id": 6,
+      "type": "EmptyLatentImage",
+      "pos": [
+        260,
+        150
+      ],
+      "size": {
+        "0": 280,
+        "1": 100
+      },
+      "flags": {},
+      "order": 4,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "width",
+          "type": "INT",
+          "link": 236,
+          "widget": {
+            "name": "width"
+          }
+        },
+        {
+          "name": "height",
+          "type": "INT",
+          "link": 237,
+          "widget": {
+            "name": "height"
+          }
+        }
+      ],
+      "outputs": [
+        {
+          "name": "LATENT",
+          "type": "LATENT",
+          "links": [
+            289
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "EmptyLatentImage"
+      },
+      "widgets_values": [
+        1024,
+        1024,
+        1
+      ]
+    },
+    {
+      "id": 3,
+      "type": "VAELoader",
+      "pos": [
+        600,
+        550
+      ],
+      "size": {
+        "0": 300,
+        "1": 60
+      },
+      "flags": {},
+      "order": 3,
+      "mode": 0,
+      "outputs": [
+        {
+          "name": "VAE",
+          "type": "VAE",
+          "links": [
+            89
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "VAELoader"
+      },
+      "widgets_values": [
+        "sd-vae-ft-ema/diffusion_pytorch_model.bin"
+      ]
+    },
+    {
+      "id": 155,
+      "type": "KSampler",
+      "pos": [
+        600,
+        30
+      ],
+      "size": {
+        "0": 300,
+        "1": 480
+      },
+      "flags": {},
+      "order": 7,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "model",
+          "type": "MODEL",
+          "link": 288
+        },
+        {
+          "name": "positive",
+          "type": "CONDITIONING",
+          "link": 290
+        },
+        {
+          "name": "negative",
+          "type": "CONDITIONING",
+          "link": 291
+        },
+        {
+          "name": "latent_image",
+          "type": "LATENT",
+          "link": 289
+        }
+      ],
+      "outputs": [
+        {
+          "name": "LATENT",
+          "type": "LATENT",
+          "links": [
+            292
+          ],
+          "shape": 3,
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "KSampler"
+      },
+      "widgets_values": [
+        160,
+        "fixed",
+        20,
+        4.5,
+        "euler",
+        "normal",
+        1
+      ]
+    }
+  ],
+  "links": [
+    [
+      87,
+      65,
+      0,
+      66,
+      0,
+      "IMAGE"
+    ],
+    [
+      89,
+      3,
+      0,
+      65,
+      1,
+      "VAE"
+    ],
+    [
+      236,
+      128,
+      0,
+      6,
+      0,
+      "INT"
+    ],
+    [
+      237,
+      128,
+      1,
+      6,
+      1,
+      "INT"
+    ],
+    [
+      263,
+      144,
+      0,
+      113,
+      0,
+      "T5"
+    ],
+    [
+      264,
+      144,
+      0,
+      125,
+      0,
+      "T5"
+    ],
+    [
+      288,
+      20,
+      0,
+      155,
+      0,
+      "MODEL"
+    ],
+    [
+      289,
+      6,
+      0,
+      155,
+      3,
+      "LATENT"
+    ],
+    [
+      290,
+      113,
+      0,
+      155,
+      1,
+      "CONDITIONING"
+    ],
+    [
+      291,
+      125,
+      0,
+      155,
+      2,
+      "CONDITIONING"
+    ],
+    [
+      292,
+      155,
+      0,
+      65,
+      0,
+      "LATENT"
+    ]
+  ],
+  "groups": [],
+  "config": {},
+  "extra": {},
+  "version": 0.4
+}

README.md

@@ -0,0 +1,8 @@
+---
+license: agpl-3.0
+---
+These weights are for the original Github repository and it's only for research purpose. For other purposes, please check https://huggingface.co/docs/diffusers/main/en/api/pipelines/pixart and https://huggingface.co/PixArt-alpha/PixArt-XL-2-1024-MS. 
+
+Inference Code: https://github.com/PixArt-alpha/PixArt-alpha
+
+Paper: https://arxiv.org/abs/2310.00426

sd-vae-ft-ema/config.json

@@ -0,0 +1,29 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.4.2",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "in_channels": 3,
+  "latent_channels": 4,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 256,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

sd-vae-ft-ema/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c98ebcd7ca5cb69d47b2ae287feba0695689fbf2c8fead2fab05fd3e0c28303
+size 334707217

t5-v1_1-xxl/config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "google/t5-v1_1-xxl",
+  "architectures": [
+    "T5EncoderModel"
+  ],
+  "d_ff": 10240,
+  "d_kv": 64,
+  "d_model": 4096,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 24,
+  "num_heads": 64,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.21.1",
+  "use_cache": true,
+  "vocab_size": 32128
+}

t5-v1_1-xxl/pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f71ad0624095dae788b1023081dda1b4040bd24f7244a5b5b46eebc09825839
+size 9452285635

t5-v1_1-xxl/pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f68f80678299ac59f69b3550ebd47b966571920d8f9e71f42ab61fabaaed868
+size 9597031749

t5-v1_1-xxl/pytorch_model.bin.index.json

@@ -0,0 +1,227 @@
+{
+  "metadata": {
+    "total_size": 19575627776
+  },
+  "weight_map": {
+    "encoder.block.0.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.0.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.1.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.10.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.11.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.11.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.11.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.11.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.11.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.11.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.11.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.12.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.12.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.12.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.12.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.12.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.12.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.12.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.13.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.13.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.13.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.13.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.13.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.13.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.13.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.14.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.14.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.14.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.14.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.14.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.14.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.14.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.15.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.15.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.15.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.15.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.15.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.15.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.15.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.16.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.16.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.16.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.16.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.16.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.16.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.16.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.17.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.17.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.17.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.17.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.17.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.17.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.17.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.18.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.18.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.18.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.18.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.18.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.18.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.18.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.19.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.19.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.19.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.19.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.19.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.19.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.19.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.2.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.2.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.2.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.2.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.2.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.2.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.2.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.20.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.20.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.20.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.20.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.20.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.20.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.20.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.21.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.21.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.21.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.21.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.21.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.21.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.21.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.22.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.22.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.22.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.22.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.22.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.22.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.22.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.23.layer.0.SelfAttention.k.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.23.layer.0.SelfAttention.o.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.23.layer.0.SelfAttention.q.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.23.layer.0.SelfAttention.v.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.23.layer.0.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.23.layer.1.DenseReluDense.wo.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.23.layer.1.layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "encoder.block.3.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.3.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.3.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.3.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.3.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.3.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.3.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.4.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.5.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.6.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.7.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.8.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.0.SelfAttention.k.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.0.SelfAttention.o.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.0.SelfAttention.q.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.0.SelfAttention.v.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.0.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.1.DenseReluDense.wo.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.block.9.layer.1.layer_norm.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
+    "encoder.final_layer_norm.weight": "pytorch_model-00002-of-00002.bin",
+    "shared.weight": "pytorch_model-00001-of-00002.bin"
+  }
+}

t5-v1_1-xxl/special_tokens_map.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}

t5-v1_1-xxl/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656

t5-v1_1-xxl/tokenizer_config.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "model_max_length": 512, "name_or_path": "t5-small"}