Hugging Face's logo

holwech
/
realistic-vision-5_1-optimized

Text-to-Image
Diffusers
Safetensors
StableDiffusionPipeline
Model card Files
xet
Community
holwech commited on
Commit
32badc6
·
1 Parent(s): 188568f

Add inpainting

Browse files
Files changed (39) hide show
  1. model_index.json +0 -33
  2. realistic_vision_5_1/feature_extractor/preprocessor_config.json +28 -0
  3. realistic_vision_5_1/model_index.json +33 -0
  4. realistic_vision_5_1/safety_checker/config.json +28 -0
  5. {text_encoder → realistic_vision_5_1/safety_checker}/model.fp16.safetensors +2 -2
  6. Realistic_Vision_V5.1_fp16-no-ema-inpainting.safetensors → realistic_vision_5_1/safety_checker/model.safetensors +2 -2
  7. {scheduler → realistic_vision_5_1/scheduler}/scheduler_config.json +5 -3
  8. {text_encoder → realistic_vision_5_1/text_encoder}/config.json +2 -3
  9. Realistic_Vision_V5.1_fp16-no-ema.safetensors → realistic_vision_5_1/text_encoder/model.fp16.safetensors +2 -2
  10. realistic_vision_5_1/text_encoder/model.safetensors +3 -0
  11. {tokenizer → realistic_vision_5_1/tokenizer}/merges.txt +0 -0
  12. {tokenizer → realistic_vision_5_1/tokenizer}/special_tokens_map.json +0 -0
  13. {tokenizer → realistic_vision_5_1/tokenizer}/tokenizer_config.json +1 -2
  14. {tokenizer → realistic_vision_5_1/tokenizer}/vocab.json +0 -0
  15. {unet → realistic_vision_5_1/unet}/config.json +32 -2
  16. {unet → realistic_vision_5_1/unet}/diffusion_pytorch_model.fp16.safetensors +1 -1
  17. realistic_vision_5_1/unet/diffusion_pytorch_model.safetensors +3 -0
  18. {vae → realistic_vision_5_1/vae}/config.json +3 -1
  19. {vae → realistic_vision_5_1/vae}/diffusion_pytorch_model.fp16.safetensors +1 -1
  20. realistic_vision_5_1/vae/diffusion_pytorch_model.safetensors +3 -0
  21. realistic_vision_5_1_inpainting/feature_extractor/preprocessor_config.json +28 -0
  22. realistic_vision_5_1_inpainting/model_index.json +33 -0
  23. realistic_vision_5_1_inpainting/safety_checker/config.json +28 -0
  24. realistic_vision_5_1_inpainting/safety_checker/model.fp16.safetensors +3 -0
  25. realistic_vision_5_1_inpainting/safety_checker/model.safetensors +3 -0
  26. realistic_vision_5_1_inpainting/scheduler/scheduler_config.json +15 -0
  27. realistic_vision_5_1_inpainting/text_encoder/config.json +24 -0
  28. realistic_vision_5_1_inpainting/text_encoder/model.fp16.safetensors +3 -0
  29. realistic_vision_5_1_inpainting/text_encoder/model.safetensors +3 -0
  30. realistic_vision_5_1_inpainting/tokenizer/merges.txt +0 -0
  31. realistic_vision_5_1_inpainting/tokenizer/special_tokens_map.json +24 -0
  32. realistic_vision_5_1_inpainting/tokenizer/tokenizer_config.json +33 -0
  33. realistic_vision_5_1_inpainting/tokenizer/vocab.json +0 -0
  34. realistic_vision_5_1_inpainting/unet/config.json +66 -0
  35. realistic_vision_5_1_inpainting/unet/diffusion_pytorch_model.fp16.safetensors +3 -0
  36. realistic_vision_5_1_inpainting/unet/diffusion_pytorch_model.safetensors +3 -0
  37. realistic_vision_5_1_inpainting/vae/config.json +31 -0
  38. realistic_vision_5_1_inpainting/vae/diffusion_pytorch_model.fp16.safetensors +3 -0
  39. realistic_vision_5_1_inpainting/vae/diffusion_pytorch_model.safetensors +3 -0
model_index.json DELETED
@@ -1,33 +0,0 @@
1
- {
2
- "_class_name": "StableDiffusionPipeline",
3
- "_diffusers_version": "0.16.1",
4
- "feature_extractor": [
5
- null,
6
- null
7
- ],
8
- "requires_safety_checker": null,
9
- "safety_checker": [
10
- null,
11
- null
12
- ],
13
- "scheduler": [
14
- "diffusers",
15
- "DEISMultistepScheduler"
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
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
realistic_vision_5_1/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
+ }
realistic_vision_5_1/model_index.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.21.0.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
+ }
realistic_vision_5_1/safety_checker/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "CompVis/stable-diffusion-safety-checker",
3
+ "architectures": [
4
+ "StableDiffusionSafetyChecker"
5
+ ],
6
+ "initializer_factor": 1.0,
7
+ "logit_scale_init_value": 2.6592,
8
+ "model_type": "clip",
9
+ "projection_dim": 768,
10
+ "text_config": {
11
+ "dropout": 0.0,
12
+ "hidden_size": 768,
13
+ "intermediate_size": 3072,
14
+ "model_type": "clip_text_model",
15
+ "num_attention_heads": 12
16
+ },
17
+ "torch_dtype": "float16",
18
+ "transformers_version": "4.33.1",
19
+ "vision_config": {
20
+ "dropout": 0.0,
21
+ "hidden_size": 1024,
22
+ "intermediate_size": 4096,
23
+ "model_type": "clip_vision_model",
24
+ "num_attention_heads": 16,
25
+ "num_hidden_layers": 24,
26
+ "patch_size": 14
27
+ }
28
+ }
{text_encoder → realistic_vision_5_1/safety_checker}/model.fp16.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:77795e2023adcf39bc29a884661950380bd093cf0750a966d473d1718dc9ef4e
3
- size 246144864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57ecdfa243b170f9b4cb3eefaf0f64552ef78fc0bf0eb1c5b9675308447184f6
3
+ size 608016280
Realistic_Vision_V5.1_fp16-no-ema-inpainting.safetensors → realistic_vision_5_1/safety_checker/model.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dbcf026dd6498122e239b06fa83a2cecca9e3ce2a39f50bef000594bd2b28ad2
3
- size 2132679782
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb351a5ded815c3ff744968ad9c6b218d071b9d313d04f35e813b84b4c0ffde8
3
+ size 1215979664
{scheduler → realistic_vision_5_1/scheduler}/scheduler_config.json RENAMED
@@ -1,13 +1,15 @@
1
  {
2
  "_class_name": "PNDMScheduler",
3
- "_diffusers_version": "0.6.0",
4
  "beta_end": 0.012,
5
  "beta_schedule": "scaled_linear",
6
  "beta_start": 0.00085,
 
7
  "num_train_timesteps": 1000,
 
8
  "set_alpha_to_one": false,
9
  "skip_prk_steps": true,
10
  "steps_offset": 1,
11
- "trained_betas": null,
12
- "clip_sample": false
13
  }
 
1
  {
2
  "_class_name": "PNDMScheduler",
3
+ "_diffusers_version": "0.21.0.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": "epsilon",
10
  "set_alpha_to_one": false,
11
  "skip_prk_steps": true,
12
  "steps_offset": 1,
13
+ "timestep_spacing": "leading",
14
+ "trained_betas": null
15
  }
{text_encoder → realistic_vision_5_1/text_encoder}/config.json RENAMED
@@ -1,5 +1,4 @@
1
  {
2
- "_name_or_path": "openai/clip-vit-large-patch14",
3
  "architectures": [
4
  "CLIPTextModel"
5
  ],
@@ -19,7 +18,7 @@
19
  "num_hidden_layers": 12,
20
  "pad_token_id": 1,
21
  "projection_dim": 768,
22
- "torch_dtype": "float32",
23
- "transformers_version": "4.22.0.dev0",
24
  "vocab_size": 49408
25
  }
 
1
  {
 
2
  "architectures": [
3
  "CLIPTextModel"
4
  ],
 
18
  "num_hidden_layers": 12,
19
  "pad_token_id": 1,
20
  "projection_dim": 768,
21
+ "torch_dtype": "float16",
22
+ "transformers_version": "4.33.1",
23
  "vocab_size": 49408
24
  }
Realistic_Vision_V5.1_fp16-no-ema.safetensors → realistic_vision_5_1/text_encoder/model.fp16.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:99a75a901f4fec732056930a89fa34cf360f6f72d75ce5bf333ddf82adf8dd2a
3
- size 2132625894
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9706025d0e3053a3cdcc7e6cfa495c5ad951267a29ad08644aadb684ae217e7e
3
+ size 246144152
realistic_vision_5_1/text_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4f27c4bde308a8aa337ce755e2af288757d86309d74b29b0bd1a3f5d6092864
3
+ size 492265168
{tokenizer → realistic_vision_5_1/tokenizer}/merges.txt RENAMED
File without changes
{tokenizer → realistic_vision_5_1/tokenizer}/special_tokens_map.json RENAMED
File without changes
{tokenizer → realistic_vision_5_1/tokenizer}/tokenizer_config.json RENAMED
@@ -8,6 +8,7 @@
8
  "rstrip": false,
9
  "single_word": false
10
  },
 
11
  "do_lower_case": true,
12
  "eos_token": {
13
  "__type": "AddedToken",
@@ -19,9 +20,7 @@
19
  },
20
  "errors": "replace",
21
  "model_max_length": 77,
22
- "name_or_path": "openai/clip-vit-large-patch14",
23
  "pad_token": "<|endoftext|>",
24
- "special_tokens_map_file": "./special_tokens_map.json",
25
  "tokenizer_class": "CLIPTokenizer",
26
  "unk_token": {
27
  "__type": "AddedToken",
 
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",
 
20
  },
21
  "errors": "replace",
22
  "model_max_length": 77,
 
23
  "pad_token": "<|endoftext|>",
 
24
  "tokenizer_class": "CLIPTokenizer",
25
  "unk_token": {
26
  "__type": "AddedToken",
{tokenizer → realistic_vision_5_1/tokenizer}/vocab.json RENAMED
File without changes
{unet → realistic_vision_5_1/unet}/config.json RENAMED
@@ -1,8 +1,12 @@
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
- "_diffusers_version": "0.6.0",
4
  "act_fn": "silu",
 
 
 
5
  "attention_head_dim": 8,
 
6
  "block_out_channels": [
7
  320,
8
  640,
@@ -10,7 +14,12 @@
10
  1280
11
  ],
12
  "center_input_sample": false,
 
 
 
 
13
  "cross_attention_dim": 768,
 
14
  "down_block_types": [
15
  "CrossAttnDownBlock2D",
16
  "CrossAttnDownBlock2D",
@@ -18,19 +27,40 @@
18
  "DownBlock2D"
19
  ],
20
  "downsample_padding": 1,
 
 
 
 
21
  "flip_sin_to_cos": true,
22
  "freq_shift": 0,
23
  "in_channels": 4,
24
  "layers_per_block": 2,
 
25
  "mid_block_scale_factor": 1,
 
26
  "norm_eps": 1e-05,
27
  "norm_num_groups": 32,
 
 
 
28
  "out_channels": 4,
 
 
 
 
29
  "sample_size": 64,
 
 
 
 
 
 
30
  "up_block_types": [
31
  "UpBlock2D",
32
  "CrossAttnUpBlock2D",
33
  "CrossAttnUpBlock2D",
34
  "CrossAttnUpBlock2D"
35
- ]
 
 
36
  }
 
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.21.0.dev0",
4
  "act_fn": "silu",
5
+ "addition_embed_type": null,
6
+ "addition_embed_type_num_heads": 64,
7
+ "addition_time_embed_dim": null,
8
  "attention_head_dim": 8,
9
+ "attention_type": "default",
10
  "block_out_channels": [
11
  320,
12
  640,
 
14
  1280
15
  ],
16
  "center_input_sample": false,
17
+ "class_embed_type": null,
18
+ "class_embeddings_concat": false,
19
+ "conv_in_kernel": 3,
20
+ "conv_out_kernel": 3,
21
  "cross_attention_dim": 768,
22
+ "cross_attention_norm": null,
23
  "down_block_types": [
24
  "CrossAttnDownBlock2D",
25
  "CrossAttnDownBlock2D",
 
27
  "DownBlock2D"
28
  ],
29
  "downsample_padding": 1,
30
+ "dropout": 0.0,
31
+ "dual_cross_attention": false,
32
+ "encoder_hid_dim": null,
33
+ "encoder_hid_dim_type": 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_attention_heads": null,
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": 64,
52
+ "time_cond_proj_dim": null,
53
+ "time_embedding_act_fn": null,
54
+ "time_embedding_dim": null,
55
+ "time_embedding_type": "positional",
56
+ "timestep_post_act": null,
57
+ "transformer_layers_per_block": 1,
58
  "up_block_types": [
59
  "UpBlock2D",
60
  "CrossAttnUpBlock2D",
61
  "CrossAttnUpBlock2D",
62
  "CrossAttnUpBlock2D"
63
+ ],
64
+ "upcast_attention": null,
65
+ "use_linear_projection": false
66
  }
{unet → realistic_vision_5_1/unet}/diffusion_pytorch_model.fp16.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c83908253f9a64d08c25fc90874c9c8aef9a329ce1ca5fb909d73b0c83d1ea21
3
  size 1719125304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c150f632d0c2338a50224504fa238f716cf50fb680897b0330563d2ff7bbf0e7
3
  size 1719125304
realistic_vision_5_1/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e0868e8fcae7d4ea8f8cdd3051704b3b47d741dc8e8629552d1a07f6efb8e32
3
+ size 3438167536
{vae → realistic_vision_5_1/vae}/config.json RENAMED
@@ -1,6 +1,6 @@
1
  {
2
  "_class_name": "AutoencoderKL",
3
- "_diffusers_version": "0.6.0",
4
  "act_fn": "silu",
5
  "block_out_channels": [
6
  128,
@@ -14,12 +14,14 @@
14
  "DownEncoderBlock2D",
15
  "DownEncoderBlock2D"
16
  ],
 
17
  "in_channels": 3,
18
  "latent_channels": 4,
19
  "layers_per_block": 2,
20
  "norm_num_groups": 32,
21
  "out_channels": 3,
22
  "sample_size": 512,
 
23
  "up_block_types": [
24
  "UpDecoderBlock2D",
25
  "UpDecoderBlock2D",
 
1
  {
2
  "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.21.0.dev0",
4
  "act_fn": "silu",
5
  "block_out_channels": [
6
  128,
 
14
  "DownEncoderBlock2D",
15
  "DownEncoderBlock2D"
16
  ],
17
+ "force_upcast": true,
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",
{vae → realistic_vision_5_1/vae}/diffusion_pytorch_model.fp16.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4fbcf0ebe55a0984f5a5e00d8c4521d52359af7229bb4d81890039d2aa16dd7c
3
  size 167335342
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:249bd6adf5e03a78cfbc21c689b08f9e285fa49fa81f2cf9ff175c6272a2740a
3
  size 167335342
realistic_vision_5_1/vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86a6170968f284b6c0c111e2611c806a04102e2a48790ebd1d490ca78040d2bb
3
+ size 334643268
realistic_vision_5_1_inpainting/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
+ }
realistic_vision_5_1_inpainting/model_index.json ADDED
@@ -0,0 +1,33 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableDiffusionInpaintPipeline",
3
+ "_diffusers_version": "0.21.0.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
+ }
realistic_vision_5_1_inpainting/safety_checker/config.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "CompVis/stable-diffusion-safety-checker",
3
+ "architectures": [
4
+ "StableDiffusionSafetyChecker"
5
+ ],
6
+ "initializer_factor": 1.0,
7
+ "logit_scale_init_value": 2.6592,
8
+ "model_type": "clip",
9
+ "projection_dim": 768,
10
+ "text_config": {
11
+ "dropout": 0.0,
12
+ "hidden_size": 768,
13
+ "intermediate_size": 3072,
14
+ "model_type": "clip_text_model",
15
+ "num_attention_heads": 12
16
+ },
17
+ "torch_dtype": "float16",
18
+ "transformers_version": "4.33.1",
19
+ "vision_config": {
20
+ "dropout": 0.0,
21
+ "hidden_size": 1024,
22
+ "intermediate_size": 4096,
23
+ "model_type": "clip_vision_model",
24
+ "num_attention_heads": 16,
25
+ "num_hidden_layers": 24,
26
+ "patch_size": 14
27
+ }
28
+ }
realistic_vision_5_1_inpainting/safety_checker/model.fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57ecdfa243b170f9b4cb3eefaf0f64552ef78fc0bf0eb1c5b9675308447184f6
3
+ size 608016280
realistic_vision_5_1_inpainting/safety_checker/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb351a5ded815c3ff744968ad9c6b218d071b9d313d04f35e813b84b4c0ffde8
3
+ size 1215979664
realistic_vision_5_1_inpainting/scheduler/scheduler_config.json ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "PNDMScheduler",
3
+ "_diffusers_version": "0.21.0.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": "epsilon",
10
+ "set_alpha_to_one": false,
11
+ "skip_prk_steps": true,
12
+ "steps_offset": 1,
13
+ "timestep_spacing": "leading",
14
+ "trained_betas": null
15
+ }
realistic_vision_5_1_inpainting/text_encoder/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "CLIPTextModel"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 0,
7
+ "dropout": 0.0,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "quick_gelu",
10
+ "hidden_size": 768,
11
+ "initializer_factor": 1.0,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 3072,
14
+ "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 77,
16
+ "model_type": "clip_text_model",
17
+ "num_attention_heads": 12,
18
+ "num_hidden_layers": 12,
19
+ "pad_token_id": 1,
20
+ "projection_dim": 768,
21
+ "torch_dtype": "float16",
22
+ "transformers_version": "4.33.1",
23
+ "vocab_size": 49408
24
+ }
realistic_vision_5_1_inpainting/text_encoder/model.fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a77608104b279703317830942b32629f8cfc5c831223b2edc494668fdf53c24
3
+ size 246144152
realistic_vision_5_1_inpainting/text_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:638b2e278b4c4398458f0fd426811ba3ff628383c51b4944f20f5a41ea35a36e
3
+ size 492265168
realistic_vision_5_1_inpainting/tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
realistic_vision_5_1_inpainting/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": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
realistic_vision_5_1_inpainting/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
+ }
realistic_vision_5_1_inpainting/tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
realistic_vision_5_1_inpainting/unet/config.json ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.21.0.dev0",
4
+ "act_fn": "silu",
5
+ "addition_embed_type": null,
6
+ "addition_embed_type_num_heads": 64,
7
+ "addition_time_embed_dim": null,
8
+ "attention_head_dim": 8,
9
+ "attention_type": "default",
10
+ "block_out_channels": [
11
+ 320,
12
+ 640,
13
+ 1280,
14
+ 1280
15
+ ],
16
+ "center_input_sample": false,
17
+ "class_embed_type": null,
18
+ "class_embeddings_concat": false,
19
+ "conv_in_kernel": 3,
20
+ "conv_out_kernel": 3,
21
+ "cross_attention_dim": 768,
22
+ "cross_attention_norm": null,
23
+ "down_block_types": [
24
+ "CrossAttnDownBlock2D",
25
+ "CrossAttnDownBlock2D",
26
+ "CrossAttnDownBlock2D",
27
+ "DownBlock2D"
28
+ ],
29
+ "downsample_padding": 1,
30
+ "dropout": 0.0,
31
+ "dual_cross_attention": false,
32
+ "encoder_hid_dim": null,
33
+ "encoder_hid_dim_type": null,
34
+ "flip_sin_to_cos": true,
35
+ "freq_shift": 0,
36
+ "in_channels": 9,
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_attention_heads": null,
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": 64,
52
+ "time_cond_proj_dim": null,
53
+ "time_embedding_act_fn": null,
54
+ "time_embedding_dim": null,
55
+ "time_embedding_type": "positional",
56
+ "timestep_post_act": null,
57
+ "transformer_layers_per_block": 1,
58
+ "up_block_types": [
59
+ "UpBlock2D",
60
+ "CrossAttnUpBlock2D",
61
+ "CrossAttnUpBlock2D",
62
+ "CrossAttnUpBlock2D"
63
+ ],
64
+ "upcast_attention": null,
65
+ "use_linear_projection": false
66
+ }
realistic_vision_5_1_inpainting/unet/diffusion_pytorch_model.fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:933f6f5ff322ca3cec10439452d3a2687ea16ac6489a6b6ebaa447c73aeab399
3
+ size 1719154104
realistic_vision_5_1_inpainting/unet/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:953a65377fede97e25e58a116056d3bafeb5b48b339db1c04227aecb062a4a98
3
+ size 3438225152
realistic_vision_5_1_inpainting/vae/config.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.21.0.dev0",
4
+ "act_fn": "silu",
5
+ "block_out_channels": [
6
+ 128,
7
+ 256,
8
+ 512,
9
+ 512
10
+ ],
11
+ "down_block_types": [
12
+ "DownEncoderBlock2D",
13
+ "DownEncoderBlock2D",
14
+ "DownEncoderBlock2D",
15
+ "DownEncoderBlock2D"
16
+ ],
17
+ "force_upcast": true,
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
+ }
realistic_vision_5_1_inpainting/vae/diffusion_pytorch_model.fp16.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4b76e590e51dcf243df63d4dedc066056cd3128328de2b3e31148c38ce328a4
3
+ size 167335342
realistic_vision_5_1_inpainting/vae/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf79c737435027af721820bd5b0addd32b76fe3026db2ea4360e5e899f62e843
3
+ size 334643268