File size: 72,706 Bytes
230a1aa | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 | qwen_image_series = [
{
# Example: ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="text_encoder/model*.safetensors")
"model_hash": "0319a1cb19835fb510907dd3367c95ff",
"model_name": "qwen_image_dit",
"model_class": "diffsynth.models.qwen_image_dit.QwenImageDiT",
},
{
# Example: ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors")
"model_hash": "8004730443f55db63092006dd9f7110e",
"model_name": "qwen_image_text_encoder",
"model_class": "diffsynth.models.qwen_image_text_encoder.QwenImageTextEncoder",
"state_dict_converter": "diffsynth.utils.state_dict_converters.qwen_image_text_encoder.QwenImageTextEncoderStateDictConverter",
},
{
# Example: ModelConfig(model_id="Qwen/Qwen-Image", origin_file_pattern="vae/diffusion_pytorch_model.safetensors")
"model_hash": "ed4ea5824d55ec3107b09815e318123a",
"model_name": "qwen_image_vae",
"model_class": "diffsynth.models.qwen_image_vae.QwenImageVAE",
},
{
# Example: ModelConfig(model_id="DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Depth", origin_file_pattern="model.safetensors")
"model_hash": "073bce9cf969e317e5662cd570c3e79c",
"model_name": "qwen_image_blockwise_controlnet",
"model_class": "diffsynth.models.qwen_image_controlnet.QwenImageBlockWiseControlNet",
},
{
# Example: ModelConfig(model_id="DiffSynth-Studio/Qwen-Image-Blockwise-ControlNet-Inpaint", origin_file_pattern="model.safetensors")
"model_hash": "a9e54e480a628f0b956a688a81c33bab",
"model_name": "qwen_image_blockwise_controlnet",
"model_class": "diffsynth.models.qwen_image_controlnet.QwenImageBlockWiseControlNet",
"extra_kwargs": {"additional_in_dim": 4},
},
{
# Example: ModelConfig(model_id="DiffSynth-Studio/General-Image-Encoders", origin_file_pattern="SigLIP2-G384/model.safetensors")
"model_hash": "469c78b61e3e31bc9eec0d0af3d3f2f8",
"model_name": "siglip2_image_encoder",
"model_class": "diffsynth.models.siglip2_image_encoder.Siglip2ImageEncoder",
},
{
# Example: ModelConfig(model_id="DiffSynth-Studio/General-Image-Encoders", origin_file_pattern="DINOv3-7B/model.safetensors")
"model_hash": "5722b5c873720009de96422993b15682",
"model_name": "dinov3_image_encoder",
"model_class": "diffsynth.models.dinov3_image_encoder.DINOv3ImageEncoder",
"state_dict_converter": "diffsynth.utils.state_dict_converters.dino_v3.DINOv3StateDictConverter",
},
{
# Example:
"model_hash": "a166c33455cdbd89c0888a3645ca5c0f",
"model_name": "qwen_image_image2lora_coarse",
"model_class": "diffsynth.models.qwen_image_image2lora.QwenImageImage2LoRAModel",
},
{
# Example:
"model_hash": "a5476e691767a4da6d3a6634a10f7408",
"model_name": "qwen_image_image2lora_fine",
"model_class": "diffsynth.models.qwen_image_image2lora.QwenImageImage2LoRAModel",
"extra_kwargs": {"residual_length": 37*37+7, "residual_mid_dim": 64}
},
{
# Example:
"model_hash": "0aad514690602ecaff932c701cb4b0bb",
"model_name": "qwen_image_image2lora_style",
"model_class": "diffsynth.models.qwen_image_image2lora.QwenImageImage2LoRAModel",
"extra_kwargs": {"compress_dim": 64, "use_residual": False}
},
{
# Example: ModelConfig(model_id="Qwen/Qwen-Image-Layered", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors")
"model_hash": "8dc8cda05de16c73afa755e2c1ce2839",
"model_name": "qwen_image_dit",
"model_class": "diffsynth.models.qwen_image_dit.QwenImageDiT",
"extra_kwargs": {"use_layer3d_rope": True, "use_additional_t_cond": True}
},
{
# Example: ModelConfig(model_id="Qwen/Qwen-Image-Layered", origin_file_pattern="vae/diffusion_pytorch_model.safetensors")
"model_hash": "44b39ddc499e027cfb24f7878d7416b9",
"model_name": "qwen_image_vae",
"model_class": "diffsynth.models.qwen_image_vae.QwenImageVAE",
"extra_kwargs": {"image_channels": 4}
},
]
wan_series = [
{
# Example: ModelConfig(model_id="krea/krea-realtime-video", origin_file_pattern="krea-realtime-video-14b.safetensors")
"model_hash": "5ec04e02b42d2580483ad69f4e76346a",
"model_name": "wan_video_dit",
"model_class": "diffsynth.models.wan_video_dit.WanModel",
"extra_kwargs": {'has_image_input': False, 'patch_size': [1, 2, 2], 'in_dim': 16, 'dim': 5120, 'ffn_dim': 13824, 'freq_dim': 256, 'text_dim': 4096, 'out_dim': 16, 'num_heads': 40, 'num_layers': 40, 'eps': 1e-06},
"state_dict_converter": "diffsynth.utils.state_dict_converters.wan_video_dit.WanVideoDiTStateDictConverter",
},
{
# Example: ModelConfig(model_id="Wan-AI/Wan2.1-T2V-14B", origin_file_pattern="models_t5_umt5-xxl-enc-bf16.pth")
"model_hash": "9c8818c2cbea55eca56c7b447df170da",
"model_name": "wan_video_text_encoder",
"model_class": "diffsynth.models.wan_video_text_encoder.WanTextEncoder",
},
{
# Example: ModelConfig(model_id="Wan-AI/Wan2.1-T2V-14B", origin_file_pattern="Wan2.1_VAE.pth")
"model_hash": "ccc42284ea13e1ad04693284c7a09be6",
"model_name": "wan_video_vae",
"model_class": "diffsynth.models.wan_video_vae.WanVideoVAE",
"state_dict_converter": "diffsynth.utils.state_dict_converters.wan_video_vae.WanVideoVAEStateDictConverter",
},
{
# Example: ModelConfig(model_id="meituan-longcat/LongCat-Video", origin_file_pattern="dit/diffusion_pytorch_model*.safetensors")
"model_hash": "8b27900f680d7251ce44e2dc8ae1ffef",
"model_name": "wan_video_dit",
"model_class": "diffsynth.models.longcat_video_dit.LongCatVideoTransformer3DModel",
},
{
# Example: ModelConfig(model_id="ByteDance/Video-As-Prompt-Wan2.1-14B", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors")
"model_hash": "5f90e66a0672219f12d9a626c8c21f61",
"model_name": "wan_video_dit",
"model_class": "diffsynth.models.wan_video_dit.WanModel",
"extra_kwargs": {'has_image_input': True, 'patch_size': [1, 2, 2], 'in_dim': 36, 'dim': 5120, 'ffn_dim': 13824, 'freq_dim': 256, 'text_dim': 4096, 'out_dim': 16, 'num_heads': 40, 'num_layers': 40, 'eps': 1e-06},
"state_dict_converter": "diffsynth.utils.state_dict_converters.wan_video_dit.WanVideoDiTFromDiffusers"
},
{
# Example: ModelConfig(model_id="ByteDance/Video-As-Prompt-Wan2.1-14B", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors")
"model_hash": "5f90e66a0672219f12d9a626c8c21f61",
"model_name": "wan_video_vap",
"model_class": "diffsynth.models.wan_video_mot.MotWanModel",
"state_dict_converter": "diffsynth.utils.state_dict_converters.wan_video_mot.WanVideoMotStateDictConverter"
},
{
# Example: ModelConfig(model_id="Wan-AI/Wan2.1-I2V-14B-480P", origin_file_pattern="models_clip_open-clip-xlm-roberta-large-vit-huge-14.pth")
"model_hash": "5941c53e207d62f20f9025686193c40b",
"model_name": "wan_video_image_encoder",
"model_class": "diffsynth.models.wan_video_image_encoder.WanImageEncoder",
"state_dict_converter": "diffsynth.utils.state_dict_converters.wan_video_image_encoder.WanImageEncoderStateDictConverter"
},
{
# Example: ModelConfig(model_id="DiffSynth-Studio/Wan2.1-1.3b-speedcontrol-v1", origin_file_pattern="model.safetensors")
"model_hash": "dbd5ec76bbf977983f972c151d545389",
"model_name": "wan_video_motion_controller",
"model_class": "diffsynth.models.wan_video_motion_controller.WanMotionControllerModel",
},
{
# Example: ModelConfig(model_id="Wan-AI/Wan2.1-T2V-1.3B", origin_file_pattern="diffusion_pytorch_model*.safetensors")
"model_hash": "9269f8db9040a9d860eaca435be61814",
"model_name": "wan_video_dit",
"model_class": "diffsynth.models.wan_video_dit.WanModel",
"extra_kwargs": {'has_image_input': False, 'patch_size': [1, 2, 2], 'in_dim': 16, 'dim': 1536, 'ffn_dim': 8960, 'freq_dim': 256, 'text_dim': 4096, 'out_dim': 16, 'num_heads': 12, 'num_layers': 30, 'eps': 1e-06}
},
{
# Example: ModelConfig(model_id="Wan-AI/Wan2.1-FLF2V-14B-720P", origin_file_pattern="diffusion_pytorch_model*.safetensors")
"model_hash": "3ef3b1f8e1dab83d5b71fd7b617f859f",
"model_name": "wan_video_dit",
"model_class": "diffsynth.models.wan_video_dit.WanModel",
"extra_kwargs": {'has_image_input': True, 'patch_size': [1, 2, 2], 'in_dim': 36, 'dim': 5120, 'ffn_dim': 13824, 'freq_dim': 256, 'text_dim': 4096, 'out_dim': 16, 'num_heads': 40, 'num_layers': 40, 'eps': 1e-06, 'has_image_pos_emb': True}
},
{
# Example: ModelConfig(model_id="PAI/Wan2.1-Fun-1.3B-Control", origin_file_pattern="diffusion_pytorch_model*.safetensors")
"model_hash": "349723183fc063b2bfc10bb2835cf677",
"model_name": "wan_video_dit",
"model_class": "diffsynth.models.wan_video_dit.WanModel",
"extra_kwargs": {'has_image_input': True, 'patch_size': [1, 2, 2], 'in_dim': 48, 'dim': 1536, 'ffn_dim': 8960, 'freq_dim': 256, 'text_dim': 4096, 'out_dim': 16, 'num_heads': 12, 'num_layers': 30, 'eps': 1e-06}
},
{
# Example: ModelConfig(model_id="PAI/Wan2.1-Fun-1.3B-InP", origin_file_pattern="diffusion_pytorch_model*.safetensors")
"model_hash": "6d6ccde6845b95ad9114ab993d917893",
"model_name": "wan_video_dit",
"model_class": "diffsynth.models.wan_video_dit.WanModel",
"extra_kwargs": {'has_image_input': True, 'patch_size': [1, 2, 2], 'in_dim': 36, 'dim': 1536, 'ffn_dim': 8960, 'freq_dim': 256, 'text_dim': 4096, 'out_dim': 16, 'num_heads': 12, 'num_layers': 30, 'eps': 1e-06}
},
{
# Example: ModelConfig(model_id="PAI/Wan2.1-Fun-14B-Control", origin_file_pattern="diffusion_pytorch_model*.safetensors")
"model_hash": "efa44cddf936c70abd0ea28b6cbe946c",
"model_name": "wan_video_dit",
"model_class": "diffsynth.models.wan_video_dit.WanModel",
"extra_kwargs": {'has_image_input': True, 'patch_size': [1, 2, 2], 'in_dim': 48, 'dim': 5120, 'ffn_dim': 13824, 'freq_dim': 256, 'text_dim': 4096, 'out_dim': 16, 'num_heads': 40, 'num_layers': 40, 'eps': 1e-06}
},
{
# Example: ModelConfig(model_id="PAI/Wan2.1-Fun-14B-InP", origin_file_pattern="diffusion_pytorch_model*.safetensors")
"model_hash": "6bfcfb3b342cb286ce886889d519a77e",
"model_name": "wan_video_dit",
"model_class": "diffsynth.models.wan_video_dit.WanModel",
"extra_kwargs": {'has_image_input': True, 'patch_size': [1, 2, 2], 'in_dim': 36, 'dim': 5120, 'ffn_dim': 13824, 'freq_dim': 256, 'text_dim': 4096, 'out_dim': 16, 'num_heads': 40, 'num_layers': 40, 'eps': 1e-06}
},
{
# Example: ModelConfig(model_id="PAI/Wan2.1-Fun-V1.1-1.3B-Control-Camera", origin_file_pattern="diffusion_pytorch_model*.safetensors")
"model_hash": "ac6a5aa74f4a0aab6f64eb9a72f19901",
"model_name": "wan_video_dit",
"model_class": "diffsynth.models.wan_video_dit.WanModel",
"extra_kwargs": {'has_image_input': True, 'patch_size': [1, 2, 2], 'in_dim': 32, 'dim': 1536, 'ffn_dim': 8960, 'freq_dim': 256, 'text_dim': 4096, 'out_dim': 16, 'num_heads': 12, 'num_layers': 30, 'eps': 1e-06, 'has_ref_conv': False, 'add_control_adapter': True, 'in_dim_control_adapter': 24}
},
{
# Example: ModelConfig(model_id="PAI/Wan2.1-Fun-V1.1-1.3B-Control", origin_file_pattern="diffusion_pytorch_model*.safetensors")
"model_hash": "70ddad9d3a133785da5ea371aae09504",
"model_name": "wan_video_dit",
"model_class": "diffsynth.models.wan_video_dit.WanModel",
"extra_kwargs": {'has_image_input': True, 'patch_size': [1, 2, 2], 'in_dim': 48, 'dim': 1536, 'ffn_dim': 8960, 'freq_dim': 256, 'text_dim': 4096, 'out_dim': 16, 'num_heads': 12, 'num_layers': 30, 'eps': 1e-06, 'has_ref_conv': True}
},
{
# Example: ModelConfig(model_id="PAI/Wan2.1-Fun-V1.1-14B-Control-Camera", origin_file_pattern="diffusion_pytorch_model*.safetensors")
"model_hash": "b61c605c2adbd23124d152ed28e049ae",
"model_name": "wan_video_dit",
"model_class": "diffsynth.models.wan_video_dit.WanModel",
"extra_kwargs": {'has_image_input': True, 'patch_size': [1, 2, 2], 'in_dim': 32, 'dim': 5120, 'ffn_dim': 13824, 'freq_dim': 256, 'text_dim': 4096, 'out_dim': 16, 'num_heads': 40, 'num_layers': 40, 'eps': 1e-06, 'has_ref_conv': False, 'add_control_adapter': True, 'in_dim_control_adapter': 24}
},
{
# Example: ModelConfig(model_id="PAI/Wan2.1-Fun-V1.1-14B-Control", origin_file_pattern="diffusion_pytorch_model*.safetensors")
"model_hash": "26bde73488a92e64cc20b0a7485b9e5b",
"model_name": "wan_video_dit",
"model_class": "diffsynth.models.wan_video_dit.WanModel",
"extra_kwargs": {'has_image_input': True, 'patch_size': [1, 2, 2], 'in_dim': 48, 'dim': 5120, 'ffn_dim': 13824, 'freq_dim': 256, 'text_dim': 4096, 'out_dim': 16, 'num_heads': 40, 'num_layers': 40, 'eps': 1e-06, 'has_ref_conv': True}
},
{
# Example: ModelConfig(model_id="Wan-AI/Wan2.1-T2V-14B", origin_file_pattern="diffusion_pytorch_model*.safetensors")
"model_hash": "aafcfd9672c3a2456dc46e1cb6e52c70",
"model_name": "wan_video_dit",
"model_class": "diffsynth.models.wan_video_dit.WanModel",
"extra_kwargs": {'has_image_input': False, 'patch_size': [1, 2, 2], 'in_dim': 16, 'dim': 5120, 'ffn_dim': 13824, 'freq_dim': 256, 'text_dim': 4096, 'out_dim': 16, 'num_heads': 40, 'num_layers': 40, 'eps': 1e-06}
},
{
# Example: ModelConfig(model_id="iic/VACE-Wan2.1-1.3B-Preview", origin_file_pattern="diffusion_pytorch_model*.safetensors")
"model_hash": "a61453409b67cd3246cf0c3bebad47ba",
"model_name": "wan_video_dit",
"model_class": "diffsynth.models.wan_video_dit.WanModel",
"extra_kwargs": {'has_image_input': False, 'patch_size': [1, 2, 2], 'in_dim': 16, 'dim': 1536, 'ffn_dim': 8960, 'freq_dim': 256, 'text_dim': 4096, 'out_dim': 16, 'num_heads': 12, 'num_layers': 30, 'eps': 1e-06},
"state_dict_converter": "diffsynth.utils.state_dict_converters.wan_video_dit.WanVideoDiTStateDictConverter",
},
{
# Example: ModelConfig(model_id="iic/VACE-Wan2.1-1.3B-Preview", origin_file_pattern="diffusion_pytorch_model*.safetensors")
"model_hash": "a61453409b67cd3246cf0c3bebad47ba",
"model_name": "wan_video_vace",
"model_class": "diffsynth.models.wan_video_vace.VaceWanModel",
"state_dict_converter": "diffsynth.utils.state_dict_converters.wan_video_vace.VaceWanModelDictConverter"
},
{
# Example: ModelConfig(model_id="Wan-AI/Wan2.1-VACE-14B", origin_file_pattern="diffusion_pytorch_model*.safetensors")
"model_hash": "7a513e1f257a861512b1afd387a8ecd9",
"model_name": "wan_video_dit",
"model_class": "diffsynth.models.wan_video_dit.WanModel",
"extra_kwargs": {'has_image_input': False, 'patch_size': [1, 2, 2], 'in_dim': 16, 'dim': 5120, 'ffn_dim': 13824, 'freq_dim': 256, 'text_dim': 4096, 'out_dim': 16, 'num_heads': 40, 'num_layers': 40, 'eps': 1e-06},
"state_dict_converter": "diffsynth.utils.state_dict_converters.wan_video_dit.WanVideoDiTStateDictConverter",
},
{
# Example: ModelConfig(model_id="Wan-AI/Wan2.1-VACE-14B", origin_file_pattern="diffusion_pytorch_model*.safetensors")
"model_hash": "7a513e1f257a861512b1afd387a8ecd9",
"model_name": "wan_video_vace",
"model_class": "diffsynth.models.wan_video_vace.VaceWanModel",
"extra_kwargs": {'vace_layers': (0, 5, 10, 15, 20, 25, 30, 35), 'vace_in_dim': 96, 'patch_size': (1, 2, 2), 'has_image_input': False, 'dim': 5120, 'num_heads': 40, 'ffn_dim': 13824, 'eps': 1e-06},
"state_dict_converter": "diffsynth.utils.state_dict_converters.wan_video_vace.VaceWanModelDictConverter"
},
{
# Example: ModelConfig(model_id="Wan-AI/Wan2.2-Animate-14B", origin_file_pattern="diffusion_pytorch_model*.safetensors")
"model_hash": "31fa352acb8a1b1d33cd8764273d80a2",
"model_name": "wan_video_dit",
"model_class": "diffsynth.models.wan_video_dit.WanModel",
"extra_kwargs": {'has_image_input': True, 'patch_size': [1, 2, 2], 'in_dim': 36, 'dim': 5120, 'ffn_dim': 13824, 'freq_dim': 256, 'text_dim': 4096, 'out_dim': 16, 'num_heads': 40, 'num_layers': 40, 'eps': 1e-06},
"state_dict_converter": "diffsynth.utils.state_dict_converters.wan_video_dit.WanVideoDiTStateDictConverter"
},
{
# Example: ModelConfig(model_id="Wan-AI/Wan2.2-Animate-14B", origin_file_pattern="diffusion_pytorch_model*.safetensors")
"model_hash": "31fa352acb8a1b1d33cd8764273d80a2",
"model_name": "wan_video_animate_adapter",
"model_class": "diffsynth.models.wan_video_animate_adapter.WanAnimateAdapter",
"state_dict_converter": "diffsynth.utils.state_dict_converters.wan_video_animate_adapter.WanAnimateAdapterStateDictConverter"
},
{
# Example: ModelConfig(model_id="PAI/Wan2.2-Fun-A14B-Control-Camera", origin_file_pattern="high_noise_model/diffusion_pytorch_model*.safetensors")
"model_hash": "47dbeab5e560db3180adf51dc0232fb1",
"model_name": "wan_video_dit",
"model_class": "diffsynth.models.wan_video_dit.WanModel",
"extra_kwargs": {'has_image_input': False, 'patch_size': [1, 2, 2], 'in_dim': 36, 'dim': 5120, 'ffn_dim': 13824, 'freq_dim': 256, 'text_dim': 4096, 'out_dim': 16, 'num_heads': 40, 'num_layers': 40, 'eps': 1e-06, 'has_ref_conv': False, 'add_control_adapter': True, 'in_dim_control_adapter': 24, 'require_clip_embedding': False}
},
{
# Example: ModelConfig(model_id="PAI/Wan2.2-Fun-A14B-Control", origin_file_pattern="high_noise_model/diffusion_pytorch_model*.safetensors")
"model_hash": "2267d489f0ceb9f21836532952852ee5",
"model_name": "wan_video_dit",
"model_class": "diffsynth.models.wan_video_dit.WanModel",
"extra_kwargs": {'has_image_input': False, 'patch_size': [1, 2, 2], 'in_dim': 52, 'dim': 5120, 'ffn_dim': 13824, 'freq_dim': 256, 'text_dim': 4096, 'out_dim': 16, 'num_heads': 40, 'num_layers': 40, 'eps': 1e-06, 'has_ref_conv': True, 'require_clip_embedding': False},
},
{
# Example: ModelConfig(model_id="Wan-AI/Wan2.2-I2V-A14B", origin_file_pattern="high_noise_model/diffusion_pytorch_model*.safetensors")
"model_hash": "5b013604280dd715f8457c6ed6d6a626",
"model_name": "wan_video_dit",
"model_class": "diffsynth.models.wan_video_dit.WanModel",
"extra_kwargs": {'has_image_input': False, 'patch_size': [1, 2, 2], 'in_dim': 36, 'dim': 5120, 'ffn_dim': 13824, 'freq_dim': 256, 'text_dim': 4096, 'out_dim': 16, 'num_heads': 40, 'num_layers': 40, 'eps': 1e-06, 'require_clip_embedding': False}
},
{
# Example: ModelConfig(model_id="Wan-AI/Wan2.2-S2V-14B", origin_file_pattern="diffusion_pytorch_model*.safetensors")
"model_hash": "966cffdcc52f9c46c391768b27637614",
"model_name": "wan_video_dit",
"model_class": "diffsynth.models.wan_video_dit_s2v.WanS2VModel",
"extra_kwargs": {'dim': 5120, 'in_dim': 16, 'ffn_dim': 13824, 'out_dim': 16, 'text_dim': 4096, 'freq_dim': 256, 'eps': 1e-06, 'patch_size': (1, 2, 2), 'num_heads': 40, 'num_layers': 40, 'cond_dim': 16, 'audio_dim': 1024, 'num_audio_token': 4}
},
{
# Example: ModelConfig(model_id="Wan-AI/Wan2.2-TI2V-5B", origin_file_pattern="diffusion_pytorch_model*.safetensors")
"model_hash": "1f5ab7703c6fc803fdded85ff040c316",
"model_name": "wan_video_dit",
"model_class": "diffsynth.models.wan_video_dit.WanModel",
"extra_kwargs": {'has_image_input': False, 'patch_size': [1, 2, 2], 'in_dim': 48, 'dim': 3072, 'ffn_dim': 14336, 'freq_dim': 256, 'text_dim': 4096, 'out_dim': 48, 'num_heads': 24, 'num_layers': 30, 'eps': 1e-06, 'seperated_timestep': True, 'require_clip_embedding': False, 'require_vae_embedding': False, 'fuse_vae_embedding_in_latents': True}
},
{
# Example: ModelConfig(model_id="Wan-AI/Wan2.2-TI2V-5B", origin_file_pattern="Wan2.2_VAE.pth")
"model_hash": "e1de6c02cdac79f8b739f4d3698cd216",
"model_name": "wan_video_vae",
"model_class": "diffsynth.models.wan_video_vae.WanVideoVAE38",
"state_dict_converter": "diffsynth.utils.state_dict_converters.wan_video_vae.WanVideoVAEStateDictConverter",
},
{
# Example: ModelConfig(model_id="Wan-AI/Wan2.2-S2V-14B", origin_file_pattern="wav2vec2-large-xlsr-53-english/model.safetensors")
"model_hash": "06be60f3a4526586d8431cd038a71486",
"model_name": "wans2v_audio_encoder",
"model_class": "diffsynth.models.wav2vec.WanS2VAudioEncoder",
"state_dict_converter": "diffsynth.utils.state_dict_converters.wans2v_audio_encoder.WanS2VAudioEncoderStateDictConverter",
},
{
# Example: ModelConfig(model_id="Wan-AI/Wan2.2-Dancer-14B", origin_file_pattern="global_model.safetensors")
"model_hash": "eb18873fc0ba77b541eb7b62dbcd2059",
"model_name": "wan_video_dit",
"model_class": "diffsynth.models.wan_video_dit.WanModel",
"extra_kwargs": {'has_image_input': True, 'patch_size': [1, 2, 2], 'in_dim': 36, 'dim': 5120, 'ffn_dim': 13824, 'freq_dim': 256, 'text_dim': 4096, 'out_dim': 16, 'num_heads': 40, 'num_layers': 40, 'eps': 1e-06, 'wantodance_enable_music_inject': True, 'wantodance_music_inject_layers': [0, 4, 8, 12, 16, 20, 24, 27], 'wantodance_enable_refimage': True, 'has_ref_conv': True, 'wantodance_enable_refface': False, 'wantodance_enable_global': True, 'wantodance_enable_dynamicfps': True, 'wantodance_enable_unimodel': True}
},
]
flux_series = [
{
# Example: ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="flux1-dev.safetensors")
"model_hash": "a29710fea6dddb0314663ee823598e50",
"model_name": "flux_dit",
"model_class": "diffsynth.models.flux_dit.FluxDiT",
"state_dict_converter": "diffsynth.utils.state_dict_converters.flux_dit.FluxDiTStateDictConverter",
},
{
# Supported due to historical reasons.
"model_hash": "605c56eab23e9e2af863ad8f0813a25d",
"model_name": "flux_dit",
"model_class": "diffsynth.models.flux_dit.FluxDiT",
"state_dict_converter": "diffsynth.utils.state_dict_converters.flux_dit.FluxDiTStateDictConverterFromDiffusers",
},
{
# Example: ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder/model.safetensors")
"model_hash": "94eefa3dac9cec93cb1ebaf1747d7b78",
"model_name": "flux_text_encoder_clip",
"model_class": "diffsynth.models.flux_text_encoder_clip.FluxTextEncoderClip",
"state_dict_converter": "diffsynth.utils.state_dict_converters.flux_text_encoder_clip.FluxTextEncoderClipStateDictConverter",
},
{
# Example: ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="text_encoder_2/*.safetensors")
"model_hash": "22540b49eaedbc2f2784b2091a234c7c",
"model_name": "flux_text_encoder_t5",
"model_class": "diffsynth.models.flux_text_encoder_t5.FluxTextEncoderT5",
"state_dict_converter": "diffsynth.utils.state_dict_converters.flux_text_encoder_t5.FluxTextEncoderT5StateDictConverter",
},
{
# Example: ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors")
"model_hash": "21ea55f476dfc4fd135587abb59dfe5d",
"model_name": "flux_vae_encoder",
"model_class": "diffsynth.models.flux_vae.FluxVAEEncoder",
"state_dict_converter": "diffsynth.utils.state_dict_converters.flux_vae.FluxVAEEncoderStateDictConverter",
},
{
# Example: ModelConfig(model_id="black-forest-labs/FLUX.1-dev", origin_file_pattern="ae.safetensors")
"model_hash": "21ea55f476dfc4fd135587abb59dfe5d",
"model_name": "flux_vae_decoder",
"model_class": "diffsynth.models.flux_vae.FluxVAEDecoder",
"state_dict_converter": "diffsynth.utils.state_dict_converters.flux_vae.FluxVAEDecoderStateDictConverter",
},
{
# Example: ModelConfig(model_id="ostris/Flex.2-preview", origin_file_pattern="Flex.2-preview.safetensors")
"model_hash": "d02f41c13549fa5093d3521f62a5570a",
"model_name": "flux_dit",
"model_class": "diffsynth.models.flux_dit.FluxDiT",
"extra_kwargs": {'input_dim': 196, 'num_blocks': 8},
"state_dict_converter": "diffsynth.utils.state_dict_converters.flux_dit.FluxDiTStateDictConverter",
},
{
# Example: ModelConfig(model_id="DiffSynth-Studio/AttriCtrl-FLUX.1-Dev", origin_file_pattern="models/brightness.safetensors")
"model_hash": "0629116fce1472503a66992f96f3eb1a",
"model_name": "flux_value_controller",
"model_class": "diffsynth.models.flux_value_control.SingleValueEncoder",
},
{
# Example: ModelConfig(model_id="alimama-creative/FLUX.1-dev-Controlnet-Inpainting-Beta", origin_file_pattern="diffusion_pytorch_model.safetensors")
"model_hash": "52357cb26250681367488a8954c271e8",
"model_name": "flux_controlnet",
"model_class": "diffsynth.models.flux_controlnet.FluxControlNet",
"state_dict_converter": "diffsynth.utils.state_dict_converters.flux_controlnet.FluxControlNetStateDictConverter",
"extra_kwargs": {"num_joint_blocks": 6, "num_single_blocks": 0, "additional_input_dim": 4},
},
{
# Example: ModelConfig(model_id="InstantX/FLUX.1-dev-Controlnet-Union-alpha", origin_file_pattern="diffusion_pytorch_model.safetensors")
"model_hash": "78d18b9101345ff695f312e7e62538c0",
"model_name": "flux_controlnet",
"model_class": "diffsynth.models.flux_controlnet.FluxControlNet",
"state_dict_converter": "diffsynth.utils.state_dict_converters.flux_controlnet.FluxControlNetStateDictConverter",
"extra_kwargs": {"num_mode": 10, "mode_dict": {"canny": 0, "tile": 1, "depth": 2, "blur": 3, "pose": 4, "gray": 5, "lq": 6}},
},
{
# Example: ModelConfig(model_id="jasperai/Flux.1-dev-Controlnet-Upscaler", origin_file_pattern="diffusion_pytorch_model.safetensors")
"model_hash": "b001c89139b5f053c715fe772362dd2a",
"model_name": "flux_controlnet",
"model_class": "diffsynth.models.flux_controlnet.FluxControlNet",
"state_dict_converter": "diffsynth.utils.state_dict_converters.flux_controlnet.FluxControlNetStateDictConverter",
"extra_kwargs": {"num_single_blocks": 0},
},
{
# Example: ModelConfig(model_id="ByteDance/InfiniteYou", origin_file_pattern="infu_flux_v1.0/aes_stage2/image_proj_model.bin")
"model_hash": "c07c0f04f5ff55e86b4e937c7a40d481",
"model_name": "infiniteyou_image_projector",
"model_class": "diffsynth.models.flux_infiniteyou.InfiniteYouImageProjector",
"state_dict_converter": "diffsynth.utils.state_dict_converters.flux_infiniteyou.FluxInfiniteYouImageProjectorStateDictConverter",
},
{
# Example: ModelConfig(model_id="ByteDance/InfiniteYou", origin_file_pattern="infu_flux_v1.0/aes_stage2/InfuseNetModel/*.safetensors")
"model_hash": "7f9583eb8ba86642abb9a21a4b2c9e16",
"model_name": "flux_controlnet",
"model_class": "diffsynth.models.flux_controlnet.FluxControlNet",
"state_dict_converter": "diffsynth.utils.state_dict_converters.flux_controlnet.FluxControlNetStateDictConverter",
"extra_kwargs": {"num_joint_blocks": 4, "num_single_blocks": 10},
},
{
# Example: ModelConfig(model_id="DiffSynth-Studio/LoRA-Encoder-FLUX.1-Dev", origin_file_pattern="model.safetensors")
"model_hash": "77c2e4dd2440269eb33bfaa0d004f6ab",
"model_name": "flux_lora_encoder",
"model_class": "diffsynth.models.flux_lora_encoder.FluxLoRAEncoder",
},
{
# Example: ModelConfig(model_id="DiffSynth-Studio/LoRAFusion-preview-FLUX.1-dev", origin_file_pattern="model.safetensors")
"model_hash": "30143afb2dea73d1ac580e0787628f8c",
"model_name": "flux_lora_patcher",
"model_class": "diffsynth.models.flux_lora_patcher.FluxLoraPatcher",
},
{
# Example: ModelConfig(model_id="DiffSynth-Studio/Nexus-GenV2", origin_file_pattern="model*.safetensors")
"model_hash": "2bd19e845116e4f875a0a048e27fc219",
"model_name": "nexus_gen_llm",
"model_class": "diffsynth.models.nexus_gen.NexusGenAutoregressiveModel",
"state_dict_converter": "diffsynth.utils.state_dict_converters.nexus_gen.NexusGenAutoregressiveModelStateDictConverter",
},
{
# Example: ModelConfig(model_id="DiffSynth-Studio/Nexus-GenV2", origin_file_pattern="edit_decoder.bin")
"model_hash": "63c969fd37cce769a90aa781fbff5f81",
"model_name": "nexus_gen_editing_adapter",
"model_class": "diffsynth.models.nexus_gen_projector.NexusGenImageEmbeddingMerger",
"state_dict_converter": "diffsynth.utils.state_dict_converters.nexus_gen_projector.NexusGenMergerStateDictConverter",
},
{
# Example: ModelConfig(model_id="DiffSynth-Studio/Nexus-GenV2", origin_file_pattern="edit_decoder.bin")
"model_hash": "63c969fd37cce769a90aa781fbff5f81",
"model_name": "flux_dit",
"model_class": "diffsynth.models.flux_dit.FluxDiT",
"state_dict_converter": "diffsynth.utils.state_dict_converters.flux_dit.FluxDiTStateDictConverter",
},
{
# Example: ModelConfig(model_id="DiffSynth-Studio/Nexus-GenV2", origin_file_pattern="generation_decoder.bin")
"model_hash": "3e6c61b0f9471135fc9c6d6a98e98b6d",
"model_name": "nexus_gen_generation_adapter",
"model_class": "diffsynth.models.nexus_gen_projector.NexusGenAdapter",
"state_dict_converter": "diffsynth.utils.state_dict_converters.nexus_gen_projector.NexusGenAdapterStateDictConverter",
},
{
# Example: ModelConfig(model_id="DiffSynth-Studio/Nexus-GenV2", origin_file_pattern="generation_decoder.bin")
"model_hash": "3e6c61b0f9471135fc9c6d6a98e98b6d",
"model_name": "flux_dit",
"model_class": "diffsynth.models.flux_dit.FluxDiT",
"state_dict_converter": "diffsynth.utils.state_dict_converters.flux_dit.FluxDiTStateDictConverter",
},
{
# Example: ModelConfig(model_id="InstantX/FLUX.1-dev-IP-Adapter", origin_file_pattern="ip-adapter.bin")
"model_hash": "4daaa66cc656a8fe369908693dad0a35",
"model_name": "flux_ipadapter",
"model_class": "diffsynth.models.flux_ipadapter.FluxIpAdapter",
"state_dict_converter": "diffsynth.utils.state_dict_converters.flux_ipadapter.FluxIpAdapterStateDictConverter",
},
{
# Example: ModelConfig(model_id="google/siglip-so400m-patch14-384", origin_file_pattern="model.safetensors")
"model_hash": "04d8c1e20a1f1b25f7434f111992a33f",
"model_name": "siglip_vision_model",
"model_class": "diffsynth.models.flux_ipadapter.SiglipVisionModelSO400M",
"state_dict_converter": "diffsynth.utils.state_dict_converters.flux_ipadapter.SiglipStateDictConverter",
},
{
# Example: ModelConfig(model_id="stepfun-ai/Step1X-Edit", origin_file_pattern="step1x-edit-i1258.safetensors"),
"model_hash": "d30fb9e02b1dbf4e509142f05cf7dd50",
"model_name": "step1x_connector",
"model_class": "diffsynth.models.step1x_connector.Qwen2Connector",
"state_dict_converter": "diffsynth.utils.state_dict_converters.step1x_connector.Qwen2ConnectorStateDictConverter",
},
{
# Example: ModelConfig(model_id="stepfun-ai/Step1X-Edit", origin_file_pattern="step1x-edit-i1258.safetensors"),
"model_hash": "d30fb9e02b1dbf4e509142f05cf7dd50",
"model_name": "flux_dit",
"model_class": "diffsynth.models.flux_dit.FluxDiT",
"state_dict_converter": "diffsynth.utils.state_dict_converters.flux_dit.FluxDiTStateDictConverter",
"extra_kwargs": {"disable_guidance_embedder": True},
},
{
# Example: ModelConfig(model_id="MAILAND/majicflus_v1", origin_file_pattern="majicflus_v134.safetensors")
"model_hash": "3394f306c4cbf04334b712bf5aaed95f",
"model_name": "flux_dit",
"model_class": "diffsynth.models.flux_dit.FluxDiT",
"state_dict_converter": "diffsynth.utils.state_dict_converters.flux_dit.FluxDiTStateDictConverter",
},
]
flux2_series = [
{
# Example: ModelConfig(model_id="black-forest-labs/FLUX.2-dev", origin_file_pattern="text_encoder/*.safetensors")
"model_hash": "28fca3d8e5bf2a2d1271748a773f6757",
"model_name": "flux2_text_encoder",
"model_class": "diffsynth.models.flux2_text_encoder.Flux2TextEncoder",
"state_dict_converter": "diffsynth.utils.state_dict_converters.flux2_text_encoder.Flux2TextEncoderStateDictConverter",
},
{
# Example: ModelConfig(model_id="black-forest-labs/FLUX.2-dev", origin_file_pattern="transformer/*.safetensors")
"model_hash": "d38e1d5c5aec3b0a11e79327ac6e3b0f",
"model_name": "flux2_dit",
"model_class": "diffsynth.models.flux2_dit.Flux2DiT",
},
{
# Example: ModelConfig(model_id="black-forest-labs/FLUX.2-dev", origin_file_pattern="vae/diffusion_pytorch_model.safetensors")
"model_hash": "c54288e3ee12ca215898840682337b95",
"model_name": "flux2_vae",
"model_class": "diffsynth.models.flux2_vae.Flux2VAE",
},
{
# Example: ModelConfig(model_id="black-forest-labs/FLUX.2-klein-4B", origin_file_pattern="transformer/*.safetensors")
"model_hash": "3bde7b817fec8143028b6825a63180df",
"model_name": "flux2_dit",
"model_class": "diffsynth.models.flux2_dit.Flux2DiT",
"extra_kwargs": {"guidance_embeds": False, "joint_attention_dim": 7680, "num_attention_heads": 24, "num_layers": 5, "num_single_layers": 20}
},
{
# Example: ModelConfig(model_id="black-forest-labs/FLUX.2-klein-9B", origin_file_pattern="text_encoder/*.safetensors")
"model_hash": "9195f3ea256fcd0ae6d929c203470754",
"model_name": "z_image_text_encoder",
"model_class": "diffsynth.models.z_image_text_encoder.ZImageTextEncoder",
"extra_kwargs": {"model_size": "8B"},
"state_dict_converter": "diffsynth.utils.state_dict_converters.z_image_text_encoder.ZImageTextEncoderStateDictConverter",
},
{
# Example: ModelConfig(model_id="black-forest-labs/FLUX.2-klein-9B", origin_file_pattern="transformer/*.safetensors")
"model_hash": "39c6fc48f07bebecedbbaa971ff466c8",
"model_name": "flux2_dit",
"model_class": "diffsynth.models.flux2_dit.Flux2DiT",
"extra_kwargs": {"guidance_embeds": False, "joint_attention_dim": 12288, "num_attention_heads": 32, "num_layers": 8, "num_single_layers": 24}
},
]
ernie_image_series = [
{
# Example: ModelConfig(model_id="PaddlePaddle/ERNIE-Image", origin_file_pattern="transformer/diffusion_pytorch_model*.safetensors")
"model_hash": "584c13713849f1af4e03d5f1858b8b7b",
"model_name": "ernie_image_dit",
"model_class": "diffsynth.models.ernie_image_dit.ErnieImageDiT",
},
{
# Example: ModelConfig(model_id="PaddlePaddle/ERNIE-Image", origin_file_pattern="text_encoder/model.safetensors")
"model_hash": "404ed9f40796a38dd34c1620f1920207",
"model_name": "ernie_image_text_encoder",
"model_class": "diffsynth.models.ernie_image_text_encoder.ErnieImageTextEncoder",
"state_dict_converter": "diffsynth.utils.state_dict_converters.ernie_image_text_encoder.ErnieImageTextEncoderStateDictConverter",
},
]
z_image_series = [
{
# Example: ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="transformer/*.safetensors")
"model_hash": "fc3a8a1247fe185ce116ccbe0e426c28",
"model_name": "z_image_dit",
"model_class": "diffsynth.models.z_image_dit.ZImageDiT",
},
{
# Example: ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="text_encoder/*.safetensors")
"model_hash": "0f050f62a88876fea6eae0a18dac5a2e",
"model_name": "z_image_text_encoder",
"model_class": "diffsynth.models.z_image_text_encoder.ZImageTextEncoder",
},
{
# Example: ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="vae/vae/diffusion_pytorch_model.safetensors")
"model_hash": "1aafa3cc91716fb6b300cc1cd51b85a3",
"model_name": "flux_vae_encoder",
"model_class": "diffsynth.models.flux_vae.FluxVAEEncoder",
"state_dict_converter": "diffsynth.utils.state_dict_converters.flux_vae.FluxVAEEncoderStateDictConverterDiffusers",
"extra_kwargs": {"use_conv_attention": False},
},
{
# Example: ModelConfig(model_id="Tongyi-MAI/Z-Image-Turbo", origin_file_pattern="vae/vae/diffusion_pytorch_model.safetensors")
"model_hash": "1aafa3cc91716fb6b300cc1cd51b85a3",
"model_name": "flux_vae_decoder",
"model_class": "diffsynth.models.flux_vae.FluxVAEDecoder",
"state_dict_converter": "diffsynth.utils.state_dict_converters.flux_vae.FluxVAEDecoderStateDictConverterDiffusers",
"extra_kwargs": {"use_conv_attention": False},
},
{
# Example: ModelConfig(model_id="Tongyi-MAI/Z-Image-Omni-Base", origin_file_pattern="transformer/*.safetensors")
"model_hash": "aa3563718e5c3ecde3dfbb020ca61180",
"model_name": "z_image_dit",
"model_class": "diffsynth.models.z_image_dit.ZImageDiT",
"extra_kwargs": {"siglip_feat_dim": 1152},
},
{
# Example: ModelConfig(model_id="Tongyi-MAI/Z-Image-Omni-Base", origin_file_pattern="siglip/model.safetensors")
"model_hash": "89d48e420f45cff95115a9f3e698d44a",
"model_name": "siglip_vision_model_428m",
"model_class": "diffsynth.models.siglip2_image_encoder.Siglip2ImageEncoder428M",
},
{
# Example: ModelConfig(model_id="PAI/Z-Image-Turbo-Fun-Controlnet-Union-2.1", origin_file_pattern="Z-Image-Turbo-Fun-Controlnet-Union-2.1-8steps.safetensors")
"model_hash": "1677708d40029ab380a95f6c731a57d7",
"model_name": "z_image_controlnet",
"model_class": "diffsynth.models.z_image_controlnet.ZImageControlNet",
},
{
# Example: ???
"model_hash": "9510cb8cd1dd34ee0e4f111c24905510",
"model_name": "z_image_image2lora_style",
"model_class": "diffsynth.models.z_image_image2lora.ZImageImage2LoRAModel",
"extra_kwargs": {"compress_dim": 128},
},
{
# Example: ModelConfig(model_id="Qwen/Qwen3-0.6B", origin_file_pattern="model.safetensors")
"model_hash": "1392adecee344136041e70553f875f31",
"model_name": "z_image_text_encoder",
"model_class": "diffsynth.models.z_image_text_encoder.ZImageTextEncoder",
"extra_kwargs": {"model_size": "0.6B"},
"state_dict_converter": "diffsynth.utils.state_dict_converters.z_image_text_encoder.ZImageTextEncoderStateDictConverter",
},
{
# To ensure compatibility with the `model.diffusion_model` prefix introduced by other frameworks.
"model_hash": "8cf241a0d32f93d5de368502a086852f",
"model_name": "z_image_dit",
"model_class": "diffsynth.models.z_image_dit.ZImageDiT",
"state_dict_converter": "diffsynth.utils.state_dict_converters.z_image_dit.ZImageDiTStateDictConverter",
},
]
"""
Offical model repo: https://www.modelscope.cn/models/Lightricks/LTX-2
Repackaged model repo: https://www.modelscope.cn/models/DiffSynth-Studio/LTX-2-Repackage
For base models of LTX-2, offical checkpoint (with model config ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-dev.safetensors"))
and repackaged checkpoints (with model config ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="*.safetensors")) are both supported.
We have repackeged the official checkpoints in DiffSynth-Studio/LTX-2-Repackage repo to support separate loading of different submodules,
and avoid redundant memory usage when users only want to use part of the model.
"""
ltx2_series = [
{
# Example: ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-dev.safetensors")
"model_hash": "aca7b0bbf8415e9c98360750268915fc",
"model_name": "ltx2_dit",
"model_class": "diffsynth.models.ltx2_dit.LTXModel",
"state_dict_converter": "diffsynth.utils.state_dict_converters.ltx2_dit.LTXModelStateDictConverter",
},
{
# Example: ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="transformer.safetensors")
"model_hash": "c567aaa37d5ed7454c73aa6024458661",
"model_name": "ltx2_dit",
"model_class": "diffsynth.models.ltx2_dit.LTXModel",
"state_dict_converter": "diffsynth.utils.state_dict_converters.ltx2_dit.LTXModelStateDictConverter",
},
{
# Example: ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-dev.safetensors")
"model_hash": "aca7b0bbf8415e9c98360750268915fc",
"model_name": "ltx2_video_vae_encoder",
"model_class": "diffsynth.models.ltx2_video_vae.LTX2VideoEncoder",
"state_dict_converter": "diffsynth.utils.state_dict_converters.ltx2_video_vae.LTX2VideoEncoderStateDictConverter",
},
{
# Example: ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_encoder.safetensors")
"model_hash": "7f7e904a53260ec0351b05f32153754b",
"model_name": "ltx2_video_vae_encoder",
"model_class": "diffsynth.models.ltx2_video_vae.LTX2VideoEncoder",
"state_dict_converter": "diffsynth.utils.state_dict_converters.ltx2_video_vae.LTX2VideoEncoderStateDictConverter",
},
{
# Example: ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-dev.safetensors")
"model_hash": "aca7b0bbf8415e9c98360750268915fc",
"model_name": "ltx2_video_vae_decoder",
"model_class": "diffsynth.models.ltx2_video_vae.LTX2VideoDecoder",
"state_dict_converter": "diffsynth.utils.state_dict_converters.ltx2_video_vae.LTX2VideoDecoderStateDictConverter",
},
{
# Example: ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="video_vae_decoder.safetensors")
"model_hash": "dc6029ca2825147872b45e35a2dc3a97",
"model_name": "ltx2_video_vae_decoder",
"model_class": "diffsynth.models.ltx2_video_vae.LTX2VideoDecoder",
"state_dict_converter": "diffsynth.utils.state_dict_converters.ltx2_video_vae.LTX2VideoDecoderStateDictConverter",
},
{
# Example: ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-dev.safetensors")
"model_hash": "aca7b0bbf8415e9c98360750268915fc",
"model_name": "ltx2_audio_vae_decoder",
"model_class": "diffsynth.models.ltx2_audio_vae.LTX2AudioDecoder",
"state_dict_converter": "diffsynth.utils.state_dict_converters.ltx2_audio_vae.LTX2AudioDecoderStateDictConverter",
},
{
# Example: ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vae_decoder.safetensors")
"model_hash": "7d7823dde8f1ea0b50fb07ac329dd4cb",
"model_name": "ltx2_audio_vae_decoder",
"model_class": "diffsynth.models.ltx2_audio_vae.LTX2AudioDecoder",
"state_dict_converter": "diffsynth.utils.state_dict_converters.ltx2_audio_vae.LTX2AudioDecoderStateDictConverter",
},
{
# Example: ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-dev.safetensors")
"model_hash": "aca7b0bbf8415e9c98360750268915fc",
"model_name": "ltx2_audio_vocoder",
"model_class": "diffsynth.models.ltx2_audio_vae.LTX2Vocoder",
"state_dict_converter": "diffsynth.utils.state_dict_converters.ltx2_audio_vae.LTX2VocoderStateDictConverter",
},
{
# Example: ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vocoder.safetensors")
"model_hash": "f471360f6b24bef702ab73133d9f8bb9",
"model_name": "ltx2_audio_vocoder",
"model_class": "diffsynth.models.ltx2_audio_vae.LTX2Vocoder",
"state_dict_converter": "diffsynth.utils.state_dict_converters.ltx2_audio_vae.LTX2VocoderStateDictConverter",
},
{
# Example: ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-dev.safetensors")
"model_hash": "aca7b0bbf8415e9c98360750268915fc",
"model_name": "ltx2_audio_vae_encoder",
"model_class": "diffsynth.models.ltx2_audio_vae.LTX2AudioEncoder",
"state_dict_converter": "diffsynth.utils.state_dict_converters.ltx2_audio_vae.LTX2AudioEncoderStateDictConverter",
},
{
# Example: ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="audio_vae_encoder.safetensors")
"model_hash": "29338f3b95e7e312a3460a482e4f4554",
"model_name": "ltx2_audio_vae_encoder",
"model_class": "diffsynth.models.ltx2_audio_vae.LTX2AudioEncoder",
"state_dict_converter": "diffsynth.utils.state_dict_converters.ltx2_audio_vae.LTX2AudioEncoderStateDictConverter",
},
{
# Example: ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-dev.safetensors")
"model_hash": "aca7b0bbf8415e9c98360750268915fc",
"model_name": "ltx2_text_encoder_post_modules",
"model_class": "diffsynth.models.ltx2_text_encoder.LTX2TextEncoderPostModules",
"state_dict_converter": "diffsynth.utils.state_dict_converters.ltx2_text_encoder.LTX2TextEncoderPostModulesStateDictConverter",
},
{
# Example: ModelConfig(model_id="DiffSynth-Studio/LTX-2-Repackage", origin_file_pattern="text_encoder_post_modules.safetensors")
"model_hash": "981629689c8be92a712ab3c5eb4fc3f6",
"model_name": "ltx2_text_encoder_post_modules",
"model_class": "diffsynth.models.ltx2_text_encoder.LTX2TextEncoderPostModules",
"state_dict_converter": "diffsynth.utils.state_dict_converters.ltx2_text_encoder.LTX2TextEncoderPostModulesStateDictConverter",
},
{
# Example: ModelConfig(model_id="google/gemma-3-12b-it-qat-q4_0-unquantized", origin_file_pattern="model-*.safetensors")
"model_hash": "33917f31c4a79196171154cca39f165e",
"model_name": "ltx2_text_encoder",
"model_class": "diffsynth.models.ltx2_text_encoder.LTX2TextEncoder",
"state_dict_converter": "diffsynth.utils.state_dict_converters.ltx2_text_encoder.LTX2TextEncoderStateDictConverter",
},
{
# Example: ModelConfig(model_id="Lightricks/LTX-2", origin_file_pattern="ltx-2-19b-dev.safetensors")
"model_hash": "c79c458c6e99e0e14d47e676761732d2",
"model_name": "ltx2_latent_upsampler",
"model_class": "diffsynth.models.ltx2_upsampler.LTX2LatentUpsampler",
},
{
# Example: ModelConfig(model_id="Lightricks/LTX-2.3", origin_file_pattern="ltx-2.3-22b-dev.safetensors")
"model_hash": "f3a83ecf3995dcc4fae2d27e08ad5767",
"model_name": "ltx2_dit",
"model_class": "diffsynth.models.ltx2_dit.LTXModel",
"extra_kwargs": {"apply_gated_attention": True, "cross_attention_adaln": True, "caption_channels": None},
"state_dict_converter": "diffsynth.utils.state_dict_converters.ltx2_dit.LTXModelStateDictConverter",
},
{
# Example: ModelConfig(model_id="Lightricks/LTX-2.3", origin_file_pattern="ltx-2.3-22b-dev.safetensors")
"model_hash": "f3a83ecf3995dcc4fae2d27e08ad5767",
"model_name": "ltx2_video_vae_encoder",
"model_class": "diffsynth.models.ltx2_video_vae.LTX2VideoEncoder",
"extra_kwargs": {"encoder_version": "ltx-2.3"},
"state_dict_converter": "diffsynth.utils.state_dict_converters.ltx2_video_vae.LTX2VideoEncoderStateDictConverter",
},
{
# Example: ModelConfig(model_id="Lightricks/LTX-2.3", origin_file_pattern="ltx-2.3-22b-dev.safetensors")
"model_hash": "f3a83ecf3995dcc4fae2d27e08ad5767",
"model_name": "ltx2_video_vae_decoder",
"model_class": "diffsynth.models.ltx2_video_vae.LTX2VideoDecoder",
"extra_kwargs": {"decoder_version": "ltx-2.3"},
"state_dict_converter": "diffsynth.utils.state_dict_converters.ltx2_video_vae.LTX2VideoDecoderStateDictConverter",
},
{
# Example: ModelConfig(model_id="Lightricks/LTX-2.3", origin_file_pattern="ltx-2.3-22b-dev.safetensors")
"model_hash": "f3a83ecf3995dcc4fae2d27e08ad5767",
"model_name": "ltx2_audio_vae_decoder",
"model_class": "diffsynth.models.ltx2_audio_vae.LTX2AudioDecoder",
"state_dict_converter": "diffsynth.utils.state_dict_converters.ltx2_audio_vae.LTX2AudioDecoderStateDictConverter",
},
{
# Example: ModelConfig(model_id="Lightricks/LTX-2.3", origin_file_pattern="ltx-2.3-22b-dev.safetensors")
"model_hash": "f3a83ecf3995dcc4fae2d27e08ad5767",
"model_name": "ltx2_audio_vocoder",
"model_class": "diffsynth.models.ltx2_audio_vae.LTX2VocoderWithBWE",
"state_dict_converter": "diffsynth.utils.state_dict_converters.ltx2_audio_vae.LTX2VocoderStateDictConverter",
},
{
# Example: ModelConfig(model_id="Lightricks/LTX-2.3", origin_file_pattern="ltx-2.3-22b-dev.safetensors")
"model_hash": "f3a83ecf3995dcc4fae2d27e08ad5767",
"model_name": "ltx2_audio_vae_encoder",
"model_class": "diffsynth.models.ltx2_audio_vae.LTX2AudioEncoder",
"state_dict_converter": "diffsynth.utils.state_dict_converters.ltx2_audio_vae.LTX2AudioEncoderStateDictConverter",
},
{
# Example: ModelConfig(model_id="Lightricks/LTX-2.3", origin_file_pattern="ltx-2.3-22b-dev.safetensors")
"model_hash": "f3a83ecf3995dcc4fae2d27e08ad5767",
"model_name": "ltx2_text_encoder_post_modules",
"model_class": "diffsynth.models.ltx2_text_encoder.LTX2TextEncoderPostModules",
"extra_kwargs": {"separated_audio_video": True, "embedding_dim_gemma": 3840, "num_layers_gemma": 49, "video_attention_heads": 32, "video_attention_head_dim": 128, "audio_attention_heads": 32, "audio_attention_head_dim": 64, "num_connector_layers": 8, "apply_gated_attention": True},
"state_dict_converter": "diffsynth.utils.state_dict_converters.ltx2_text_encoder.LTX2TextEncoderPostModulesStateDictConverter",
},
{
# Example: ModelConfig(model_id="Lightricks/LTX-2.3", origin_file_pattern="ltx-2.3-spatial-upscaler-x2-1.0.safetensors")
"model_hash": "aed408774d694a2452f69936c32febb5",
"model_name": "ltx2_latent_upsampler",
"model_class": "diffsynth.models.ltx2_upsampler.LTX2LatentUpsampler",
"extra_kwargs": {"rational_resampler": False},
},
{
# Example: ModelConfig(model_id="DiffSynth-Studio/LTX-2.3-Repackage", origin_file_pattern="transformer.safetensors")
"model_hash": "1c55afad76ed33c112a2978550b524d1",
"model_name": "ltx2_dit",
"model_class": "diffsynth.models.ltx2_dit.LTXModel",
"extra_kwargs": {"apply_gated_attention": True, "cross_attention_adaln": True, "caption_channels": None},
"state_dict_converter": "diffsynth.utils.state_dict_converters.ltx2_dit.LTXModelStateDictConverter",
},
{
# Example: ModelConfig(model_id="DiffSynth-Studio/LTX-2.3-Repackage", origin_file_pattern="video_vae_encoder.safetensors")
"model_hash": "eecdc07c2ec30863b8a2b8b2134036cf",
"model_name": "ltx2_video_vae_encoder",
"model_class": "diffsynth.models.ltx2_video_vae.LTX2VideoEncoder",
"extra_kwargs": {"encoder_version": "ltx-2.3"},
"state_dict_converter": "diffsynth.utils.state_dict_converters.ltx2_video_vae.LTX2VideoEncoderStateDictConverter",
},
{
# Example: ModelConfig(model_id="DiffSynth-Studio/LTX-2.3-Repackage", origin_file_pattern="video_vae_decoder.safetensors")
"model_hash": "deda2f542e17ee25bc8c38fd605316ea",
"model_name": "ltx2_video_vae_decoder",
"model_class": "diffsynth.models.ltx2_video_vae.LTX2VideoDecoder",
"extra_kwargs": {"decoder_version": "ltx-2.3"},
"state_dict_converter": "diffsynth.utils.state_dict_converters.ltx2_video_vae.LTX2VideoDecoderStateDictConverter",
},
{
# Example: ModelConfig(model_id="DiffSynth-Studio/LTX-2.3-Repackage", origin_file_pattern="audio_vocoder.safetensors")
"model_hash": "cd436c99e69ec5c80f050f0944f02a15",
"model_name": "ltx2_audio_vocoder",
"model_class": "diffsynth.models.ltx2_audio_vae.LTX2VocoderWithBWE",
"state_dict_converter": "diffsynth.utils.state_dict_converters.ltx2_audio_vae.LTX2VocoderStateDictConverter",
},
{
# Example: ModelConfig(model_id="DiffSynth-Studio/LTX-2.3-Repackage", origin_file_pattern="text_encoder_post_modules.safetensors")
"model_hash": "05da2aab1c4b061f72c426311c165a43",
"model_name": "ltx2_text_encoder_post_modules",
"model_class": "diffsynth.models.ltx2_text_encoder.LTX2TextEncoderPostModules",
"extra_kwargs": {"separated_audio_video": True, "embedding_dim_gemma": 3840, "num_layers_gemma": 49, "video_attention_heads": 32, "video_attention_head_dim": 128, "audio_attention_heads": 32, "audio_attention_head_dim": 64, "num_connector_layers": 8, "apply_gated_attention": True},
"state_dict_converter": "diffsynth.utils.state_dict_converters.ltx2_text_encoder.LTX2TextEncoderPostModulesStateDictConverter",
},
]
anima_series = [
{
# Example: ModelConfig(model_id="circlestone-labs/Anima", origin_file_pattern="split_files/vae/qwen_image_vae.safetensors")
"model_hash": "a9995952c2d8e63cf82e115005eb61b9",
"model_name": "z_image_text_encoder",
"model_class": "diffsynth.models.z_image_text_encoder.ZImageTextEncoder",
"extra_kwargs": {"model_size": "0.6B"},
},
{
# Example: ModelConfig(model_id="circlestone-labs/Anima", origin_file_pattern="split_files/diffusion_models/anima-preview.safetensors")
"model_hash": "417673936471e79e31ed4d186d7a3f4a",
"model_name": "anima_dit",
"model_class": "diffsynth.models.anima_dit.AnimaDiT",
"state_dict_converter": "diffsynth.utils.state_dict_converters.anima_dit.AnimaDiTStateDictConverter",
}
]
mova_series = [
# Example: ModelConfig(model_id="openmoss/MOVA-720p", origin_file_pattern="audio_dit/diffusion_pytorch_model.safetensors")
{
"model_hash": "8c57e12790e2c45a64817e0ce28cde2f",
"model_name": "mova_audio_dit",
"model_class": "diffsynth.models.mova_audio_dit.MovaAudioDit",
"extra_kwargs": {'has_image_input': False, 'patch_size': [1], 'in_dim': 128, 'dim': 1536, 'ffn_dim': 8960, 'freq_dim': 256, 'text_dim': 4096, 'out_dim': 128, 'num_heads': 12, 'num_layers': 30, 'eps': 1e-06}
},
# Example: ModelConfig(model_id="openmoss/MOVA-720p", origin_file_pattern="audio_vae/diffusion_pytorch_model.safetensors")
{
"model_hash": "418517fb2b4e919d2cac8f314fcf82ac",
"model_name": "mova_audio_vae",
"model_class": "diffsynth.models.mova_audio_vae.DacVAE",
},
# Example: ModelConfig(model_id="openmoss/MOVA-720p", origin_file_pattern="dual_tower_bridge/diffusion_pytorch_model.safetensors")
{
"model_hash": "d1139dbbc8b4ab53cf4b4243d57bbceb",
"model_name": "mova_dual_tower_bridge",
"model_class": "diffsynth.models.mova_dual_tower_bridge.DualTowerConditionalBridge",
},
]
stable_diffusion_xl_series = [
{
# Example: ModelConfig(model_id="stabilityai/stable-diffusion-xl-base-1.0", origin_file_pattern="unet/diffusion_pytorch_model.safetensors")
"model_hash": "142b114f67f5ab3a6d83fb5788f12ded",
"model_name": "stable_diffusion_xl_unet",
"model_class": "diffsynth.models.stable_diffusion_xl_unet.SDXLUNet2DConditionModel",
"extra_kwargs": {"attention_head_dim": [5, 10, 20], "transformer_layers_per_block": [1, 2, 10], "use_linear_projection": True, "addition_embed_type": "text_time", "addition_time_embed_dim": 256, "projection_class_embeddings_input_dim": 2816},
},
{
# Example: ModelConfig(model_id="stabilityai/stable-diffusion-xl-base-1.0", origin_file_pattern="text_encoder_2/model.safetensors")
"model_hash": "98cc34ccc5b54ae0e56bdea8688dcd5a",
"model_name": "stable_diffusion_xl_text_encoder",
"model_class": "diffsynth.models.stable_diffusion_xl_text_encoder.SDXLTextEncoder2",
"state_dict_converter": "diffsynth.utils.state_dict_converters.stable_diffusion_xl_text_encoder.SDXLTextEncoder2StateDictConverter",
},
{
# Example: ModelConfig(model_id="stabilityai/stable-diffusion-xl-base-1.0", origin_file_pattern="text_encoder/model.safetensors")
"model_hash": "94eefa3dac9cec93cb1ebaf1747d7b78",
"model_name": "stable_diffusion_text_encoder",
"model_class": "diffsynth.models.stable_diffusion_text_encoder.SDTextEncoder",
"state_dict_converter": "diffsynth.utils.state_dict_converters.stable_diffusion_text_encoder.SDTextEncoderStateDictConverter",
},
{
# Example: ModelConfig(model_id="stabilityai/stable-diffusion-xl-base-1.0", origin_file_pattern="vae/diffusion_pytorch_model.safetensors")
"model_hash": "13115dd45a6e1c39860f91ab073b8a78",
"model_name": "stable_diffusion_xl_vae",
"model_class": "diffsynth.models.stable_diffusion_vae.StableDiffusionVAE",
"state_dict_converter": "diffsynth.utils.state_dict_converters.stable_diffusion_vae.SDVAEStateDictConverter",
"extra_kwargs": {"scaling_factor": 0.13025, "sample_size": 1024, "force_upcast": True},
},
]
stable_diffusion_series = [
{
# Example: ModelConfig(model_id="AI-ModelScope/stable-diffusion-v1-5", origin_file_pattern="text_encoder/model.safetensors")
"model_hash": "ffd1737ae9df7fd43f5fbed653bdad67",
"model_name": "stable_diffusion_text_encoder",
"model_class": "diffsynth.models.stable_diffusion_text_encoder.SDTextEncoder",
"state_dict_converter": "diffsynth.utils.state_dict_converters.stable_diffusion_text_encoder.SDTextEncoderStateDictConverter",
},
{
# Example: ModelConfig(model_id="AI-ModelScope/stable-diffusion-v1-5", origin_file_pattern="vae/diffusion_pytorch_model.safetensors")
"model_hash": "f86d5683ed32433be8ca69969c67ba69",
"model_name": "stable_diffusion_vae",
"model_class": "diffsynth.models.stable_diffusion_vae.StableDiffusionVAE",
"state_dict_converter": "diffsynth.utils.state_dict_converters.stable_diffusion_vae.SDVAEStateDictConverter",
},
{
# Example: ModelConfig(model_id="AI-ModelScope/stable-diffusion-v1-5", origin_file_pattern="unet/diffusion_pytorch_model.safetensors")
"model_hash": "025a4b86a84829399d89f613e580757b",
"model_name": "stable_diffusion_unet",
"model_class": "diffsynth.models.stable_diffusion_unet.UNet2DConditionModel",
},
]
joyai_image_series = [
{
# Example: ModelConfig(model_id="jd-opensource/JoyAI-Image-Edit", origin_file_pattern="transformer/transformer.pth")
"model_hash": "56592ddfd7d0249d3aa527d24161a863",
"model_name": "joyai_image_dit",
"model_class": "diffsynth.models.joyai_image_dit.JoyAIImageDiT",
},
{
# Example: ModelConfig(model_id="jd-opensource/JoyAI-Image-Edit", origin_file_pattern="JoyAI-Image-Und/model-*.safetensors")
# Example: ModelConfig(model_id="DiffSynth-Studio/ImageMetrics", origin_file_pattern="UnifiedReward-Edit-qwen3vl-8b/model-*.safetensors")
"model_hash": "2d11bf14bba8b4e87477c8199a895403",
"model_name": "joyai_image_text_encoder",
"model_class": "diffsynth.models.joyai_image_text_encoder.JoyAIImageTextEncoder",
"state_dict_converter": "diffsynth.utils.state_dict_converters.joyai_image_text_encoder.JoyAIImageTextEncoderStateDictConverter",
},
]
ace_step_series = [
{
# Example: ModelConfig(model_id="ACE-Step/Ace-Step1.5", origin_file_pattern="acestep-v15-turbo/model.safetensors")
"model_hash": "ba29d8bddbb6ace65675f6a757a13c00",
"model_name": "ace_step_dit",
"model_class": "diffsynth.models.ace_step_dit.AceStepDiTModel",
"state_dict_converter": "diffsynth.utils.state_dict_converters.ace_step_dit.AceStepDiTModelStateDictConverter",
},
{
# Example: ModelConfig(model_id="ACE-Step/acestep-v15-xl-base", origin_file_pattern="model-*.safetensors")
"model_hash": "3a28a410c2246f125153ef792d8bc828",
"model_name": "ace_step_dit",
"model_class": "diffsynth.models.ace_step_dit.AceStepDiTModel",
"state_dict_converter": "diffsynth.utils.state_dict_converters.ace_step_dit.AceStepDiTModelStateDictConverter",
"extra_kwargs": {
"hidden_size": 2560,
"intermediate_size": 9728,
"num_hidden_layers": 32,
"num_attention_heads": 32,
"num_key_value_heads": 8,
"head_dim": 128,
"encoder_hidden_size": 2048,
"layer_types": ["sliding_attention", "full_attention"] * 16,
},
},
{
# Example: ModelConfig(model_id="ACE-Step/Ace-Step1.5", origin_file_pattern="acestep-v15-turbo/model.safetensors")
"model_hash": "ba29d8bddbb6ace65675f6a757a13c00",
"model_name": "ace_step_conditioner",
"model_class": "diffsynth.models.ace_step_conditioner.AceStepConditionEncoder",
"state_dict_converter": "diffsynth.utils.state_dict_converters.ace_step_conditioner.AceStepConditionEncoderStateDictConverter",
},
{
# Example: ModelConfig(model_id="ACE-Step/acestep-v15-xl-base", origin_file_pattern="model-*.safetensors")
"model_hash": "3a28a410c2246f125153ef792d8bc828",
"model_name": "ace_step_conditioner",
"model_class": "diffsynth.models.ace_step_conditioner.AceStepConditionEncoder",
"state_dict_converter": "diffsynth.utils.state_dict_converters.ace_step_conditioner.AceStepConditionEncoderStateDictConverter",
},
{
# Example: ModelConfig(model_id="ACE-Step/Ace-Step1.5", origin_file_pattern="Qwen3-Embedding-0.6B/model.safetensors")
"model_hash": "3509bea17b0e8cffc3dd4a15cc7899d0",
"model_name": "ace_step_text_encoder",
"model_class": "diffsynth.models.ace_step_text_encoder.AceStepTextEncoder",
"state_dict_converter": "diffsynth.utils.state_dict_converters.ace_step_text_encoder.AceStepTextEncoderStateDictConverter",
},
{
# Example: ModelConfig(model_id="ACE-Step/Ace-Step1.5", origin_file_pattern="vae/diffusion_pytorch_model.safetensors")
"model_hash": "51420834e54474986a7f4be0e4d6f687",
"model_name": "ace_step_vae",
"model_class": "diffsynth.models.ace_step_vae.AceStepVAE",
},
{
# Example: ModelConfig(model_id="ACE-Step/Ace-Step1.5", origin_file_pattern="acestep-v15-turbo/model.safetensors")
"model_hash": "ba29d8bddbb6ace65675f6a757a13c00",
"model_name": "ace_step_tokenizer",
"model_class": "diffsynth.models.ace_step_tokenizer.AceStepTokenizer",
"state_dict_converter": "diffsynth.utils.state_dict_converters.ace_step_tokenizer.AceStepTokenizerStateDictConverter",
},
{
# Example: ModelConfig(model_id="ACE-Step/acestep-v15-xl-base", origin_file_pattern="model-*.safetensors")
"model_hash": "3a28a410c2246f125153ef792d8bc828",
"model_name": "ace_step_tokenizer",
"model_class": "diffsynth.models.ace_step_tokenizer.AceStepTokenizer",
"state_dict_converter": "diffsynth.utils.state_dict_converters.ace_step_tokenizer.AceStepTokenizerStateDictConverter",
},
{
# Example: ???
"model_hash": "ff74b1806e6a0b52e7bbd1d3df2d26d1",
"model_name": "demucs",
"model_class": "diffsynth.models.demucs.HTDemucs",
},
]
image_metrics_series = [
{
# Example: ModelConfig(model_id="DiffSynth-Studio/ImageMetrics", origin_file_pattern="PickScore/model.safetensors")
# Example: ModelConfig(model_id="DiffSynth-Studio/ImageMetrics", origin_file_pattern="CLIP-ViT-H-14-laion2B-s32B-b79K/model.safetensors")
"model_hash": "b5e2c0bfcbf4085ccdb2feb8f0ba408a",
"model_name": "image_metrics_clip_hf",
"model_class": "diffsynth.models.clip.ImageMetricsCLIPModel",
"state_dict_converter": "diffsynth.utils.state_dict_converters.image_metrics.ImageMetricsCLIPStateDictConverter",
},
{
# Example: ModelConfig(model_id="DiffSynth-Studio/ImageMetrics", origin_file_pattern="HPSv2/model.safetensors")
"model_hash": "f79e72cec8ae5a540cff0304bfb21b00",
"model_name": "image_metrics_hpsv2",
"model_class": "diffsynth.models.clip.ImageMetricsCLIPModel",
"state_dict_converter": "diffsynth.utils.state_dict_converters.image_metrics.ImageMetricsOpenCLIPStateDictConverter",
},
{
# Example: ModelConfig(model_id="DiffSynth-Studio/ImageMetrics", origin_file_pattern="HPSv3/model.safetensors")
"model_hash": "5655d9cde15b759cfeefe7432d7a912c",
"model_name": "image_metrics_hpsv3",
"model_class": "diffsynth.models.hpsv3.HPSv3Qwen2VLRewardModel",
"state_dict_converter": "diffsynth.utils.state_dict_converters.image_metrics.ImageMetricsHPSv3StateDictConverter",
"extra_kwargs": {"vocab_size": 151658, "output_dim": 2, "reward_token": "special", "rm_head_type": "ranknet"},
},
{
# Example: ModelConfig(model_id="DiffSynth-Studio/ImageMetrics", origin_file_pattern="ImageReward/model.safetensors")
"model_hash": "b3cc8e10b76ca98cde653daa5cf63139",
"model_name": "image_metrics_image_reward",
"model_class": "diffsynth.models.image_reward.ImageRewardModel",
"state_dict_converter": "diffsynth.utils.state_dict_converters.image_metrics.ImageMetricsImageRewardStateDictConverter",
},
{
# Example: ModelConfig(model_id="DiffSynth-Studio/ImageMetrics", origin_file_pattern="Aesthetic/model.safetensors")
"model_hash": "306981222ec94302794e07cf676c84cc",
"model_name": "image_metrics_aesthetic",
"model_class": "diffsynth.models.aesthetic.AestheticModel",
"state_dict_converter": "diffsynth.utils.state_dict_converters.image_metrics.ImageMetricsAestheticStateDictConverter",
},
{
# Example: ModelConfig(model_id="DiffSynth-Studio/ImageMetrics", origin_file_pattern="FID/model.safetensors")
"model_hash": "d4e9549be726259b444d1f62db4ce413",
"model_name": "image_metrics_fid_inception",
"model_class": "diffsynth.models.fid.FIDInceptionModel",
"state_dict_converter": "diffsynth.utils.state_dict_converters.image_metrics.ImageMetricsFIDStateDictConverter",
},
{
# Example: ModelConfig(model_id="DiffSynth-Studio/ImageMetrics", origin_file_pattern="BioCLIPv2/open_clip_model.safetensors")
"model_hash": "3a020a3e47afb7c5e21c52f2d0692c09",
"model_name": "image_metrics_bioclip_v2",
"model_class": "diffsynth.models.bioclip.BioCLIPv2Model",
"state_dict_converter": "diffsynth.utils.state_dict_converters.image_metrics.ImageMetricsOpenCLIPStateDictConverter",
},
{
# Example: ModelConfig(model_id="DiffSynth-Studio/ImageMetrics", origin_file_pattern="LPIPS/alexnet.safetensors")
"model_hash": "08a75c660c9b2e775c530a0955857f1f",
"model_name": "image_metrics_lpips_alex",
"model_class": "diffsynth.models.lpips.LPIPSModel",
"extra_kwargs": {"net": "alex"},
},
{
# Example: ModelConfig(model_id="DiffSynth-Studio/ImageMetrics", origin_file_pattern="LPIPS/vgg.safetensors")
"model_hash": "5740953aaa8aba2ecd9b9c23da813591",
"model_name": "image_metrics_lpips_vgg",
"model_class": "diffsynth.models.lpips.LPIPSModel",
"extra_kwargs": {"net": "vgg"},
},
{
# Example: ModelConfig(model_id="DiffSynth-Studio/ImageMetrics", origin_file_pattern="LPIPS/squeezenet.safetensors")
"model_hash": "ff994b70a30599287a332105396d5004",
"model_name": "image_metrics_lpips_squeeze",
"model_class": "diffsynth.models.lpips.LPIPSModel",
"extra_kwargs": {"net": "squeeze"},
},
{
# Example: ModelConfig(model_id="DiffSynth-Studio/ImageMetrics", origin_file_pattern="UnifiedReward-2.0-qwen35-9b/model-*.safetensors")
"model_hash": "f9786d06eca5c0f1ece89843b2c4cc66",
"model_name": "image_metrics_unified_reward_2",
"model_class": "diffsynth.models.unified_reward_2.UnifiedReward2Qwen35ForConditionalGeneration",
"state_dict_converter": "diffsynth.utils.state_dict_converters.image_metrics.ImageMetricsUnifiedRewardStateDictConverter",
"extra_kwargs": {"variant": "qwen35_9b"},
},
{
# Example: ModelConfig(model_id="DiffSynth-Studio/ImageMetrics", origin_file_pattern="Qwen-Image-Bench/model-*.safetensors")
"model_hash": "ff4ad0463675e96738483611f6dd551b",
"model_name": "image_metrics_qwen_image_bench",
"model_class": "diffsynth.models.qwen_image_bench.QwenImageBenchQwen35ForConditionalGeneration",
"state_dict_converter": "diffsynth.utils.state_dict_converters.image_metrics.ImageMetricsUnifiedRewardStateDictConverter",
"extra_kwargs": {"variant": "qwen35"},
},
]
hidream_o1_image_series = [
{
# Example: ModelConfig(model_id="HiDream-ai/HiDream-O1-Image", origin_file_pattern="model-*.safetensors")
"model_hash": "58a7c1073d79556bfc61e05e6061b771",
"model_name": "hidream_o1_image_dit",
"model_class": "diffsynth.models.hidream_o1_image_dit.HiDreamO1ImageModel",
},
]
ideogram4_series = [
{
# Example: ModelConfig(model_id="ideogram-ai/ideogram-4-fp8", origin_file_pattern="transformer/diffusion_pytorch_model.safetensors")
"model_hash": "6f56a1d28667f2ff98e1c79af88a7516",
"model_name": "ideogram4_dit",
"model_class": "diffsynth.models.ideogram4_dit.Ideogram4DiT",
"extra_kwargs": {"config": {"emb_dim": 4608, "num_layers": 34, "num_heads": 18, "intermediate_size": 12288, "adanln_dim": 512, "in_channels": 128, "llm_features_dim": 53248, "rope_theta": 5000000, "mrope_section": [24, 20, 20], "norm_eps": 1e-05}, "keep_original_dtype": True},
},
{
# Example: ModelConfig(model_id="ideogram-ai/ideogram-4-fp8", origin_file_pattern="text_encoder/model.safetensors")
"model_hash": "6d72a86d1027baff87e2cf8fc523aab1",
"model_name": "ideogram4_text_encoder",
"model_class": "diffsynth.models.ideogram4_text_encoder.Ideogram4TextEncoder",
"extra_kwargs": {"keep_original_dtype": True},
},
{
# Example: ModelConfig(model_id="DiffSynth-Studio/ideogram-4-bf16-repackage", origin_file_pattern="transformer/diffusion_pytorch_model.safetensors")
"model_hash": "291b300b11c8c8e11978bd85a9c5f80c",
"model_name": "ideogram4_dit",
"model_class": "diffsynth.models.ideogram4_dit.Ideogram4DiT",
"extra_kwargs": {"config": {"emb_dim": 4608, "num_layers": 34, "num_heads": 18, "intermediate_size": 12288, "adanln_dim": 512, "in_channels": 128, "llm_features_dim": 53248, "rope_theta": 5000000, "mrope_section": [24, 20, 20], "norm_eps": 1e-05}},
},
{
# Example: ModelConfig(model_id="ideogram-ai/ideogram-4-fp8", origin_file_pattern="text_encoder/model.safetensors")
"model_hash": "6a269892c0757aacd46bd41b8d5a7aef",
"model_name": "ideogram4_text_encoder",
"model_class": "diffsynth.models.ideogram4_text_encoder.Ideogram4TextEncoder",
},
]
MODEL_CONFIGS = (
stable_diffusion_xl_series + stable_diffusion_series + qwen_image_series + wan_series + flux_series + flux2_series + ernie_image_series
+ z_image_series + ltx2_series + anima_series + mova_series + joyai_image_series + ace_step_series + hidream_o1_image_series
+ image_metrics_series + ideogram4_series
)
|