Hugging Face's logo

Spaces:
acvlab
/
FantasyTalking
Running on Zero

App Files Community
1
FantasyTalking
File size: 40,013 Bytes 
282b272
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
 
from typing_extensions import Literal, TypeAlias

from ..models.wan_video_dit import WanModel
from ..models.wan_video_text_encoder import WanTextEncoder
from ..models.wan_video_image_encoder import WanImageEncoder
from ..models.wan_video_vae import WanVideoVAE


model_loader_configs = [
    # These configs are provided for detecting model type automatically.
    # The format is (state_dict_keys_hash, state_dict_keys_hash_with_shape, model_names, model_classes, model_resource)
    (None, "9269f8db9040a9d860eaca435be61814", ["wan_video_dit"], [WanModel], "civitai"),
    (None, "aafcfd9672c3a2456dc46e1cb6e52c70", ["wan_video_dit"], [WanModel], "civitai"),
    (None, "6bfcfb3b342cb286ce886889d519a77e", ["wan_video_dit"], [WanModel], "civitai"),
    (None, "9c8818c2cbea55eca56c7b447df170da", ["wan_video_text_encoder"], [WanTextEncoder], "civitai"),
    (None, "5941c53e207d62f20f9025686193c40b", ["wan_video_image_encoder"], [WanImageEncoder], "civitai"),
    (None, "1378ea763357eea97acdef78e65d6d96", ["wan_video_vae"], [WanVideoVAE], "civitai"),
    (None, "ccc42284ea13e1ad04693284c7a09be6", ["wan_video_vae"], [WanVideoVAE], "civitai"),
]
huggingface_model_loader_configs = [
    # These configs are provided for detecting model type automatically.
    # The format is (architecture_in_huggingface_config, huggingface_lib, model_name, redirected_architecture)
    ("ChatGLMModel", "diffsynth.models.kolors_text_encoder", "kolors_text_encoder", None),
    ("MarianMTModel", "transformers.models.marian.modeling_marian", "translator", None),
    ("BloomForCausalLM", "transformers.models.bloom.modeling_bloom", "beautiful_prompt", None),
    ("Qwen2ForCausalLM", "transformers.models.qwen2.modeling_qwen2", "qwen_prompt", None),
    # ("LlamaForCausalLM", "transformers.models.llama.modeling_llama", "omost_prompt", None),
    ("T5EncoderModel", "diffsynth.models.flux_text_encoder", "flux_text_encoder_2", "FluxTextEncoder2"),
    ("CogVideoXTransformer3DModel", "diffsynth.models.cog_dit", "cog_dit", "CogDiT"),
    ("SiglipModel", "transformers.models.siglip.modeling_siglip", "siglip_vision_model", "SiglipVisionModel"),
    ("LlamaForCausalLM", "diffsynth.models.hunyuan_video_text_encoder", "hunyuan_video_text_encoder_2", "HunyuanVideoLLMEncoder"),
    ("Step1Model", "diffsynth.models.stepvideo_text_encoder", "stepvideo_text_encoder_2", "STEP1TextEncoder"),
]
patch_model_loader_configs = [
    # These configs are provided for detecting model type automatically.
    # The format is (state_dict_keys_hash_with_shape, model_name, model_class, extra_kwargs)
    # ("9a4ab6869ac9b7d6e31f9854e397c867", ["svd_unet"], [SVDUNet], {"add_positional_conv": 128}),
]

preset_models_on_huggingface = {
    "HunyuanDiT": [
        ("Tencent-Hunyuan/HunyuanDiT", "t2i/clip_text_encoder/pytorch_model.bin", "models/HunyuanDiT/t2i/clip_text_encoder"),
        ("Tencent-Hunyuan/HunyuanDiT", "t2i/mt5/pytorch_model.bin", "models/HunyuanDiT/t2i/mt5"),
        ("Tencent-Hunyuan/HunyuanDiT", "t2i/model/pytorch_model_ema.pt", "models/HunyuanDiT/t2i/model"),
        ("Tencent-Hunyuan/HunyuanDiT", "t2i/sdxl-vae-fp16-fix/diffusion_pytorch_model.bin", "models/HunyuanDiT/t2i/sdxl-vae-fp16-fix"),
    ],
    "stable-video-diffusion-img2vid-xt": [
        ("stabilityai/stable-video-diffusion-img2vid-xt", "svd_xt.safetensors", "models/stable_video_diffusion"),
    ],
    "ExVideo-SVD-128f-v1": [
        ("ECNU-CILab/ExVideo-SVD-128f-v1", "model.fp16.safetensors", "models/stable_video_diffusion"),
    ],
    # Stable Diffusion
    "StableDiffusion_v15": [
        ("benjamin-paine/stable-diffusion-v1-5", "v1-5-pruned-emaonly.safetensors", "models/stable_diffusion"),
    ],
    "DreamShaper_8": [
        ("Yntec/Dreamshaper8", "dreamshaper_8.safetensors", "models/stable_diffusion"),
    ],
    # Textual Inversion
    "TextualInversion_VeryBadImageNegative_v1.3": [
        ("gemasai/verybadimagenegative_v1.3", "verybadimagenegative_v1.3.pt", "models/textual_inversion"),
    ],
    # Stable Diffusion XL
    "StableDiffusionXL_v1": [
        ("stabilityai/stable-diffusion-xl-base-1.0", "sd_xl_base_1.0.safetensors", "models/stable_diffusion_xl"),
    ],
    "BluePencilXL_v200": [
        ("frankjoshua/bluePencilXL_v200", "bluePencilXL_v200.safetensors", "models/stable_diffusion_xl"),
    ],
    "StableDiffusionXL_Turbo": [
        ("stabilityai/sdxl-turbo", "sd_xl_turbo_1.0_fp16.safetensors", "models/stable_diffusion_xl_turbo"),
    ],
    # Stable Diffusion 3
    "StableDiffusion3": [
        ("stabilityai/stable-diffusion-3-medium", "sd3_medium_incl_clips_t5xxlfp16.safetensors", "models/stable_diffusion_3"),
    ],
    "StableDiffusion3_without_T5": [
        ("stabilityai/stable-diffusion-3-medium", "sd3_medium_incl_clips.safetensors", "models/stable_diffusion_3"),
    ],
    # ControlNet
    "ControlNet_v11f1p_sd15_depth": [
        ("lllyasviel/ControlNet-v1-1", "control_v11f1p_sd15_depth.pth", "models/ControlNet"),
        ("lllyasviel/Annotators", "dpt_hybrid-midas-501f0c75.pt", "models/Annotators")
    ],
    "ControlNet_v11p_sd15_softedge": [
        ("lllyasviel/ControlNet-v1-1", "control_v11p_sd15_softedge.pth", "models/ControlNet"),
        ("lllyasviel/Annotators", "ControlNetHED.pth", "models/Annotators")
    ],
    "ControlNet_v11f1e_sd15_tile": [
        ("lllyasviel/ControlNet-v1-1", "control_v11f1e_sd15_tile.pth", "models/ControlNet")
    ],
    "ControlNet_v11p_sd15_lineart": [
        ("lllyasviel/ControlNet-v1-1", "control_v11p_sd15_lineart.pth", "models/ControlNet"),
        ("lllyasviel/Annotators", "sk_model.pth", "models/Annotators"),
        ("lllyasviel/Annotators", "sk_model2.pth", "models/Annotators")
    ],
    "ControlNet_union_sdxl_promax": [
        ("xinsir/controlnet-union-sdxl-1.0", "diffusion_pytorch_model_promax.safetensors", "models/ControlNet/controlnet_union"),
        ("lllyasviel/Annotators", "dpt_hybrid-midas-501f0c75.pt", "models/Annotators")
    ],
    # AnimateDiff
    "AnimateDiff_v2": [
        ("guoyww/animatediff", "mm_sd_v15_v2.ckpt", "models/AnimateDiff"),
    ],
    "AnimateDiff_xl_beta": [
        ("guoyww/animatediff", "mm_sdxl_v10_beta.ckpt", "models/AnimateDiff"),
    ],

    # Qwen Prompt
    "QwenPrompt": [
        ("Qwen/Qwen2-1.5B-Instruct", "config.json", "models/QwenPrompt/qwen2-1.5b-instruct"),
        ("Qwen/Qwen2-1.5B-Instruct", "generation_config.json", "models/QwenPrompt/qwen2-1.5b-instruct"),
        ("Qwen/Qwen2-1.5B-Instruct", "model.safetensors", "models/QwenPrompt/qwen2-1.5b-instruct"),
        ("Qwen/Qwen2-1.5B-Instruct", "special_tokens_map.json", "models/QwenPrompt/qwen2-1.5b-instruct"),
        ("Qwen/Qwen2-1.5B-Instruct", "tokenizer.json", "models/QwenPrompt/qwen2-1.5b-instruct"),
        ("Qwen/Qwen2-1.5B-Instruct", "tokenizer_config.json", "models/QwenPrompt/qwen2-1.5b-instruct"),
        ("Qwen/Qwen2-1.5B-Instruct", "merges.txt", "models/QwenPrompt/qwen2-1.5b-instruct"),
        ("Qwen/Qwen2-1.5B-Instruct", "vocab.json", "models/QwenPrompt/qwen2-1.5b-instruct"),
    ],
    # Beautiful Prompt
    "BeautifulPrompt": [
        ("alibaba-pai/pai-bloom-1b1-text2prompt-sd", "config.json", "models/BeautifulPrompt/pai-bloom-1b1-text2prompt-sd"),
        ("alibaba-pai/pai-bloom-1b1-text2prompt-sd", "generation_config.json", "models/BeautifulPrompt/pai-bloom-1b1-text2prompt-sd"),
        ("alibaba-pai/pai-bloom-1b1-text2prompt-sd", "model.safetensors", "models/BeautifulPrompt/pai-bloom-1b1-text2prompt-sd"),
        ("alibaba-pai/pai-bloom-1b1-text2prompt-sd", "special_tokens_map.json", "models/BeautifulPrompt/pai-bloom-1b1-text2prompt-sd"),
        ("alibaba-pai/pai-bloom-1b1-text2prompt-sd", "tokenizer.json", "models/BeautifulPrompt/pai-bloom-1b1-text2prompt-sd"),
        ("alibaba-pai/pai-bloom-1b1-text2prompt-sd", "tokenizer_config.json", "models/BeautifulPrompt/pai-bloom-1b1-text2prompt-sd"),
    ],
    # Omost prompt
    "OmostPrompt":[
        ("lllyasviel/omost-llama-3-8b-4bits", "model-00001-of-00002.safetensors", "models/OmostPrompt/omost-llama-3-8b-4bits"),
        ("lllyasviel/omost-llama-3-8b-4bits", "model-00002-of-00002.safetensors", "models/OmostPrompt/omost-llama-3-8b-4bits"),
        ("lllyasviel/omost-llama-3-8b-4bits", "tokenizer.json", "models/OmostPrompt/omost-llama-3-8b-4bits"),
        ("lllyasviel/omost-llama-3-8b-4bits", "tokenizer_config.json", "models/OmostPrompt/omost-llama-3-8b-4bits"),  
        ("lllyasviel/omost-llama-3-8b-4bits", "config.json", "models/OmostPrompt/omost-llama-3-8b-4bits"),
        ("lllyasviel/omost-llama-3-8b-4bits", "generation_config.json", "models/OmostPrompt/omost-llama-3-8b-4bits"),
        ("lllyasviel/omost-llama-3-8b-4bits", "model.safetensors.index.json", "models/OmostPrompt/omost-llama-3-8b-4bits"),
        ("lllyasviel/omost-llama-3-8b-4bits", "special_tokens_map.json", "models/OmostPrompt/omost-llama-3-8b-4bits"),
    ],
    # Translator
    "opus-mt-zh-en": [
        ("Helsinki-NLP/opus-mt-zh-en", "config.json", "models/translator/opus-mt-zh-en"),
        ("Helsinki-NLP/opus-mt-zh-en", "generation_config.json", "models/translator/opus-mt-zh-en"),
        ("Helsinki-NLP/opus-mt-zh-en", "metadata.json", "models/translator/opus-mt-zh-en"),
        ("Helsinki-NLP/opus-mt-zh-en", "pytorch_model.bin", "models/translator/opus-mt-zh-en"),
        ("Helsinki-NLP/opus-mt-zh-en", "source.spm", "models/translator/opus-mt-zh-en"),
        ("Helsinki-NLP/opus-mt-zh-en", "target.spm", "models/translator/opus-mt-zh-en"),
        ("Helsinki-NLP/opus-mt-zh-en", "tokenizer_config.json", "models/translator/opus-mt-zh-en"),
        ("Helsinki-NLP/opus-mt-zh-en", "vocab.json", "models/translator/opus-mt-zh-en"),
    ],
    # IP-Adapter
    "IP-Adapter-SD": [
        ("h94/IP-Adapter", "models/image_encoder/model.safetensors", "models/IpAdapter/stable_diffusion/image_encoder"),
        ("h94/IP-Adapter", "models/ip-adapter_sd15.bin", "models/IpAdapter/stable_diffusion"),
    ],
    "IP-Adapter-SDXL": [
        ("h94/IP-Adapter", "sdxl_models/image_encoder/model.safetensors", "models/IpAdapter/stable_diffusion_xl/image_encoder"),
        ("h94/IP-Adapter", "sdxl_models/ip-adapter_sdxl.bin", "models/IpAdapter/stable_diffusion_xl"),
    ],
    "SDXL-vae-fp16-fix": [
        ("madebyollin/sdxl-vae-fp16-fix", "diffusion_pytorch_model.safetensors", "models/sdxl-vae-fp16-fix")
    ],
    # Kolors
    "Kolors": [
        ("Kwai-Kolors/Kolors", "text_encoder/config.json", "models/kolors/Kolors/text_encoder"),
        ("Kwai-Kolors/Kolors", "text_encoder/pytorch_model.bin.index.json", "models/kolors/Kolors/text_encoder"),
        ("Kwai-Kolors/Kolors", "text_encoder/pytorch_model-00001-of-00007.bin", "models/kolors/Kolors/text_encoder"),
        ("Kwai-Kolors/Kolors", "text_encoder/pytorch_model-00002-of-00007.bin", "models/kolors/Kolors/text_encoder"),
        ("Kwai-Kolors/Kolors", "text_encoder/pytorch_model-00003-of-00007.bin", "models/kolors/Kolors/text_encoder"),
        ("Kwai-Kolors/Kolors", "text_encoder/pytorch_model-00004-of-00007.bin", "models/kolors/Kolors/text_encoder"),
        ("Kwai-Kolors/Kolors", "text_encoder/pytorch_model-00005-of-00007.bin", "models/kolors/Kolors/text_encoder"),
        ("Kwai-Kolors/Kolors", "text_encoder/pytorch_model-00006-of-00007.bin", "models/kolors/Kolors/text_encoder"),
        ("Kwai-Kolors/Kolors", "text_encoder/pytorch_model-00007-of-00007.bin", "models/kolors/Kolors/text_encoder"),
        ("Kwai-Kolors/Kolors", "unet/diffusion_pytorch_model.safetensors", "models/kolors/Kolors/unet"),
        ("Kwai-Kolors/Kolors", "vae/diffusion_pytorch_model.safetensors", "models/kolors/Kolors/vae"),
    ],
    # FLUX
    "FLUX.1-dev": [
        ("black-forest-labs/FLUX.1-dev", "text_encoder/model.safetensors", "models/FLUX/FLUX.1-dev/text_encoder"),
        ("black-forest-labs/FLUX.1-dev", "text_encoder_2/config.json", "models/FLUX/FLUX.1-dev/text_encoder_2"),
        ("black-forest-labs/FLUX.1-dev", "text_encoder_2/model-00001-of-00002.safetensors", "models/FLUX/FLUX.1-dev/text_encoder_2"),
        ("black-forest-labs/FLUX.1-dev", "text_encoder_2/model-00002-of-00002.safetensors", "models/FLUX/FLUX.1-dev/text_encoder_2"),
        ("black-forest-labs/FLUX.1-dev", "text_encoder_2/model.safetensors.index.json", "models/FLUX/FLUX.1-dev/text_encoder_2"),
        ("black-forest-labs/FLUX.1-dev", "ae.safetensors", "models/FLUX/FLUX.1-dev"),
        ("black-forest-labs/FLUX.1-dev", "flux1-dev.safetensors", "models/FLUX/FLUX.1-dev"),
    ],
    "InstantX/FLUX.1-dev-IP-Adapter": {
        "file_list": [
            ("InstantX/FLUX.1-dev-IP-Adapter", "ip-adapter.bin", "models/IpAdapter/InstantX/FLUX.1-dev-IP-Adapter"),
            ("google/siglip-so400m-patch14-384", "model.safetensors", "models/IpAdapter/InstantX/FLUX.1-dev-IP-Adapter/image_encoder"),
            ("google/siglip-so400m-patch14-384", "config.json", "models/IpAdapter/InstantX/FLUX.1-dev-IP-Adapter/image_encoder"),
        ],
        "load_path": [
            "models/IpAdapter/InstantX/FLUX.1-dev-IP-Adapter/ip-adapter.bin",
            "models/IpAdapter/InstantX/FLUX.1-dev-IP-Adapter/image_encoder",
        ],
    },
    # RIFE
    "RIFE": [
        ("AlexWortega/RIFE", "flownet.pkl", "models/RIFE"),
    ],
    # CogVideo
    "CogVideoX-5B": [
        ("THUDM/CogVideoX-5b", "text_encoder/config.json", "models/CogVideo/CogVideoX-5b/text_encoder"),
        ("THUDM/CogVideoX-5b", "text_encoder/model.safetensors.index.json", "models/CogVideo/CogVideoX-5b/text_encoder"),
        ("THUDM/CogVideoX-5b", "text_encoder/model-00001-of-00002.safetensors", "models/CogVideo/CogVideoX-5b/text_encoder"),
        ("THUDM/CogVideoX-5b", "text_encoder/model-00002-of-00002.safetensors", "models/CogVideo/CogVideoX-5b/text_encoder"),
        ("THUDM/CogVideoX-5b", "transformer/config.json", "models/CogVideo/CogVideoX-5b/transformer"),
        ("THUDM/CogVideoX-5b", "transformer/diffusion_pytorch_model.safetensors.index.json", "models/CogVideo/CogVideoX-5b/transformer"),
        ("THUDM/CogVideoX-5b", "transformer/diffusion_pytorch_model-00001-of-00002.safetensors", "models/CogVideo/CogVideoX-5b/transformer"),
        ("THUDM/CogVideoX-5b", "transformer/diffusion_pytorch_model-00002-of-00002.safetensors", "models/CogVideo/CogVideoX-5b/transformer"),
        ("THUDM/CogVideoX-5b", "vae/diffusion_pytorch_model.safetensors", "models/CogVideo/CogVideoX-5b/vae"),
    ],
    # Stable Diffusion 3.5
    "StableDiffusion3.5-large": [
        ("stabilityai/stable-diffusion-3.5-large", "sd3.5_large.safetensors", "models/stable_diffusion_3"),
        ("stabilityai/stable-diffusion-3.5-large", "text_encoders/clip_l.safetensors", "models/stable_diffusion_3/text_encoders"),
        ("stabilityai/stable-diffusion-3.5-large", "text_encoders/clip_g.safetensors", "models/stable_diffusion_3/text_encoders"),
        ("stabilityai/stable-diffusion-3.5-large", "text_encoders/t5xxl_fp16.safetensors", "models/stable_diffusion_3/text_encoders"),
    ],
}
preset_models_on_modelscope = {
    # Hunyuan DiT
    "HunyuanDiT": [
        ("modelscope/HunyuanDiT", "t2i/clip_text_encoder/pytorch_model.bin", "models/HunyuanDiT/t2i/clip_text_encoder"),
        ("modelscope/HunyuanDiT", "t2i/mt5/pytorch_model.bin", "models/HunyuanDiT/t2i/mt5"),
        ("modelscope/HunyuanDiT", "t2i/model/pytorch_model_ema.pt", "models/HunyuanDiT/t2i/model"),
        ("modelscope/HunyuanDiT", "t2i/sdxl-vae-fp16-fix/diffusion_pytorch_model.bin", "models/HunyuanDiT/t2i/sdxl-vae-fp16-fix"),
    ],
    # Stable Video Diffusion
    "stable-video-diffusion-img2vid-xt": [
        ("AI-ModelScope/stable-video-diffusion-img2vid-xt", "svd_xt.safetensors", "models/stable_video_diffusion"),
    ],
    # ExVideo
    "ExVideo-SVD-128f-v1": [
        ("ECNU-CILab/ExVideo-SVD-128f-v1", "model.fp16.safetensors", "models/stable_video_diffusion"),
    ],
    "ExVideo-CogVideoX-LoRA-129f-v1": [
        ("ECNU-CILab/ExVideo-CogVideoX-LoRA-129f-v1", "ExVideo-CogVideoX-LoRA-129f-v1.safetensors", "models/lora"),
    ],
    # Stable Diffusion
    "StableDiffusion_v15": [
        ("AI-ModelScope/stable-diffusion-v1-5", "v1-5-pruned-emaonly.safetensors", "models/stable_diffusion"),
    ],
    "DreamShaper_8": [
        ("sd_lora/dreamshaper_8", "dreamshaper_8.safetensors", "models/stable_diffusion"),
    ],
    "AingDiffusion_v12": [
        ("sd_lora/aingdiffusion_v12", "aingdiffusion_v12.safetensors", "models/stable_diffusion"),
    ],
    "Flat2DAnimerge_v45Sharp": [
        ("sd_lora/Flat-2D-Animerge", "flat2DAnimerge_v45Sharp.safetensors", "models/stable_diffusion"),
    ],
    # Textual Inversion
    "TextualInversion_VeryBadImageNegative_v1.3": [
        ("sd_lora/verybadimagenegative_v1.3", "verybadimagenegative_v1.3.pt", "models/textual_inversion"),
    ],
    # Stable Diffusion XL
    "StableDiffusionXL_v1": [
        ("AI-ModelScope/stable-diffusion-xl-base-1.0", "sd_xl_base_1.0.safetensors", "models/stable_diffusion_xl"),
    ],
    "BluePencilXL_v200": [
        ("sd_lora/bluePencilXL_v200", "bluePencilXL_v200.safetensors", "models/stable_diffusion_xl"),
    ],
    "StableDiffusionXL_Turbo": [
        ("AI-ModelScope/sdxl-turbo", "sd_xl_turbo_1.0_fp16.safetensors", "models/stable_diffusion_xl_turbo"),
    ],
    "SDXL_lora_zyd232_ChineseInkStyle_SDXL_v1_0": [
        ("sd_lora/zyd232_ChineseInkStyle_SDXL_v1_0", "zyd232_ChineseInkStyle_SDXL_v1_0.safetensors", "models/lora"),
    ],
    # Stable Diffusion 3
    "StableDiffusion3": [
        ("AI-ModelScope/stable-diffusion-3-medium", "sd3_medium_incl_clips_t5xxlfp16.safetensors", "models/stable_diffusion_3"),
    ],
    "StableDiffusion3_without_T5": [
        ("AI-ModelScope/stable-diffusion-3-medium", "sd3_medium_incl_clips.safetensors", "models/stable_diffusion_3"),
    ],
    # ControlNet
    "ControlNet_v11f1p_sd15_depth": [
        ("AI-ModelScope/ControlNet-v1-1", "control_v11f1p_sd15_depth.pth", "models/ControlNet"),
        ("sd_lora/Annotators", "dpt_hybrid-midas-501f0c75.pt", "models/Annotators")
    ],
    "ControlNet_v11p_sd15_softedge": [
        ("AI-ModelScope/ControlNet-v1-1", "control_v11p_sd15_softedge.pth", "models/ControlNet"),
        ("sd_lora/Annotators", "ControlNetHED.pth", "models/Annotators")
    ],
    "ControlNet_v11f1e_sd15_tile": [
        ("AI-ModelScope/ControlNet-v1-1", "control_v11f1e_sd15_tile.pth", "models/ControlNet")
    ],
    "ControlNet_v11p_sd15_lineart": [
        ("AI-ModelScope/ControlNet-v1-1", "control_v11p_sd15_lineart.pth", "models/ControlNet"),
        ("sd_lora/Annotators", "sk_model.pth", "models/Annotators"),
        ("sd_lora/Annotators", "sk_model2.pth", "models/Annotators")
    ],
    "ControlNet_union_sdxl_promax": [
        ("AI-ModelScope/controlnet-union-sdxl-1.0", "diffusion_pytorch_model_promax.safetensors", "models/ControlNet/controlnet_union"),
        ("sd_lora/Annotators", "dpt_hybrid-midas-501f0c75.pt", "models/Annotators")
    ],
    "Annotators:Depth": [
        ("sd_lora/Annotators", "dpt_hybrid-midas-501f0c75.pt", "models/Annotators"),
    ],
    "Annotators:Softedge": [
        ("sd_lora/Annotators", "ControlNetHED.pth", "models/Annotators"),
    ],
    "Annotators:Lineart": [
        ("sd_lora/Annotators", "sk_model.pth", "models/Annotators"),
        ("sd_lora/Annotators", "sk_model2.pth", "models/Annotators"),
    ],
    "Annotators:Normal": [
        ("sd_lora/Annotators", "scannet.pt", "models/Annotators"),
    ],
    "Annotators:Openpose": [
        ("sd_lora/Annotators", "body_pose_model.pth", "models/Annotators"),
        ("sd_lora/Annotators", "facenet.pth", "models/Annotators"),
        ("sd_lora/Annotators", "hand_pose_model.pth", "models/Annotators"),
    ],
    # AnimateDiff
    "AnimateDiff_v2": [
        ("Shanghai_AI_Laboratory/animatediff", "mm_sd_v15_v2.ckpt", "models/AnimateDiff"),
    ],
    "AnimateDiff_xl_beta": [
        ("Shanghai_AI_Laboratory/animatediff", "mm_sdxl_v10_beta.ckpt", "models/AnimateDiff"),
    ],
    # RIFE
    "RIFE": [
        ("Damo_XR_Lab/cv_rife_video-frame-interpolation", "flownet.pkl", "models/RIFE"),
    ],
    # Qwen Prompt
    "QwenPrompt": {
        "file_list": [
            ("qwen/Qwen2-1.5B-Instruct", "config.json", "models/QwenPrompt/qwen2-1.5b-instruct"),
            ("qwen/Qwen2-1.5B-Instruct", "generation_config.json", "models/QwenPrompt/qwen2-1.5b-instruct"),
            ("qwen/Qwen2-1.5B-Instruct", "model.safetensors", "models/QwenPrompt/qwen2-1.5b-instruct"),
            ("qwen/Qwen2-1.5B-Instruct", "special_tokens_map.json", "models/QwenPrompt/qwen2-1.5b-instruct"),
            ("qwen/Qwen2-1.5B-Instruct", "tokenizer.json", "models/QwenPrompt/qwen2-1.5b-instruct"),
            ("qwen/Qwen2-1.5B-Instruct", "tokenizer_config.json", "models/QwenPrompt/qwen2-1.5b-instruct"),
            ("qwen/Qwen2-1.5B-Instruct", "merges.txt", "models/QwenPrompt/qwen2-1.5b-instruct"),
            ("qwen/Qwen2-1.5B-Instruct", "vocab.json", "models/QwenPrompt/qwen2-1.5b-instruct"),
        ],
        "load_path": [
            "models/QwenPrompt/qwen2-1.5b-instruct",
        ],
    },
    # Beautiful Prompt
    "BeautifulPrompt": {
        "file_list": [
            ("AI-ModelScope/pai-bloom-1b1-text2prompt-sd", "config.json", "models/BeautifulPrompt/pai-bloom-1b1-text2prompt-sd"),
            ("AI-ModelScope/pai-bloom-1b1-text2prompt-sd", "generation_config.json", "models/BeautifulPrompt/pai-bloom-1b1-text2prompt-sd"),
            ("AI-ModelScope/pai-bloom-1b1-text2prompt-sd", "model.safetensors", "models/BeautifulPrompt/pai-bloom-1b1-text2prompt-sd"),
            ("AI-ModelScope/pai-bloom-1b1-text2prompt-sd", "special_tokens_map.json", "models/BeautifulPrompt/pai-bloom-1b1-text2prompt-sd"),
            ("AI-ModelScope/pai-bloom-1b1-text2prompt-sd", "tokenizer.json", "models/BeautifulPrompt/pai-bloom-1b1-text2prompt-sd"),
            ("AI-ModelScope/pai-bloom-1b1-text2prompt-sd", "tokenizer_config.json", "models/BeautifulPrompt/pai-bloom-1b1-text2prompt-sd"),
        ],
        "load_path": [
            "models/BeautifulPrompt/pai-bloom-1b1-text2prompt-sd",
        ],
    },
    # Omost prompt
    "OmostPrompt": {
        "file_list": [
            ("Omost/omost-llama-3-8b-4bits", "model-00001-of-00002.safetensors", "models/OmostPrompt/omost-llama-3-8b-4bits"),
            ("Omost/omost-llama-3-8b-4bits", "model-00002-of-00002.safetensors", "models/OmostPrompt/omost-llama-3-8b-4bits"),
            ("Omost/omost-llama-3-8b-4bits", "tokenizer.json", "models/OmostPrompt/omost-llama-3-8b-4bits"),
            ("Omost/omost-llama-3-8b-4bits", "tokenizer_config.json", "models/OmostPrompt/omost-llama-3-8b-4bits"),  
            ("Omost/omost-llama-3-8b-4bits", "config.json", "models/OmostPrompt/omost-llama-3-8b-4bits"),
            ("Omost/omost-llama-3-8b-4bits", "generation_config.json", "models/OmostPrompt/omost-llama-3-8b-4bits"),
            ("Omost/omost-llama-3-8b-4bits", "model.safetensors.index.json", "models/OmostPrompt/omost-llama-3-8b-4bits"),
            ("Omost/omost-llama-3-8b-4bits", "special_tokens_map.json", "models/OmostPrompt/omost-llama-3-8b-4bits"),
        ],
        "load_path": [
            "models/OmostPrompt/omost-llama-3-8b-4bits",
        ],
    },
    # Translator
    "opus-mt-zh-en": {
        "file_list": [
            ("moxying/opus-mt-zh-en", "config.json", "models/translator/opus-mt-zh-en"),
            ("moxying/opus-mt-zh-en", "generation_config.json", "models/translator/opus-mt-zh-en"),
            ("moxying/opus-mt-zh-en", "metadata.json", "models/translator/opus-mt-zh-en"),
            ("moxying/opus-mt-zh-en", "pytorch_model.bin", "models/translator/opus-mt-zh-en"),
            ("moxying/opus-mt-zh-en", "source.spm", "models/translator/opus-mt-zh-en"),
            ("moxying/opus-mt-zh-en", "target.spm", "models/translator/opus-mt-zh-en"),
            ("moxying/opus-mt-zh-en", "tokenizer_config.json", "models/translator/opus-mt-zh-en"),
            ("moxying/opus-mt-zh-en", "vocab.json", "models/translator/opus-mt-zh-en"),
        ],
        "load_path": [
            "models/translator/opus-mt-zh-en",
        ],
    },
    # IP-Adapter
    "IP-Adapter-SD": [
        ("AI-ModelScope/IP-Adapter", "models/image_encoder/model.safetensors", "models/IpAdapter/stable_diffusion/image_encoder"),
        ("AI-ModelScope/IP-Adapter", "models/ip-adapter_sd15.bin", "models/IpAdapter/stable_diffusion"),
    ],
    "IP-Adapter-SDXL": [
        ("AI-ModelScope/IP-Adapter", "sdxl_models/image_encoder/model.safetensors", "models/IpAdapter/stable_diffusion_xl/image_encoder"),
        ("AI-ModelScope/IP-Adapter", "sdxl_models/ip-adapter_sdxl.bin", "models/IpAdapter/stable_diffusion_xl"),
    ],
    # Kolors
    "Kolors": {
        "file_list": [
            ("Kwai-Kolors/Kolors", "text_encoder/config.json", "models/kolors/Kolors/text_encoder"),
            ("Kwai-Kolors/Kolors", "text_encoder/pytorch_model.bin.index.json", "models/kolors/Kolors/text_encoder"),
            ("Kwai-Kolors/Kolors", "text_encoder/pytorch_model-00001-of-00007.bin", "models/kolors/Kolors/text_encoder"),
            ("Kwai-Kolors/Kolors", "text_encoder/pytorch_model-00002-of-00007.bin", "models/kolors/Kolors/text_encoder"),
            ("Kwai-Kolors/Kolors", "text_encoder/pytorch_model-00003-of-00007.bin", "models/kolors/Kolors/text_encoder"),
            ("Kwai-Kolors/Kolors", "text_encoder/pytorch_model-00004-of-00007.bin", "models/kolors/Kolors/text_encoder"),
            ("Kwai-Kolors/Kolors", "text_encoder/pytorch_model-00005-of-00007.bin", "models/kolors/Kolors/text_encoder"),
            ("Kwai-Kolors/Kolors", "text_encoder/pytorch_model-00006-of-00007.bin", "models/kolors/Kolors/text_encoder"),
            ("Kwai-Kolors/Kolors", "text_encoder/pytorch_model-00007-of-00007.bin", "models/kolors/Kolors/text_encoder"),
            ("Kwai-Kolors/Kolors", "unet/diffusion_pytorch_model.safetensors", "models/kolors/Kolors/unet"),
            ("Kwai-Kolors/Kolors", "vae/diffusion_pytorch_model.safetensors", "models/kolors/Kolors/vae"),
        ],
        "load_path": [
            "models/kolors/Kolors/text_encoder",
            "models/kolors/Kolors/unet/diffusion_pytorch_model.safetensors",
            "models/kolors/Kolors/vae/diffusion_pytorch_model.safetensors",
        ],
    },
    "SDXL-vae-fp16-fix": [
        ("AI-ModelScope/sdxl-vae-fp16-fix", "diffusion_pytorch_model.safetensors", "models/sdxl-vae-fp16-fix")
    ],
    # FLUX
    "FLUX.1-dev": {
        "file_list": [
            ("AI-ModelScope/FLUX.1-dev", "text_encoder/model.safetensors", "models/FLUX/FLUX.1-dev/text_encoder"),
            ("AI-ModelScope/FLUX.1-dev", "text_encoder_2/config.json", "models/FLUX/FLUX.1-dev/text_encoder_2"),
            ("AI-ModelScope/FLUX.1-dev", "text_encoder_2/model-00001-of-00002.safetensors", "models/FLUX/FLUX.1-dev/text_encoder_2"),
            ("AI-ModelScope/FLUX.1-dev", "text_encoder_2/model-00002-of-00002.safetensors", "models/FLUX/FLUX.1-dev/text_encoder_2"),
            ("AI-ModelScope/FLUX.1-dev", "text_encoder_2/model.safetensors.index.json", "models/FLUX/FLUX.1-dev/text_encoder_2"),
            ("AI-ModelScope/FLUX.1-dev", "ae.safetensors", "models/FLUX/FLUX.1-dev"),
            ("AI-ModelScope/FLUX.1-dev", "flux1-dev.safetensors", "models/FLUX/FLUX.1-dev"),
        ],
        "load_path": [
            "models/FLUX/FLUX.1-dev/text_encoder/model.safetensors",
            "models/FLUX/FLUX.1-dev/text_encoder_2",
            "models/FLUX/FLUX.1-dev/ae.safetensors",
            "models/FLUX/FLUX.1-dev/flux1-dev.safetensors"
        ],
    },
    "FLUX.1-schnell": {
        "file_list": [
            ("AI-ModelScope/FLUX.1-dev", "text_encoder/model.safetensors", "models/FLUX/FLUX.1-dev/text_encoder"),
            ("AI-ModelScope/FLUX.1-dev", "text_encoder_2/config.json", "models/FLUX/FLUX.1-dev/text_encoder_2"),
            ("AI-ModelScope/FLUX.1-dev", "text_encoder_2/model-00001-of-00002.safetensors", "models/FLUX/FLUX.1-dev/text_encoder_2"),
            ("AI-ModelScope/FLUX.1-dev", "text_encoder_2/model-00002-of-00002.safetensors", "models/FLUX/FLUX.1-dev/text_encoder_2"),
            ("AI-ModelScope/FLUX.1-dev", "text_encoder_2/model.safetensors.index.json", "models/FLUX/FLUX.1-dev/text_encoder_2"),
            ("AI-ModelScope/FLUX.1-dev", "ae.safetensors", "models/FLUX/FLUX.1-dev"),
            ("AI-ModelScope/FLUX.1-schnell", "flux1-schnell.safetensors", "models/FLUX/FLUX.1-schnell"),
        ],
        "load_path": [
            "models/FLUX/FLUX.1-dev/text_encoder/model.safetensors",
            "models/FLUX/FLUX.1-dev/text_encoder_2",
            "models/FLUX/FLUX.1-dev/ae.safetensors",
            "models/FLUX/FLUX.1-schnell/flux1-schnell.safetensors"
        ],
    },
    "InstantX/FLUX.1-dev-Controlnet-Union-alpha": [
        ("InstantX/FLUX.1-dev-Controlnet-Union-alpha", "diffusion_pytorch_model.safetensors", "models/ControlNet/InstantX/FLUX.1-dev-Controlnet-Union-alpha"),
    ],
    "jasperai/Flux.1-dev-Controlnet-Depth": [
        ("jasperai/Flux.1-dev-Controlnet-Depth", "diffusion_pytorch_model.safetensors", "models/ControlNet/jasperai/Flux.1-dev-Controlnet-Depth"),
    ],
    "jasperai/Flux.1-dev-Controlnet-Surface-Normals": [
        ("jasperai/Flux.1-dev-Controlnet-Surface-Normals", "diffusion_pytorch_model.safetensors", "models/ControlNet/jasperai/Flux.1-dev-Controlnet-Surface-Normals"),
    ],
    "jasperai/Flux.1-dev-Controlnet-Upscaler": [
        ("jasperai/Flux.1-dev-Controlnet-Upscaler", "diffusion_pytorch_model.safetensors", "models/ControlNet/jasperai/Flux.1-dev-Controlnet-Upscaler"),
    ],
    "alimama-creative/FLUX.1-dev-Controlnet-Inpainting-Alpha": [
        ("alimama-creative/FLUX.1-dev-Controlnet-Inpainting-Alpha", "diffusion_pytorch_model.safetensors", "models/ControlNet/alimama-creative/FLUX.1-dev-Controlnet-Inpainting-Alpha"),
    ],
    "alimama-creative/FLUX.1-dev-Controlnet-Inpainting-Beta": [
        ("alimama-creative/FLUX.1-dev-Controlnet-Inpainting-Beta", "diffusion_pytorch_model.safetensors", "models/ControlNet/alimama-creative/FLUX.1-dev-Controlnet-Inpainting-Beta"),
    ],
    "Shakker-Labs/FLUX.1-dev-ControlNet-Depth": [
        ("Shakker-Labs/FLUX.1-dev-ControlNet-Depth", "diffusion_pytorch_model.safetensors", "models/ControlNet/Shakker-Labs/FLUX.1-dev-ControlNet-Depth"),
    ],
    "Shakker-Labs/FLUX.1-dev-ControlNet-Union-Pro": [
        ("Shakker-Labs/FLUX.1-dev-ControlNet-Union-Pro", "diffusion_pytorch_model.safetensors", "models/ControlNet/Shakker-Labs/FLUX.1-dev-ControlNet-Union-Pro"),
    ],
    "InstantX/FLUX.1-dev-IP-Adapter": {
        "file_list": [
            ("InstantX/FLUX.1-dev-IP-Adapter", "ip-adapter.bin", "models/IpAdapter/InstantX/FLUX.1-dev-IP-Adapter"),
            ("AI-ModelScope/siglip-so400m-patch14-384", "model.safetensors", "models/IpAdapter/InstantX/FLUX.1-dev-IP-Adapter/image_encoder"),
            ("AI-ModelScope/siglip-so400m-patch14-384", "config.json", "models/IpAdapter/InstantX/FLUX.1-dev-IP-Adapter/image_encoder"),
        ],
        "load_path": [
            "models/IpAdapter/InstantX/FLUX.1-dev-IP-Adapter/ip-adapter.bin",
            "models/IpAdapter/InstantX/FLUX.1-dev-IP-Adapter/image_encoder",
        ],
    },
    # ESRGAN
    "ESRGAN_x4": [
        ("AI-ModelScope/Real-ESRGAN", "RealESRGAN_x4.pth", "models/ESRGAN"),
    ],
    # RIFE
    "RIFE": [
        ("AI-ModelScope/RIFE", "flownet.pkl", "models/RIFE"),
    ],
    # Omnigen
    "OmniGen-v1": {
        "file_list": [
            ("BAAI/OmniGen-v1", "vae/diffusion_pytorch_model.safetensors", "models/OmniGen/OmniGen-v1/vae"),
            ("BAAI/OmniGen-v1", "model.safetensors", "models/OmniGen/OmniGen-v1"),
            ("BAAI/OmniGen-v1", "config.json", "models/OmniGen/OmniGen-v1"),
            ("BAAI/OmniGen-v1", "special_tokens_map.json", "models/OmniGen/OmniGen-v1"),
            ("BAAI/OmniGen-v1", "tokenizer_config.json", "models/OmniGen/OmniGen-v1"),
            ("BAAI/OmniGen-v1", "tokenizer.json", "models/OmniGen/OmniGen-v1"),
        ],
        "load_path": [
            "models/OmniGen/OmniGen-v1/vae/diffusion_pytorch_model.safetensors",
            "models/OmniGen/OmniGen-v1/model.safetensors",
        ]
    },
    # CogVideo
    "CogVideoX-5B": {
        "file_list": [
            ("ZhipuAI/CogVideoX-5b", "text_encoder/config.json", "models/CogVideo/CogVideoX-5b/text_encoder"),
            ("ZhipuAI/CogVideoX-5b", "text_encoder/model.safetensors.index.json", "models/CogVideo/CogVideoX-5b/text_encoder"),
            ("ZhipuAI/CogVideoX-5b", "text_encoder/model-00001-of-00002.safetensors", "models/CogVideo/CogVideoX-5b/text_encoder"),
            ("ZhipuAI/CogVideoX-5b", "text_encoder/model-00002-of-00002.safetensors", "models/CogVideo/CogVideoX-5b/text_encoder"),
            ("ZhipuAI/CogVideoX-5b", "transformer/config.json", "models/CogVideo/CogVideoX-5b/transformer"),
            ("ZhipuAI/CogVideoX-5b", "transformer/diffusion_pytorch_model.safetensors.index.json", "models/CogVideo/CogVideoX-5b/transformer"),
            ("ZhipuAI/CogVideoX-5b", "transformer/diffusion_pytorch_model-00001-of-00002.safetensors", "models/CogVideo/CogVideoX-5b/transformer"),
            ("ZhipuAI/CogVideoX-5b", "transformer/diffusion_pytorch_model-00002-of-00002.safetensors", "models/CogVideo/CogVideoX-5b/transformer"),
            ("ZhipuAI/CogVideoX-5b", "vae/diffusion_pytorch_model.safetensors", "models/CogVideo/CogVideoX-5b/vae"),
        ],
        "load_path": [
            "models/CogVideo/CogVideoX-5b/text_encoder",
            "models/CogVideo/CogVideoX-5b/transformer",
            "models/CogVideo/CogVideoX-5b/vae/diffusion_pytorch_model.safetensors",
        ],
    },
    # Stable Diffusion 3.5
    "StableDiffusion3.5-large": [
        ("AI-ModelScope/stable-diffusion-3.5-large", "sd3.5_large.safetensors", "models/stable_diffusion_3"),
        ("AI-ModelScope/stable-diffusion-3.5-large", "text_encoders/clip_l.safetensors", "models/stable_diffusion_3/text_encoders"),
        ("AI-ModelScope/stable-diffusion-3.5-large", "text_encoders/clip_g.safetensors", "models/stable_diffusion_3/text_encoders"),
        ("AI-ModelScope/stable-diffusion-3.5-large", "text_encoders/t5xxl_fp16.safetensors", "models/stable_diffusion_3/text_encoders"),
    ],
    "StableDiffusion3.5-medium": [
        ("AI-ModelScope/stable-diffusion-3.5-medium", "sd3.5_medium.safetensors", "models/stable_diffusion_3"),
        ("AI-ModelScope/stable-diffusion-3.5-large", "text_encoders/clip_l.safetensors", "models/stable_diffusion_3/text_encoders"),
        ("AI-ModelScope/stable-diffusion-3.5-large", "text_encoders/clip_g.safetensors", "models/stable_diffusion_3/text_encoders"),
        ("AI-ModelScope/stable-diffusion-3.5-large", "text_encoders/t5xxl_fp16.safetensors", "models/stable_diffusion_3/text_encoders"),
    ],
    "StableDiffusion3.5-large-turbo": [
        ("AI-ModelScope/stable-diffusion-3.5-large-turbo", "sd3.5_large_turbo.safetensors", "models/stable_diffusion_3"),
        ("AI-ModelScope/stable-diffusion-3.5-large", "text_encoders/clip_l.safetensors", "models/stable_diffusion_3/text_encoders"),
        ("AI-ModelScope/stable-diffusion-3.5-large", "text_encoders/clip_g.safetensors", "models/stable_diffusion_3/text_encoders"),
        ("AI-ModelScope/stable-diffusion-3.5-large", "text_encoders/t5xxl_fp16.safetensors", "models/stable_diffusion_3/text_encoders"),
    ],
    "HunyuanVideo":{
        "file_list": [
            ("AI-ModelScope/clip-vit-large-patch14", "model.safetensors", "models/HunyuanVideo/text_encoder"),
            ("DiffSynth-Studio/HunyuanVideo_MLLM_text_encoder", "model-00001-of-00004.safetensors", "models/HunyuanVideo/text_encoder_2"),
            ("DiffSynth-Studio/HunyuanVideo_MLLM_text_encoder", "model-00002-of-00004.safetensors", "models/HunyuanVideo/text_encoder_2"),
            ("DiffSynth-Studio/HunyuanVideo_MLLM_text_encoder", "model-00003-of-00004.safetensors", "models/HunyuanVideo/text_encoder_2"),
            ("DiffSynth-Studio/HunyuanVideo_MLLM_text_encoder", "model-00004-of-00004.safetensors", "models/HunyuanVideo/text_encoder_2"),
            ("DiffSynth-Studio/HunyuanVideo_MLLM_text_encoder", "config.json", "models/HunyuanVideo/text_encoder_2"),
            ("DiffSynth-Studio/HunyuanVideo_MLLM_text_encoder", "model.safetensors.index.json", "models/HunyuanVideo/text_encoder_2"),
            ("AI-ModelScope/HunyuanVideo", "hunyuan-video-t2v-720p/vae/pytorch_model.pt", "models/HunyuanVideo/vae"),
            ("AI-ModelScope/HunyuanVideo", "hunyuan-video-t2v-720p/transformers/mp_rank_00_model_states.pt", "models/HunyuanVideo/transformers")
        ],
        "load_path": [
            "models/HunyuanVideo/text_encoder/model.safetensors",
            "models/HunyuanVideo/text_encoder_2",
            "models/HunyuanVideo/vae/pytorch_model.pt",
            "models/HunyuanVideo/transformers/mp_rank_00_model_states.pt"
        ],
    },
    "HunyuanVideo-fp8":{
        "file_list": [
            ("AI-ModelScope/clip-vit-large-patch14", "model.safetensors", "models/HunyuanVideo/text_encoder"),
            ("DiffSynth-Studio/HunyuanVideo_MLLM_text_encoder", "model-00001-of-00004.safetensors", "models/HunyuanVideo/text_encoder_2"),
            ("DiffSynth-Studio/HunyuanVideo_MLLM_text_encoder", "model-00002-of-00004.safetensors", "models/HunyuanVideo/text_encoder_2"),
            ("DiffSynth-Studio/HunyuanVideo_MLLM_text_encoder", "model-00003-of-00004.safetensors", "models/HunyuanVideo/text_encoder_2"),
            ("DiffSynth-Studio/HunyuanVideo_MLLM_text_encoder", "model-00004-of-00004.safetensors", "models/HunyuanVideo/text_encoder_2"),
            ("DiffSynth-Studio/HunyuanVideo_MLLM_text_encoder", "config.json", "models/HunyuanVideo/text_encoder_2"),
            ("DiffSynth-Studio/HunyuanVideo_MLLM_text_encoder", "model.safetensors.index.json", "models/HunyuanVideo/text_encoder_2"),
            ("AI-ModelScope/HunyuanVideo", "hunyuan-video-t2v-720p/vae/pytorch_model.pt", "models/HunyuanVideo/vae"),
            ("DiffSynth-Studio/HunyuanVideo-safetensors", "model.fp8.safetensors", "models/HunyuanVideo/transformers")
        ],
        "load_path": [
            "models/HunyuanVideo/text_encoder/model.safetensors",
            "models/HunyuanVideo/text_encoder_2",
            "models/HunyuanVideo/vae/pytorch_model.pt",
            "models/HunyuanVideo/transformers/model.fp8.safetensors"
        ],
    },
}
Preset_model_id: TypeAlias = Literal[
    "HunyuanDiT",
    "stable-video-diffusion-img2vid-xt",
    "ExVideo-SVD-128f-v1",
    "ExVideo-CogVideoX-LoRA-129f-v1",
    "StableDiffusion_v15",
    "DreamShaper_8",
    "AingDiffusion_v12",
    "Flat2DAnimerge_v45Sharp",
    "TextualInversion_VeryBadImageNegative_v1.3",
    "StableDiffusionXL_v1",
    "BluePencilXL_v200",
    "StableDiffusionXL_Turbo",
    "ControlNet_v11f1p_sd15_depth",
    "ControlNet_v11p_sd15_softedge",
    "ControlNet_v11f1e_sd15_tile",
    "ControlNet_v11p_sd15_lineart",
    "AnimateDiff_v2",
    "AnimateDiff_xl_beta",
    "RIFE",
    "BeautifulPrompt",
    "opus-mt-zh-en",
    "IP-Adapter-SD",
    "IP-Adapter-SDXL",
    "StableDiffusion3",
    "StableDiffusion3_without_T5",
    "Kolors",
    "SDXL-vae-fp16-fix",
    "ControlNet_union_sdxl_promax",
    "FLUX.1-dev",
    "FLUX.1-schnell",
    "InstantX/FLUX.1-dev-Controlnet-Union-alpha",
    "jasperai/Flux.1-dev-Controlnet-Depth",
    "jasperai/Flux.1-dev-Controlnet-Surface-Normals",
    "jasperai/Flux.1-dev-Controlnet-Upscaler",
    "alimama-creative/FLUX.1-dev-Controlnet-Inpainting-Alpha",
    "alimama-creative/FLUX.1-dev-Controlnet-Inpainting-Beta",
    "Shakker-Labs/FLUX.1-dev-ControlNet-Depth",
    "Shakker-Labs/FLUX.1-dev-ControlNet-Union-Pro",
    "InstantX/FLUX.1-dev-IP-Adapter",
    "SDXL_lora_zyd232_ChineseInkStyle_SDXL_v1_0",
    "QwenPrompt",
    "OmostPrompt",
    "ESRGAN_x4",
    "RIFE",
    "OmniGen-v1",
    "CogVideoX-5B",
    "Annotators:Depth",
    "Annotators:Softedge",
    "Annotators:Lineart",
    "Annotators:Normal",
    "Annotators:Openpose",
    "StableDiffusion3.5-large",
    "StableDiffusion3.5-medium",
    "HunyuanVideo",
    "HunyuanVideo-fp8",
]