Hugging Face's logo

Spaces:
Ryukijano
/
CatCon-One-Shot-Controlnet-SD-1-5-b2
Build error

App Files Community
2
Ryukijano commited on
Commit
f959177
•
1 Parent(s): 8819e4c

Updated checkpoints and app.py

Browse files
Files changed (37) hide show
  1. .gitattributes +34 -0
  2. app.py +22 -11
  3. models/catcon-controlnet-wd/config.json +38 -0
  4. models/catcon-controlnet-wd/diffusion_flax_model.msgpack +3 -0
  5. models/wd-1-5-b2-flax/feature_extractor/preprocessor_config.json +28 -0
  6. models/wd-1-5-b2-flax/model_index.json +32 -0
  7. models/wd-1-5-b2-flax/safety_checker/config.json +168 -0
  8. models/wd-1-5-b2-flax/safety_checker/flax_model.msgpack +3 -0
  9. models/wd-1-5-b2-flax/scheduler/scheduler_config.json +14 -0
  10. models/wd-1-5-b2-flax/text_encoder/config.json +25 -0
  11. models/wd-1-5-b2-flax/text_encoder/flax_model.msgpack +3 -0
  12. models/wd-1-5-b2-flax/tokenizer/merges.txt +0 -0
  13. models/wd-1-5-b2-flax/tokenizer/special_tokens_map.json +24 -0
  14. models/wd-1-5-b2-flax/tokenizer/tokenizer_config.json +33 -0
  15. models/wd-1-5-b2-flax/tokenizer/vocab.json +0 -0
  16. models/wd-1-5-b2-flax/unet/config.json +65 -0
  17. models/wd-1-5-b2-flax/unet/diffusion_flax_model.msgpack +3 -0
  18. models/wd-1-5-b2-flax/vae/config.json +31 -0
  19. models/wd-1-5-b2-flax/vae/diffusion_flax_model.msgpack +3 -0
  20. models/wd-1-5-b2/feature_extractor/preprocessor_config.json +28 -0
  21. models/wd-1-5-b2/model_index.json +33 -0
  22. models/wd-1-5-b2/safety_checker/config.json +168 -0
  23. models/wd-1-5-b2/safety_checker/pytorch_model.bin +3 -0
  24. models/wd-1-5-b2/scheduler/scheduler_config.json +14 -0
  25. models/wd-1-5-b2/text_encoder/config.json +25 -0
  26. models/wd-1-5-b2/text_encoder/pytorch_model.bin +3 -0
  27. models/wd-1-5-b2/tokenizer/merges.txt +0 -0
  28. models/wd-1-5-b2/tokenizer/special_tokens_map.json +24 -0
  29. models/wd-1-5-b2/tokenizer/tokenizer_config.json +33 -0
  30. models/wd-1-5-b2/tokenizer/vocab.json +0 -0
  31. models/wd-1-5-b2/unet/config.json +63 -0
  32. models/wd-1-5-b2/unet/diffusion_pytorch_model.bin +3 -0
  33. models/wd-1-5-b2/vae/config.json +31 -0
  34. models/wd-1-5-b2/vae/diffusion_pytorch_model.bin +3 -0
  35. requirements.txt +4 -4
  36. wikipe_cond_2.png +0 -0
  37. wikipe_cond_3.png +0 -0
.gitattributes ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ *.7z filter=lfs diff=lfs merge=lfs -text
2
+ *.arrow filter=lfs diff=lfs merge=lfs -text
3
+ *.bin filter=lfs diff=lfs merge=lfs -text
4
+ *.bz2 filter=lfs diff=lfs merge=lfs -text
5
+ *.ckpt filter=lfs diff=lfs merge=lfs -text
6
+ *.ftz filter=lfs diff=lfs merge=lfs -text
7
+ *.gz filter=lfs diff=lfs merge=lfs -text
8
+ *.h5 filter=lfs diff=lfs merge=lfs -text
9
+ *.joblib filter=lfs diff=lfs merge=lfs -text
10
+ *.lfs.* filter=lfs diff=lfs merge=lfs -text
11
+ *.mlmodel filter=lfs diff=lfs merge=lfs -text
12
+ *.model filter=lfs diff=lfs merge=lfs -text
13
+ *.msgpack filter=lfs diff=lfs merge=lfs -text
14
+ *.npy filter=lfs diff=lfs merge=lfs -text
15
+ *.npz filter=lfs diff=lfs merge=lfs -text
16
+ *.onnx filter=lfs diff=lfs merge=lfs -text
17
+ *.ot filter=lfs diff=lfs merge=lfs -text
18
+ *.parquet filter=lfs diff=lfs merge=lfs -text
19
+ *.pb filter=lfs diff=lfs merge=lfs -text
20
+ *.pickle filter=lfs diff=lfs merge=lfs -text
21
+ *.pkl filter=lfs diff=lfs merge=lfs -text
22
+ *.pt filter=lfs diff=lfs merge=lfs -text
23
+ *.pth filter=lfs diff=lfs merge=lfs -text
24
+ *.rar filter=lfs diff=lfs merge=lfs -text
25
+ *.safetensors filter=lfs diff=lfs merge=lfs -text
26
+ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
27
+ *.tar.* filter=lfs diff=lfs merge=lfs -text
28
+ *.tflite filter=lfs diff=lfs merge=lfs -text
29
+ *.tgz filter=lfs diff=lfs merge=lfs -text
30
+ *.wasm filter=lfs diff=lfs merge=lfs -text
31
+ *.xz filter=lfs diff=lfs merge=lfs -text
32
+ *.zip filter=lfs diff=lfs merge=lfs -text
33
+ *.zst filter=lfs diff=lfs merge=lfs -text
34
+ *tfevents* filter=lfs diff=lfs merge=lfs -text
app.py CHANGED
@@ -8,19 +8,17 @@ import torchvision
8
  import torchvision.transforms as T
9
  from flax.jax_utils import replicate
10
  from flax.training.common_utils import shard
 
11
  import cv2
12
  import PIL
13
  from PIL import Image
14
  import numpy as np
15
  import jax
16
 
17
- def create_key(seed=0):
18
- return jax.random.PRNGKey(seed)
19
-
20
 
21
  output_res = (768,768)
22
 
23
-
24
  conditioning_image_transforms = T.Compose(
25
  [
26
  #T2.ScaleJitter(target_size=output_res, scale_range=(0.5, 3.0))),
@@ -30,17 +28,26 @@ conditioning_image_transforms = T.Compose(
30
  ]
31
  )
32
 
33
- cnet, cnet_params = FlaxControlNetModel.from_pretrained("Ryukijano/catcon-controlnet-wd", dtype=jnp.bfloat16, from_flax=True)
34
  pipe, params = FlaxStableDiffusionControlNetPipeline.from_pretrained(
35
  "./models/wd-1-5-b2-flax",
36
  controlnet=cnet,
37
  revision="flax",
38
  dtype=jnp.bfloat16,
39
  )
 
 
 
 
 
40
 
41
- key = jax.random.PRNGKey(0)
 
 
 
 
 
42
 
43
- # inference function takes prompt, negative prompt and image
44
  # inference function takes prompt, negative prompt and image
45
  def infer(prompt, negative_prompt, image):
46
  # implement your inference function here
@@ -92,12 +99,16 @@ gr.Interface(
92
  max_lines=1,
93
  placeholder="low quality",
94
  ),
95
- gr.Image(type="pil"),
96
- gr.Slider(minimum=0, maximum=100, step=1, default=0, label="Seed (0 for random seed)")
97
  ],
98
  outputs=gr.Gallery().style(grid=[2], height="auto"),
99
- title="Generate controlled outputs with Categorical Conditioning on Stable Diffusion 1.5 beta 2.",
100
  description="This Space uses image examples as style conditioning.",
101
- examples=[["1girl, green hair, sweater, looking at viewer, upper body, beanie, outdoors, watercolor, night, turtleneck", "low quality", "wikipe_cond_1.png"]],
 
 
 
 
102
  allow_flagging=False,
103
  ).launch(enable_queue=True)
 
 
8
  import torchvision.transforms as T
9
  from flax.jax_utils import replicate
10
  from flax.training.common_utils import shard
11
+ #from torchvision.transforms import v2 as T2
12
  import cv2
13
  import PIL
14
  from PIL import Image
15
  import numpy as np
16
  import jax
17
 
18
+ import torchvision.transforms.functional as F
 
 
19
 
20
  output_res = (768,768)
21
 
 
22
  conditioning_image_transforms = T.Compose(
23
  [
24
  #T2.ScaleJitter(target_size=output_res, scale_range=(0.5, 3.0))),
 
28
  ]
29
  )
30
 
31
+ cnet, cnet_params = FlaxControlNetModel.from_pretrained("./models/catcon-controlnet-wd", dtype=jnp.bfloat16, from_flax=True)
32
  pipe, params = FlaxStableDiffusionControlNetPipeline.from_pretrained(
33
  "./models/wd-1-5-b2-flax",
34
  controlnet=cnet,
35
  revision="flax",
36
  dtype=jnp.bfloat16,
37
  )
38
+ #scheduler, scheduler_state = FlaxDPMSolverMultistepScheduler.from_pretrained(
39
+ # "./models/wd-1-5-b2-flax",
40
+ # subfolder="scheduler"
41
+ #)
42
+ #params["scheduler"] = scheduler_state
43
 
44
+ #scheduler = FlaxDPMSolverMultistepScheduler.from_config(pipe.scheduler.config)
45
+ #pipe.enable_model_cpu_offload()
46
+ #pipe.enable_xformers_memory_efficient_attention()
47
+
48
+ def get_random(seed):
49
+ return jax.random.PRNGKey(seed)
50
 
 
51
  # inference function takes prompt, negative prompt and image
52
  def infer(prompt, negative_prompt, image):
53
  # implement your inference function here
 
99
  max_lines=1,
100
  placeholder="low quality",
101
  ),
102
+ gr.Image(),
 
103
  ],
104
  outputs=gr.Gallery().style(grid=[2], height="auto"),
105
+ title="Generate controlled outputs with Categorical Conditioning on Waifu Diffusion 1.5 beta 2.",
106
  description="This Space uses image examples as style conditioning.",
107
+ examples=[
108
+ ["1girl, green hair, sweater, looking at viewer, upper body, beanie, outdoors, watercolor, night, turtleneck", "realistic, real life", "wikipe_cond_1.png"],
109
+ ["1girl, green hair, sweater, looking at viewer, upper body, beanie, outdoors, watercolor, night, turtleneck", "realistic, real life", "wikipe_cond_2.png"],
110
+ ["1girl, green hair, sweater, looking at viewer, upper body, beanie, outdoors, watercolor, night, turtleneck", "realistic, real life", "wikipe_cond_3.png"]
111
+ ],
112
  allow_flagging=False,
113
  ).launch(enable_queue=True)
114
+
models/catcon-controlnet-wd/config.json ADDED
@@ -0,0 +1,38 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "FlaxControlNetModel",
3
+ "_diffusers_version": "0.16.0.dev0",
4
+ "attention_head_dim": [
5
+ 5,
6
+ 10,
7
+ 20,
8
+ 20
9
+ ],
10
+ "block_out_channels": [
11
+ 320,
12
+ 640,
13
+ 1280,
14
+ 1280
15
+ ],
16
+ "conditioning_embedding_out_channels": [
17
+ 16,
18
+ 32,
19
+ 96,
20
+ 256
21
+ ],
22
+ "controlnet_conditioning_channel_order": "rgb",
23
+ "cross_attention_dim": 1024,
24
+ "down_block_types": [
25
+ "CrossAttnDownBlock2D",
26
+ "CrossAttnDownBlock2D",
27
+ "CrossAttnDownBlock2D",
28
+ "DownBlock2D"
29
+ ],
30
+ "dropout": 0.0,
31
+ "flip_sin_to_cos": true,
32
+ "freq_shift": 0,
33
+ "in_channels": 4,
34
+ "layers_per_block": 2,
35
+ "only_cross_attention": false,
36
+ "sample_size": 32,
37
+ "use_linear_projection": true
38
+ }
models/catcon-controlnet-wd/diffusion_flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1704f5628e480511c1cc3c638aa00695635c3c08358682dffa2e2f6724644bfc
3
+ size 1456925250
models/wd-1-5-b2-flax/feature_extractor/preprocessor_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 224,
4
+ "width": 224
5
+ },
6
+ "do_center_crop": true,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "feature_extractor_type": "CLIPFeatureExtractor",
12
+ "image_mean": [
13
+ 0.48145466,
14
+ 0.4578275,
15
+ 0.40821073
16
+ ],
17
+ "image_processor_type": "CLIPFeatureExtractor",
18
+ "image_std": [
19
+ 0.26862954,
20
+ 0.26130258,
21
+ 0.27577711
22
+ ],
23
+ "resample": 3,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "shortest_edge": 224
27
+ }
28
+ }
models/wd-1-5-b2-flax/model_index.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "FlaxStableDiffusionPipeline",
3
+ "_diffusers_version": "0.16.0.dev0",
4
+ "feature_extractor": [
5
+ "transformers",
6
+ "CLIPFeatureExtractor"
7
+ ],
8
+ "safety_checker": [
9
+ "stable_diffusion",
10
+ "FlaxStableDiffusionSafetyChecker"
11
+ ],
12
+ "scheduler": [
13
+ "diffusers",
14
+ "FlaxPNDMScheduler"
15
+ ],
16
+ "text_encoder": [
17
+ "transformers",
18
+ "FlaxCLIPTextModel"
19
+ ],
20
+ "tokenizer": [
21
+ "transformers",
22
+ "CLIPTokenizer"
23
+ ],
24
+ "unet": [
25
+ "diffusers",
26
+ "FlaxUNet2DConditionModel"
27
+ ],
28
+ "vae": [
29
+ "diffusers",
30
+ "FlaxAutoencoderKL"
31
+ ]
32
+ }
models/wd-1-5-b2-flax/safety_checker/config.json ADDED
@@ -0,0 +1,168 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "_name_or_path": "./safety_checker",
4
+ "architectures": [
5
+ "StableDiffusionSafetyChecker"
6
+ ],
7
+ "initializer_factor": 1.0,
8
+ "logit_scale_init_value": 2.6592,
9
+ "model_type": "clip",
10
+ "projection_dim": 768,
11
+ "text_config": {
12
+ "_name_or_path": "",
13
+ "add_cross_attention": false,
14
+ "architectures": null,
15
+ "attention_dropout": 0.0,
16
+ "bad_words_ids": null,
17
+ "begin_suppress_tokens": null,
18
+ "bos_token_id": 0,
19
+ "chunk_size_feed_forward": 0,
20
+ "cross_attention_hidden_size": null,
21
+ "decoder_start_token_id": null,
22
+ "diversity_penalty": 0.0,
23
+ "do_sample": false,
24
+ "dropout": 0.0,
25
+ "early_stopping": false,
26
+ "encoder_no_repeat_ngram_size": 0,
27
+ "eos_token_id": 2,
28
+ "exponential_decay_length_penalty": null,
29
+ "finetuning_task": null,
30
+ "forced_bos_token_id": null,
31
+ "forced_eos_token_id": null,
32
+ "hidden_act": "quick_gelu",
33
+ "hidden_size": 768,
34
+ "id2label": {
35
+ "0": "LABEL_0",
36
+ "1": "LABEL_1"
37
+ },
38
+ "initializer_factor": 1.0,
39
+ "initializer_range": 0.02,
40
+ "intermediate_size": 3072,
41
+ "is_decoder": false,
42
+ "is_encoder_decoder": false,
43
+ "label2id": {
44
+ "LABEL_0": 0,
45
+ "LABEL_1": 1
46
+ },
47
+ "layer_norm_eps": 1e-05,
48
+ "length_penalty": 1.0,
49
+ "max_length": 20,
50
+ "max_position_embeddings": 77,
51
+ "min_length": 0,
52
+ "model_type": "clip_text_model",
53
+ "no_repeat_ngram_size": 0,
54
+ "num_attention_heads": 12,
55
+ "num_beam_groups": 1,
56
+ "num_beams": 1,
57
+ "num_hidden_layers": 12,
58
+ "num_return_sequences": 1,
59
+ "output_attentions": false,
60
+ "output_hidden_states": false,
61
+ "output_scores": false,
62
+ "pad_token_id": 1,
63
+ "prefix": null,
64
+ "problem_type": null,
65
+ "projection_dim": 512,
66
+ "pruned_heads": {},
67
+ "remove_invalid_values": false,
68
+ "repetition_penalty": 1.0,
69
+ "return_dict": true,
70
+ "return_dict_in_generate": false,
71
+ "sep_token_id": null,
72
+ "suppress_tokens": null,
73
+ "task_specific_params": null,
74
+ "temperature": 1.0,
75
+ "tf_legacy_loss": false,
76
+ "tie_encoder_decoder": false,
77
+ "tie_word_embeddings": true,
78
+ "tokenizer_class": null,
79
+ "top_k": 50,
80
+ "top_p": 1.0,
81
+ "torch_dtype": null,
82
+ "torchscript": false,
83
+ "transformers_version": "4.28.1",
84
+ "typical_p": 1.0,
85
+ "use_bfloat16": false,
86
+ "vocab_size": 49408
87
+ },
88
+ "torch_dtype": "float32",
89
+ "transformers_version": null,
90
+ "vision_config": {
91
+ "_name_or_path": "",
92
+ "add_cross_attention": false,
93
+ "architectures": null,
94
+ "attention_dropout": 0.0,
95
+ "bad_words_ids": null,
96
+ "begin_suppress_tokens": null,
97
+ "bos_token_id": null,
98
+ "chunk_size_feed_forward": 0,
99
+ "cross_attention_hidden_size": null,
100
+ "decoder_start_token_id": null,
101
+ "diversity_penalty": 0.0,
102
+ "do_sample": false,
103
+ "dropout": 0.0,
104
+ "early_stopping": false,
105
+ "encoder_no_repeat_ngram_size": 0,
106
+ "eos_token_id": null,
107
+ "exponential_decay_length_penalty": null,
108
+ "finetuning_task": null,
109
+ "forced_bos_token_id": null,
110
+ "forced_eos_token_id": null,
111
+ "hidden_act": "quick_gelu",
112
+ "hidden_size": 1024,
113
+ "id2label": {
114
+ "0": "LABEL_0",
115
+ "1": "LABEL_1"
116
+ },
117
+ "image_size": 224,
118
+ "initializer_factor": 1.0,
119
+ "initializer_range": 0.02,
120
+ "intermediate_size": 4096,
121
+ "is_decoder": false,
122
+ "is_encoder_decoder": false,
123
+ "label2id": {
124
+ "LABEL_0": 0,
125
+ "LABEL_1": 1
126
+ },
127
+ "layer_norm_eps": 1e-05,
128
+ "length_penalty": 1.0,
129
+ "max_length": 20,
130
+ "min_length": 0,
131
+ "model_type": "clip_vision_model",
132
+ "no_repeat_ngram_size": 0,
133
+ "num_attention_heads": 16,
134
+ "num_beam_groups": 1,
135
+ "num_beams": 1,
136
+ "num_channels": 3,
137
+ "num_hidden_layers": 24,
138
+ "num_return_sequences": 1,
139
+ "output_attentions": false,
140
+ "output_hidden_states": false,
141
+ "output_scores": false,
142
+ "pad_token_id": null,
143
+ "patch_size": 14,
144
+ "prefix": null,
145
+ "problem_type": null,
146
+ "projection_dim": 512,
147
+ "pruned_heads": {},
148
+ "remove_invalid_values": false,
149
+ "repetition_penalty": 1.0,
150
+ "return_dict": true,
151
+ "return_dict_in_generate": false,
152
+ "sep_token_id": null,
153
+ "suppress_tokens": null,
154
+ "task_specific_params": null,
155
+ "temperature": 1.0,
156
+ "tf_legacy_loss": false,
157
+ "tie_encoder_decoder": false,
158
+ "tie_word_embeddings": true,
159
+ "tokenizer_class": null,
160
+ "top_k": 50,
161
+ "top_p": 1.0,
162
+ "torch_dtype": null,
163
+ "torchscript": false,
164
+ "transformers_version": "4.28.1",
165
+ "typical_p": 1.0,
166
+ "use_bfloat16": false
167
+ }
168
+ }
models/wd-1-5-b2-flax/safety_checker/flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:851a10d6a89e86dfac8397af9e09f754b6220dfa71a334c3a60c7883149e748c
3
+ size 1215939995
models/wd-1-5-b2-flax/scheduler/scheduler_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "FlaxPNDMScheduler",
3
+ "_diffusers_version": "0.16.0.dev0",
4
+ "beta_end": 0.012,
5
+ "beta_schedule": "scaled_linear",
6
+ "beta_start": 0.00085,
7
+ "clip_sample": false,
8
+ "num_train_timesteps": 1000,
9
+ "prediction_type": "v_prediction",
10
+ "set_alpha_to_one": false,
11
+ "skip_prk_steps": true,
12
+ "steps_offset": 1,
13
+ "trained_betas": null
14
+ }
models/wd-1-5-b2-flax/text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./text_encoder",
3
+ "architectures": [
4
+ "CLIPTextModel"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "dropout": 0.0,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_size": 1024,
12
+ "initializer_factor": 1.0,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 4096,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 77,
17
+ "model_type": "clip_text_model",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 23,
20
+ "pad_token_id": 1,
21
+ "projection_dim": 512,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.28.1",
24
+ "vocab_size": 49408
25
+ }
models/wd-1-5-b2-flax/text_encoder/flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:60f914bf080600a7d6678c70339679c7997d03faec449d2bd2e5269673b25762
3
+ size 1361564130
models/wd-1-5-b2-flax/tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
models/wd-1-5-b2-flax/tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "!",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
models/wd-1-5-b2-flax/tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<|startoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "clean_up_tokenization_spaces": true,
12
+ "do_lower_case": true,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "<|endoftext|>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "errors": "replace",
22
+ "model_max_length": 77,
23
+ "pad_token": "<|endoftext|>",
24
+ "tokenizer_class": "CLIPTokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<|endoftext|>",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
models/wd-1-5-b2-flax/tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
models/wd-1-5-b2-flax/unet/config.json ADDED
@@ -0,0 +1,65 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "FlaxUNet2DConditionModel",
3
+ "_diffusers_version": "0.16.0.dev0",
4
+ "_name_or_path": "./unet",
5
+ "act_fn": "silu",
6
+ "attention_head_dim": [
7
+ 5,
8
+ 10,
9
+ 20,
10
+ 20
11
+ ],
12
+ "block_out_channels": [
13
+ 320,
14
+ 640,
15
+ 1280,
16
+ 1280
17
+ ],
18
+ "center_input_sample": false,
19
+ "class_embed_type": null,
20
+ "class_embeddings_concat": false,
21
+ "conv_in_kernel": 3,
22
+ "conv_out_kernel": 3,
23
+ "cross_attention_dim": 1024,
24
+ "cross_attention_norm": null,
25
+ "down_block_types": [
26
+ "CrossAttnDownBlock2D",
27
+ "CrossAttnDownBlock2D",
28
+ "CrossAttnDownBlock2D",
29
+ "DownBlock2D"
30
+ ],
31
+ "downsample_padding": 1,
32
+ "dropout": 0.0,
33
+ "dual_cross_attention": false,
34
+ "encoder_hid_dim": null,
35
+ "flip_sin_to_cos": true,
36
+ "freq_shift": 0,
37
+ "in_channels": 4,
38
+ "layers_per_block": 2,
39
+ "mid_block_only_cross_attention": null,
40
+ "mid_block_scale_factor": 1,
41
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
42
+ "norm_eps": 1e-05,
43
+ "norm_num_groups": 32,
44
+ "num_class_embeds": null,
45
+ "only_cross_attention": false,
46
+ "out_channels": 4,
47
+ "projection_class_embeddings_input_dim": null,
48
+ "resnet_out_scale_factor": 1.0,
49
+ "resnet_skip_time_act": false,
50
+ "resnet_time_scale_shift": "default",
51
+ "sample_size": 96,
52
+ "time_cond_proj_dim": null,
53
+ "time_embedding_act_fn": null,
54
+ "time_embedding_type": "positional",
55
+ "timestep_post_act": null,
56
+ "up_block_types": [
57
+ "UpBlock2D",
58
+ "CrossAttnUpBlock2D",
59
+ "CrossAttnUpBlock2D",
60
+ "CrossAttnUpBlock2D"
61
+ ],
62
+ "upcast_attention": true,
63
+ "use_linear_projection": true,
64
+ "use_memory_efficient_attention": false
65
+ }
models/wd-1-5-b2-flax/unet/diffusion_flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:968e09645dc34b19c4d2383a5871bb62bed0cdacfc54b275721a37cacdb8913e
3
+ size 3463667343
models/wd-1-5-b2-flax/vae/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "FlaxAutoencoderKL",
3
+ "_diffusers_version": "0.16.0.dev0",
4
+ "_name_or_path": "./vae",
5
+ "act_fn": "silu",
6
+ "block_out_channels": [
7
+ 128,
8
+ 256,
9
+ 512,
10
+ 512
11
+ ],
12
+ "down_block_types": [
13
+ "DownEncoderBlock2D",
14
+ "DownEncoderBlock2D",
15
+ "DownEncoderBlock2D",
16
+ "DownEncoderBlock2D"
17
+ ],
18
+ "in_channels": 3,
19
+ "latent_channels": 4,
20
+ "layers_per_block": 2,
21
+ "norm_num_groups": 32,
22
+ "out_channels": 3,
23
+ "sample_size": 512,
24
+ "scaling_factor": 0.18215,
25
+ "up_block_types": [
26
+ "UpDecoderBlock2D",
27
+ "UpDecoderBlock2D",
28
+ "UpDecoderBlock2D",
29
+ "UpDecoderBlock2D"
30
+ ]
31
+ }
models/wd-1-5-b2-flax/vae/diffusion_flax_model.msgpack ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a0e3a4600b500f63b6e05c8d772777389990de394f896c8e0df253688b78628
3
+ size 334623853
models/wd-1-5-b2/feature_extractor/preprocessor_config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "crop_size": {
3
+ "height": 224,
4
+ "width": 224
5
+ },
6
+ "do_center_crop": true,
7
+ "do_convert_rgb": true,
8
+ "do_normalize": true,
9
+ "do_rescale": true,
10
+ "do_resize": true,
11
+ "feature_extractor_type": "CLIPFeatureExtractor",
12
+ "image_mean": [
13
+ 0.48145466,
14
+ 0.4578275,
15
+ 0.40821073
16
+ ],
17
+ "image_processor_type": "CLIPFeatureExtractor",
18
+ "image_std": [
19
+ 0.26862954,
20
+ 0.26130258,
21
+ 0.27577711
22
+ ],
23
+ "resample": 3,
24
+ "rescale_factor": 0.00392156862745098,
25
+ "size": {
26
+ "shortest_edge": 224
27
+ }
28
+ }
models/wd-1-5-b2/model_index.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.16.0.dev0",
4
+ "feature_extractor": [
5
+ "transformers",
6
+ "CLIPFeatureExtractor"
7
+ ],
8
+ "requires_safety_checker": true,
9
+ "safety_checker": [
10
+ "stable_diffusion",
11
+ "StableDiffusionSafetyChecker"
12
+ ],
13
+ "scheduler": [
14
+ "diffusers",
15
+ "PNDMScheduler"
16
+ ],
17
+ "text_encoder": [
18
+ "transformers",
19
+ "CLIPTextModel"
20
+ ],
21
+ "tokenizer": [
22
+ "transformers",
23
+ "CLIPTokenizer"
24
+ ],
25
+ "unet": [
26
+ "diffusers",
27
+ "UNet2DConditionModel"
28
+ ],
29
+ "vae": [
30
+ "diffusers",
31
+ "AutoencoderKL"
32
+ ]
33
+ }
models/wd-1-5-b2/safety_checker/config.json ADDED
@@ -0,0 +1,168 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_commit_hash": null,
3
+ "_name_or_path": "./safety_checker",
4
+ "architectures": [
5
+ "StableDiffusionSafetyChecker"
6
+ ],
7
+ "initializer_factor": 1.0,
8
+ "logit_scale_init_value": 2.6592,
9
+ "model_type": "clip",
10
+ "projection_dim": 768,
11
+ "text_config": {
12
+ "_name_or_path": "",
13
+ "add_cross_attention": false,
14
+ "architectures": null,
15
+ "attention_dropout": 0.0,
16
+ "bad_words_ids": null,
17
+ "begin_suppress_tokens": null,
18
+ "bos_token_id": 0,
19
+ "chunk_size_feed_forward": 0,
20
+ "cross_attention_hidden_size": null,
21
+ "decoder_start_token_id": null,
22
+ "diversity_penalty": 0.0,
23
+ "do_sample": false,
24
+ "dropout": 0.0,
25
+ "early_stopping": false,
26
+ "encoder_no_repeat_ngram_size": 0,
27
+ "eos_token_id": 2,
28
+ "exponential_decay_length_penalty": null,
29
+ "finetuning_task": null,
30
+ "forced_bos_token_id": null,
31
+ "forced_eos_token_id": null,
32
+ "hidden_act": "quick_gelu",
33
+ "hidden_size": 768,
34
+ "id2label": {
35
+ "0": "LABEL_0",
36
+ "1": "LABEL_1"
37
+ },
38
+ "initializer_factor": 1.0,
39
+ "initializer_range": 0.02,
40
+ "intermediate_size": 3072,
41
+ "is_decoder": false,
42
+ "is_encoder_decoder": false,
43
+ "label2id": {
44
+ "LABEL_0": 0,
45
+ "LABEL_1": 1
46
+ },
47
+ "layer_norm_eps": 1e-05,
48
+ "length_penalty": 1.0,
49
+ "max_length": 20,
50
+ "max_position_embeddings": 77,
51
+ "min_length": 0,
52
+ "model_type": "clip_text_model",
53
+ "no_repeat_ngram_size": 0,
54
+ "num_attention_heads": 12,
55
+ "num_beam_groups": 1,
56
+ "num_beams": 1,
57
+ "num_hidden_layers": 12,
58
+ "num_return_sequences": 1,
59
+ "output_attentions": false,
60
+ "output_hidden_states": false,
61
+ "output_scores": false,
62
+ "pad_token_id": 1,
63
+ "prefix": null,
64
+ "problem_type": null,
65
+ "projection_dim": 512,
66
+ "pruned_heads": {},
67
+ "remove_invalid_values": false,
68
+ "repetition_penalty": 1.0,
69
+ "return_dict": true,
70
+ "return_dict_in_generate": false,
71
+ "sep_token_id": null,
72
+ "suppress_tokens": null,
73
+ "task_specific_params": null,
74
+ "temperature": 1.0,
75
+ "tf_legacy_loss": false,
76
+ "tie_encoder_decoder": false,
77
+ "tie_word_embeddings": true,
78
+ "tokenizer_class": null,
79
+ "top_k": 50,
80
+ "top_p": 1.0,
81
+ "torch_dtype": null,
82
+ "torchscript": false,
83
+ "transformers_version": "4.28.1",
84
+ "typical_p": 1.0,
85
+ "use_bfloat16": false,
86
+ "vocab_size": 49408
87
+ },
88
+ "torch_dtype": "float32",
89
+ "transformers_version": null,
90
+ "vision_config": {
91
+ "_name_or_path": "",
92
+ "add_cross_attention": false,
93
+ "architectures": null,
94
+ "attention_dropout": 0.0,
95
+ "bad_words_ids": null,
96
+ "begin_suppress_tokens": null,
97
+ "bos_token_id": null,
98
+ "chunk_size_feed_forward": 0,
99
+ "cross_attention_hidden_size": null,
100
+ "decoder_start_token_id": null,
101
+ "diversity_penalty": 0.0,
102
+ "do_sample": false,
103
+ "dropout": 0.0,
104
+ "early_stopping": false,
105
+ "encoder_no_repeat_ngram_size": 0,
106
+ "eos_token_id": null,
107
+ "exponential_decay_length_penalty": null,
108
+ "finetuning_task": null,
109
+ "forced_bos_token_id": null,
110
+ "forced_eos_token_id": null,
111
+ "hidden_act": "quick_gelu",
112
+ "hidden_size": 1024,
113
+ "id2label": {
114
+ "0": "LABEL_0",
115
+ "1": "LABEL_1"
116
+ },
117
+ "image_size": 224,
118
+ "initializer_factor": 1.0,
119
+ "initializer_range": 0.02,
120
+ "intermediate_size": 4096,
121
+ "is_decoder": false,
122
+ "is_encoder_decoder": false,
123
+ "label2id": {
124
+ "LABEL_0": 0,
125
+ "LABEL_1": 1
126
+ },
127
+ "layer_norm_eps": 1e-05,
128
+ "length_penalty": 1.0,
129
+ "max_length": 20,
130
+ "min_length": 0,
131
+ "model_type": "clip_vision_model",
132
+ "no_repeat_ngram_size": 0,
133
+ "num_attention_heads": 16,
134
+ "num_beam_groups": 1,
135
+ "num_beams": 1,
136
+ "num_channels": 3,
137
+ "num_hidden_layers": 24,
138
+ "num_return_sequences": 1,
139
+ "output_attentions": false,
140
+ "output_hidden_states": false,
141
+ "output_scores": false,
142
+ "pad_token_id": null,
143
+ "patch_size": 14,
144
+ "prefix": null,
145
+ "problem_type": null,
146
+ "projection_dim": 512,
147
+ "pruned_heads": {},
148
+ "remove_invalid_values": false,
149
+ "repetition_penalty": 1.0,
150
+ "return_dict": true,
151
+ "return_dict_in_generate": false,
152
+ "sep_token_id": null,
153
+ "suppress_tokens": null,
154
+ "task_specific_params": null,
155
+ "temperature": 1.0,
156
+ "tf_legacy_loss": false,
157
+ "tie_encoder_decoder": false,
158
+ "tie_word_embeddings": true,
159
+ "tokenizer_class": null,
160
+ "top_k": 50,
161
+ "top_p": 1.0,
162
+ "torch_dtype": null,
163
+ "torchscript": false,
164
+ "transformers_version": "4.28.1",
165
+ "typical_p": 1.0,
166
+ "use_bfloat16": false
167
+ }
168
+ }
models/wd-1-5-b2/safety_checker/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16d28f2b37109f222cdc33620fdd262102ac32112be0352a7f77e9614b35a394
3
+ size 1216064769
models/wd-1-5-b2/scheduler/scheduler_config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "PNDMScheduler",
3
+ "_diffusers_version": "0.16.0.dev0",
4
+ "beta_end": 0.012,
5
+ "beta_schedule": "scaled_linear",
6
+ "beta_start": 0.00085,
7
+ "clip_sample": false,
8
+ "num_train_timesteps": 1000,
9
+ "prediction_type": "v_prediction",
10
+ "set_alpha_to_one": false,
11
+ "skip_prk_steps": true,
12
+ "steps_offset": 1,
13
+ "trained_betas": null
14
+ }
models/wd-1-5-b2/text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "./text_encoder",
3
+ "architectures": [
4
+ "CLIPTextModel"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 0,
8
+ "dropout": 0.0,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "gelu",
11
+ "hidden_size": 1024,
12
+ "initializer_factor": 1.0,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 4096,
15
+ "layer_norm_eps": 1e-05,
16
+ "max_position_embeddings": 77,
17
+ "model_type": "clip_text_model",
18
+ "num_attention_heads": 16,
19
+ "num_hidden_layers": 23,
20
+ "pad_token_id": 1,
21
+ "projection_dim": 512,
22
+ "torch_dtype": "float32",
23
+ "transformers_version": "4.28.1",
24
+ "vocab_size": 49408
25
+ }
models/wd-1-5-b2/text_encoder/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2188379b05015f531d61503e714234d00a64939792f3098b324e516547f0194f
3
+ size 1361674657
models/wd-1-5-b2/tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
models/wd-1-5-b2/tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|startoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "!",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
models/wd-1-5-b2/tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<|startoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "clean_up_tokenization_spaces": true,
12
+ "do_lower_case": true,
13
+ "eos_token": {
14
+ "__type": "AddedToken",
15
+ "content": "<|endoftext|>",
16
+ "lstrip": false,
17
+ "normalized": true,
18
+ "rstrip": false,
19
+ "single_word": false
20
+ },
21
+ "errors": "replace",
22
+ "model_max_length": 77,
23
+ "pad_token": "<|endoftext|>",
24
+ "tokenizer_class": "CLIPTokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<|endoftext|>",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }
models/wd-1-5-b2/tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
models/wd-1-5-b2/unet/config.json ADDED
@@ -0,0 +1,63 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.16.0.dev0",
4
+ "_name_or_path": "./unet",
5
+ "act_fn": "silu",
6
+ "attention_head_dim": [
7
+ 5,
8
+ 10,
9
+ 20,
10
+ 20
11
+ ],
12
+ "block_out_channels": [
13
+ 320,
14
+ 640,
15
+ 1280,
16
+ 1280
17
+ ],
18
+ "center_input_sample": false,
19
+ "class_embed_type": null,
20
+ "class_embeddings_concat": false,
21
+ "conv_in_kernel": 3,
22
+ "conv_out_kernel": 3,
23
+ "cross_attention_dim": 1024,
24
+ "cross_attention_norm": null,
25
+ "down_block_types": [
26
+ "CrossAttnDownBlock2D",
27
+ "CrossAttnDownBlock2D",
28
+ "CrossAttnDownBlock2D",
29
+ "DownBlock2D"
30
+ ],
31
+ "downsample_padding": 1,
32
+ "dual_cross_attention": false,
33
+ "encoder_hid_dim": null,
34
+ "flip_sin_to_cos": true,
35
+ "freq_shift": 0,
36
+ "in_channels": 4,
37
+ "layers_per_block": 2,
38
+ "mid_block_only_cross_attention": null,
39
+ "mid_block_scale_factor": 1,
40
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
41
+ "norm_eps": 1e-05,
42
+ "norm_num_groups": 32,
43
+ "num_class_embeds": null,
44
+ "only_cross_attention": false,
45
+ "out_channels": 4,
46
+ "projection_class_embeddings_input_dim": null,
47
+ "resnet_out_scale_factor": 1.0,
48
+ "resnet_skip_time_act": false,
49
+ "resnet_time_scale_shift": "default",
50
+ "sample_size": 96,
51
+ "time_cond_proj_dim": null,
52
+ "time_embedding_act_fn": null,
53
+ "time_embedding_type": "positional",
54
+ "timestep_post_act": null,
55
+ "up_block_types": [
56
+ "UpBlock2D",
57
+ "CrossAttnUpBlock2D",
58
+ "CrossAttnUpBlock2D",
59
+ "CrossAttnUpBlock2D"
60
+ ],
61
+ "upcast_attention": true,
62
+ "use_linear_projection": true
63
+ }
models/wd-1-5-b2/unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:25cb929e196c8bb9b25eab6730180931756e213b8022745bc9d7f6f603a9f70d
3
+ size 3463925093
models/wd-1-5-b2/vae/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.16.0.dev0",
4
+ "_name_or_path": "./vae",
5
+ "act_fn": "silu",
6
+ "block_out_channels": [
7
+ 128,
8
+ 256,
9
+ 512,
10
+ 512
11
+ ],
12
+ "down_block_types": [
13
+ "DownEncoderBlock2D",
14
+ "DownEncoderBlock2D",
15
+ "DownEncoderBlock2D",
16
+ "DownEncoderBlock2D"
17
+ ],
18
+ "in_channels": 3,
19
+ "latent_channels": 4,
20
+ "layers_per_block": 2,
21
+ "norm_num_groups": 32,
22
+ "out_channels": 3,
23
+ "sample_size": 512,
24
+ "scaling_factor": 0.18215,
25
+ "up_block_types": [
26
+ "UpDecoderBlock2D",
27
+ "UpDecoderBlock2D",
28
+ "UpDecoderBlock2D",
29
+ "UpDecoderBlock2D"
30
+ ]
31
+ }
models/wd-1-5-b2/vae/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e174991e5609bc5c2b3995e3f223fb2c5f0ae3be307fa9591b351d837a08770
3
+ size 334711857
requirements.txt CHANGED
@@ -1,11 +1,11 @@
1
- -f https://storage.googleapis.com/jax-releases/jax_cuda_releases.html
 
2
  jax[cuda11_pip]
 
3
  jaxlib
4
  git+https://github.com/huggingface/diffusers@main
5
- opencv-python
6
- transformers
7
- flax
8
  pillow
 
9
  torch
10
  torchvision
11
  accelerate
 
1
+ transformers
2
+ flax
3
  jax[cuda11_pip]
4
+ -f https://storage.googleapis.com/jax-releases/jax_cuda_releases.html
5
  jaxlib
6
  git+https://github.com/huggingface/diffusers@main
 
 
 
7
  pillow
8
+ opencv-python
9
  torch
10
  torchvision
11
  accelerate
wikipe_cond_2.png ADDED
wikipe_cond_3.png ADDED