Remove file information

#2
by nielsr HF Staff - opened
Files changed (1) hide show
  1. README.md +1 -452
README.md CHANGED
@@ -4,457 +4,6 @@ pipeline_tag: text-to-image
4
  library_name: diffusers
5
  ---
6
 
7
- # File information
8
-
9
- The repository contains the following file information:
10
-
11
- Filename: model_index.json
12
- Content: {
13
- "_class_name": "StableDiffusionPipeline",
14
- "_diffusers_version": "0.6.0",
15
- "feature_extractor": [
16
- "transformers",
17
- "CLIPImageProcessor"
18
- ],
19
- "safety_checker": [
20
- "stable_diffusion",
21
- "StableDiffusionSafetyChecker"
22
- ],
23
- "scheduler": [
24
- "diffusers",
25
- "PNDMScheduler"
26
- ],
27
- "text_encoder": [
28
- "transformers",
29
- "CLIPTextModel"
30
- ],
31
- "tokenizer": [
32
- "transformers",
33
- "CLIPTokenizer"
34
- ],
35
- "unet": [
36
- "diffusers",
37
- "UNet2DConditionModel"
38
- ],
39
- "vae": [
40
- "diffusers",
41
- "AutoencoderKL"
42
- ]
43
- }
44
-
45
- Filename: preprocessor_config.json
46
- Content: {
47
- "crop_size": 224,
48
- "do_center_crop": true,
49
- "do_convert_rgb": true,
50
- "do_normalize": true,
51
- "do_resize": true,
52
- "feature_extractor_type": "CLIPFeatureExtractor",
53
- "image_mean": [
54
- 0.48145466,
55
- 0.4578275,
56
- "0.40821073"
57
- ],
58
- "image_std": [
59
- "0.26862954",
60
- "0.26130258",
61
- "0.27577711"
62
- ],
63
- "resample": 3,
64
- "size": 224
65
- }
66
-
67
- Filename: config.json
68
- Content: {
69
- "_commit_hash": "4bb648a606ef040e7685bde262611766a5fdd67b",
70
- "_name_or_path": "CompVis/stable-diffusion-safety-checker",
71
- "architectures": [
72
- "StableDiffusionSafetyChecker"
73
- ],
74
- "initializer_factor": 1.0,
75
- "logit_scale_init_value": 2.6592,
76
- "model_type": "clip",
77
- "projection_dim": 768,
78
- "text_config": {
79
- "_name_or_path": "",
80
- "add_cross_attention": false,
81
- "architectures": null,
82
- "attention_dropout": 0.0,
83
- "bad_words_ids": null,
84
- "bos_token_id": 0,
85
- "chunk_size_feed_forward": 0,
86
- "cross_attention_hidden_size": null,
87
- "decoder_start_token_id": null,
88
- "diversity_penalty": 0.0,
89
- "do_sample": false,
90
- "dropout": 0.0,
91
- "early_stopping": false,
92
- "encoder_no_repeat_ngram_size": 0,
93
- "eos_token_id": 2,
94
- "exponential_decay_length_penalty": null,
95
- "finetuning_task": null,
96
- "forced_bos_token_id": null,
97
- "forced_eos_token_id": null,
98
- "hidden_act": "quick_gelu",
99
- "hidden_size": 768,
100
- "id2label": {
101
- "0": "LABEL_0",
102
- "1": "LABEL_1"
103
- },
104
- "initializer_factor": 1.0,
105
- "initializer_range": 0.02,
106
- "intermediate_size": 3072,
107
- "is_decoder": false,
108
- "is_encoder_decoder": false,
109
- "label2id": {
110
- "LABEL_0": 0,
111
- "LABEL_1": 1
112
- },
113
- "layer_norm_eps": 1e-05,
114
- "length_penalty": 1.0,
115
- "max_length": 20,
116
- "max_position_embeddings": 77,
117
- "min_length": 0,
118
- "model_type": "clip_text_model",
119
- "no_repeat_ngram_size": 0,
120
- "num_attention_heads": 12,
121
- "num_beam_groups": 1,
122
- "num_beams": 1,
123
- "num_hidden_layers": 12,
124
- "num_return_sequences": 1,
125
- "output_attentions": false,
126
- "output_hidden_states": false,
127
- "output_scores": false,
128
- "pad_token_id": 1,
129
- "prefix": null,
130
- "problem_type": null,
131
- "pruned_heads": {},
132
- "remove_invalid_values": false,
133
- "repetition_penalty": 1.0,
134
- "return_dict": true,
135
- "return_dict_in_generate": false,
136
- "sep_token_id": null,
137
- "task_specific_params": null,
138
- "temperature": 1.0,
139
- "tf_legacy_loss": false,
140
- "tie_encoder_decoder": false,
141
- "tie_word_embeddings": true,
142
- "tokenizer_class": null,
143
- "top_k": 50,
144
- "top_p": 1.0,
145
- "torch_dtype": null,
146
- "torchscript": false,
147
- "transformers_version": "4.22.0.dev0",
148
- "typical_p": 1.0,
149
- "use_bfloat16": false,
150
- "vocab_size": 49408
151
- },
152
- "text_config_dict": {
153
- "hidden_size": 768,
154
- "intermediate_size": 3072,
155
- "num_attention_heads": 12,
156
- "num_hidden_layers": 12
157
- },
158
- "torch_dtype": "float32",
159
- "transformers_version": null,
160
- "vision_config": {
161
- "_name_or_path": "",
162
- "add_cross_attention": false,
163
- "architectures": null,
164
- "attention_dropout": 0.0,
165
- "bad_words_ids": null,
166
- "bos_token_id": null,
167
- "chunk_size_feed_forward": 0,
168
- "cross_attention_hidden_size": null,
169
- "decoder_start_token_id": null,
170
- "diversity_penalty": 0.0,
171
- "do_sample": false,
172
- "dropout": 0.0,
173
- "early_stopping": false,
174
- "encoder_no_repeat_ngram_size": 0,
175
- "eos_token_id": null,
176
- "exponential_decay_length_penalty": null,
177
- "finetuning_task": null,
178
- "forced_bos_token_id": null,
179
- "forced_eos_token_id": null,
180
- "hidden_act": "quick_gelu",
181
- "hidden_size": 1024,
182
- "id2label": {
183
- "0": "LABEL_0",
184
- "1": "LABEL_1"
185
- },
186
- "image_size": 224,
187
- "initializer_factor": 1.0,
188
- "initializer_range": 0.02,
189
- "intermediate_size": 4096,
190
- "is_decoder": false,
191
- "is_encoder_decoder": false,
192
- "label2id": {
193
- "LABEL_0": 0,
194
- "LABEL_1": 1
195
- },
196
- "layer_norm_eps": 1e-05,
197
- "length_penalty": 1.0,
198
- "max_length": 20,
199
- "min_length": 0,
200
- "model_type": "clip_vision_model",
201
- "no_repeat_ngram_size": 0,
202
- "num_attention_heads": 16,
203
- "num_beam_groups": 1,
204
- "num_beams": 1,
205
- "num_channels": 3,
206
- "num_hidden_layers": 24,
207
- "num_return_sequences": 1,
208
- "output_attentions": false,
209
- "output_hidden_states": false,
210
- "output_scores": false,
211
- "pad_token_id": null,
212
- "patch_size": 14,
213
- "prefix": null,
214
- "problem_type": null,
215
- "pruned_heads": {},
216
- "remove_invalid_values": false,
217
- "repetition_penalty": 1.0,
218
- "return_dict": true,
219
- "return_dict_in_generate": false,
220
- "sep_token_id": null,
221
- "task_specific_params": null,
222
- "temperature": 1.0,
223
- "tf_legacy_loss": false,
224
- "tie_encoder_decoder": false,
225
- "tie_word_embeddings": true,
226
- "tokenizer_class": null,
227
- "top_k": 50,
228
- "top_p": 1.0,
229
- "torch_dtype": null,
230
- "torchscript": false,
231
- "transformers_version": "4.22.0.dev0",
232
- "typical_p": 1.0,
233
- "use_bfloat16": false
234
- },
235
- "vision_config_dict": {
236
- "hidden_size": 1024,
237
- "intermediate_size": 4096,
238
- "num_attention_heads": 16,
239
- "num_hidden_layers": 24,
240
- "patch_size": 14
241
- }
242
- }
243
-
244
- Filename: config.json
245
- Content: {
246
- "_class_name": "AutoencoderKL",
247
- "_diffusers_version": "0.6.0",
248
- "act_fn": "silu",
249
- "block_out_channels": [
250
- 128,
251
- 256,
252
- 512,
253
- 512
254
- ],
255
- "down_block_types": [
256
- "DownEncoderBlock2D",
257
- "DownEncoderBlock2D",
258
- "DownEncoderBlock2D",
259
- "DownEncoderBlock2D"
260
- ],
261
- "in_channels": 3,
262
- "latent_channels": 4,
263
- "layers_per_block": 2,
264
- "norm_num_groups": 32,
265
- "out_channels": 3,
266
- "sample_size": 512,
267
- "up_block_types": [
268
- "UpDecoderBlock2D",
269
- "UpDecoderBlock2D",
270
- "UpDecoderBlock2D",
271
- "UpDecoderBlock2D"
272
- ]
273
- }
274
-
275
- Filename: vocab.json
276
- Content: Content of the file is larger than 50 KB, too long to display.
277
-
278
- Filename: special_tokens_map.json
279
- Content: {
280
- "bos_token": {
281
- "content": "<|startoftext|>",
282
- "lstrip": false,
283
- "normalized": true,
284
- "rstrip": false,
285
- "single_word": false
286
- },
287
- "eos_token": {
288
- "content": "<|endoftext|>",
289
- "lstrip": false,
290
- "normalized": true,
291
- "rstrip": false,
292
- "single_word": false
293
- },
294
- "pad_token": "<|endoftext|>",
295
- "unk_token": {
296
- "content": "<|endoftext|>",
297
- "lstrip": false,
298
- "normalized": true,
299
- "rstrip": false,
300
- "single_word": false
301
- }
302
- }
303
-
304
- Filename: tokenizer_config.json
305
- Content: {
306
- "add_prefix_space": false,
307
- "bos_token": {
308
- "__type": "AddedToken",
309
- "content": "<|startoftext|>",
310
- "lstrip": false,
311
- "normalized": true,
312
- "rstrip": false,
313
- "single_word": false
314
- },
315
- "do_lower_case": true,
316
- "eos_token": {
317
- "__type": "AddedToken",
318
- "content": "<|endoftext|>\",
319
- \"lstrip\": false,
320
- \"normalized\": true,
321
- \"rstrip\": false,
322
- \"single_word\": false
323
- },
324
- "errors": "replace",
325
- "model_max_length": 77,
326
- "name_or_path": "openai/clip-vit-large-patch14",
327
- "pad_token": "<|endoftext|>",
328
- "special_tokens_map_file": "./special_tokens_map.json",
329
- "tokenizer_class": "CLIPTokenizer",
330
- "unk_token": {
331
- "__type": "AddedToken",
332
- "content": "<|endoftext|>",
333
- "lstrip": false,
334
- "normalized": true,
335
- "rstrip": false,
336
- "single_word": false
337
- }
338
- }
339
-
340
- Filename: config.json
341
- Content: {
342
- "_class_name": "UNet2DConditionModel",
343
- "_diffusers_version": "0.28.2",
344
- "_name_or_path": "/home/share/Loopfree/pretrained/loopfree-step4-sd15",
345
- "act_fn": "silu",
346
- "addition_embed_type": null,
347
- "addition_embed_type_num_heads": 64,
348
- "addition_time_embed_dim": null,
349
- "attention_head_dim": 8,
350
- "attention_type": "default",
351
- "block_out_channels": [
352
- 320,
353
- 640,
354
- 1280,
355
- 1280
356
- ],
357
- "center_input_sample": false,
358
- "class_embed_type": null,
359
- "class_embeddings_concat": false,
360
- "conv_in_kernel": 3,
361
- "conv_out_kernel": 3,
362
- "cross_attention_dim": 768,
363
- "cross_attention_norm": null,
364
- "decay": 0.9999,
365
- "down_block_types": [
366
- "CrossAttnDownBlock2D",
367
- "CrossAttnDownBlock2D",
368
- "CrossAttnDownBlock2D",
369
- "DownBlock2D"
370
- ],
371
- "downsample_padding": 1,
372
- "dropout": 0.0,
373
- "dual_cross_attention": false,
374
- "encoder_hid_dim": null,
375
- "encoder_hid_dim_type": null,
376
- "flip_sin_to_cos": true,
377
- "freq_shift": 0,
378
- "in_channels": 4,
379
- "inv_gamma": 1.0,
380
- "layers_per_block": 2,
381
- "mid_block_only_cross_attention": null,
382
- "mid_block_scale_factor": 1,
383
- "mid_block_type": "UNetMidBlock2DCrossAttn",
384
- "min_decay": 0.0,
385
- "norm_eps": 1e-05,
386
- "norm_num_groups": 32,
387
- "num_attention_heads": null,
388
- "num_class_embeds": null,
389
- "only_cross_attention": false,
390
- "optimization_step": 10000,
391
- "out_channels": 4,
392
- "power": 0.6666666666666666,
393
- "projection_class_embeddings_input_dim": null,
394
- "resnet_out_scale_factor": 1.0,
395
- "resnet_skip_time_act": false,
396
- "resnet_time_scale_shift": "default",
397
- "reverse_transformer_layers_per_block": null,
398
- "sample_size": 64,
399
- "time_cond_proj_dim": null,
400
- "time_embedding_act_fn": null,
401
- "time_embedding_dim": null,
402
- "time_embedding_type": "positional",
403
- "timestep_post_act": null,
404
- "transformer_layers_per_block": 1,
405
- "up_block_types": [
406
- "UpBlock2D",
407
- "CrossAttnUpBlock2D",
408
- "CrossAttnUpBlock2D",
409
- "CrossAttnUpBlock2D"
410
- ],
411
- "upcast_attention": false,
412
- "update_after_step": 0,
413
- "use_ema_warmup": false,
414
- "use_linear_projection": false
415
- }
416
-
417
- Filename: scheduler_config.json
418
- Content: {
419
- "_class_name": "PNDMScheduler",
420
- "_diffusers_version": "0.6.0",
421
- "beta_end": 0.012,
422
- "beta_schedule": "scaled_linear",
423
- "beta_start": 0.00085,
424
- "num_train_timesteps": 1000,
425
- "set_alpha_to_one": false,
426
- "skip_prk_steps": true,
427
- "steps_offset": 1,
428
- "trained_betas": null,
429
- "clip_sample": false
430
- }
431
-
432
- Filename: config.json
433
- Content: {
434
- "_name_or_path": "openai/clip-vit-large-patch14",
435
- "architectures": [
436
- "CLIPTextModel"
437
- ],
438
- "attention_dropout": 0.0,
439
- "bos_token_id": 0,
440
- "dropout": 0.0,
441
- "eos_token_id": 2,
442
- "hidden_act": "quick_gelu",
443
- "hidden_size": 768,
444
- "initializer_factor": 1.0,
445
- "initializer_range": 0.02,
446
- "intermediate_size": 3072,
447
- "layer_norm_eps": 1e-05,
448
- "max_position_embeddings": 77,
449
- "model_type": "clip_text_model",
450
- "num_attention_heads": 12,
451
- "num_hidden_layers": 12,
452
- "pad_token_id": 1,
453
- "projection_dim": 768,
454
- "torch_dtype": "float32",
455
- "transformers_version": "4.22.0.dev0",
456
- "vocab_size": 49408
457
- }
458
-
459
  This model implements the method described in the paper [One-Way Ticket:Time-Independent Unified Encoder for Distilling Text-to-Image Diffusion Models](https://huggingface.co/papers/2505.21960).
 
460
  Github repository: https://github.com/sen-mao/Loopfree
 
4
  library_name: diffusers
5
  ---
6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  This model implements the method described in the paper [One-Way Ticket:Time-Independent Unified Encoder for Distilling Text-to-Image Diffusion Models](https://huggingface.co/papers/2505.21960).
8
+
9
  Github repository: https://github.com/sen-mao/Loopfree