feature_extractor/preprocessor_config.json CHANGED
@@ -1,8 +1,12 @@
1
  {
2
- "crop_size": 224,
 
 
 
3
  "do_center_crop": true,
4
  "do_convert_rgb": true,
5
  "do_normalize": true,
 
6
  "do_resize": true,
7
  "feature_extractor_type": "CLIPFeatureExtractor",
8
  "image_mean": [
@@ -10,11 +14,15 @@
10
  0.4578275,
11
  0.40821073
12
  ],
 
13
  "image_std": [
14
  0.26862954,
15
  0.26130258,
16
  0.27577711
17
  ],
18
  "resample": 3,
19
- "size": 224
 
 
 
20
  }
 
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": [
 
14
  0.4578275,
15
  0.40821073
16
  ],
17
+ "image_processor_type": "CLIPImageProcessor",
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
  }
model_index.json CHANGED
@@ -1,10 +1,11 @@
1
  {
2
  "_class_name": "StableDiffusionPipeline",
3
- "_diffusers_version": "0.8.0.dev0",
4
  "feature_extractor": [
5
  "transformers",
6
- "CLIPFeatureExtractor"
7
  ],
 
8
  "safety_checker": [
9
  "stable_diffusion",
10
  "StableDiffusionSafetyChecker"
 
1
  {
2
  "_class_name": "StableDiffusionPipeline",
3
+ "_diffusers_version": "0.10.2",
4
  "feature_extractor": [
5
  "transformers",
6
+ "CLIPImageProcessor"
7
  ],
8
+ "requires_safety_checker": true,
9
  "safety_checker": [
10
  "stable_diffusion",
11
  "StableDiffusionSafetyChecker"
safety_checker/config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_commit_hash": "4bb648a606ef040e7685bde262611766a5fdd67b",
3
  "_name_or_path": "CompVis/stable-diffusion-safety-checker",
4
  "architectures": [
5
  "StableDiffusionSafetyChecker"
@@ -62,6 +62,7 @@
62
  "pad_token_id": 1,
63
  "prefix": null,
64
  "problem_type": null,
 
65
  "pruned_heads": {},
66
  "remove_invalid_values": false,
67
  "repetition_penalty": 1.0,
@@ -79,7 +80,7 @@
79
  "top_p": 1.0,
80
  "torch_dtype": null,
81
  "torchscript": false,
82
- "transformers_version": "4.24.0",
83
  "typical_p": 1.0,
84
  "use_bfloat16": false,
85
  "vocab_size": 49408
@@ -90,7 +91,7 @@
90
  "num_attention_heads": 12,
91
  "num_hidden_layers": 12
92
  },
93
- "torch_dtype": "float32",
94
  "transformers_version": null,
95
  "vision_config": {
96
  "_name_or_path": "",
@@ -148,6 +149,7 @@
148
  "patch_size": 14,
149
  "prefix": null,
150
  "problem_type": null,
 
151
  "pruned_heads": {},
152
  "remove_invalid_values": false,
153
  "repetition_penalty": 1.0,
@@ -165,7 +167,7 @@
165
  "top_p": 1.0,
166
  "torch_dtype": null,
167
  "torchscript": false,
168
- "transformers_version": "4.24.0",
169
  "typical_p": 1.0,
170
  "use_bfloat16": false
171
  },
 
1
  {
2
+ "_commit_hash": null,
3
  "_name_or_path": "CompVis/stable-diffusion-safety-checker",
4
  "architectures": [
5
  "StableDiffusionSafetyChecker"
 
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,
 
80
  "top_p": 1.0,
81
  "torch_dtype": null,
82
  "torchscript": false,
83
+ "transformers_version": "4.25.1",
84
  "typical_p": 1.0,
85
  "use_bfloat16": false,
86
  "vocab_size": 49408
 
91
  "num_attention_heads": 12,
92
  "num_hidden_layers": 12
93
  },
94
+ "torch_dtype": "float16",
95
  "transformers_version": null,
96
  "vision_config": {
97
  "_name_or_path": "",
 
149
  "patch_size": 14,
150
  "prefix": null,
151
  "problem_type": null,
152
+ "projection_dim": 512,
153
  "pruned_heads": {},
154
  "remove_invalid_values": false,
155
  "repetition_penalty": 1.0,
 
167
  "top_p": 1.0,
168
  "torch_dtype": null,
169
  "torchscript": false,
170
+ "transformers_version": "4.25.1",
171
  "typical_p": 1.0,
172
  "use_bfloat16": false
173
  },
text_encoder/pytorch_model.bin β†’ safety_checker/model.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90cacd05ab6f5dc1989fea6b114897494f6f0c3a6a00399d4fce4210ff6f066b
3
- size 492307041
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69c4f8737c7620a738704911a1c7be4dce7bad37bead09e9e499da8810ffb26d
3
+ size 608018446
scheduler/scheduler_config.json CHANGED
@@ -1,11 +1,12 @@
1
  {
2
  "_class_name": "PNDMScheduler",
3
- "_diffusers_version": "0.8.0.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
  "set_alpha_to_one": false,
10
  "skip_prk_steps": true,
11
  "steps_offset": 1,
 
1
  {
2
  "_class_name": "PNDMScheduler",
3
+ "_diffusers_version": "0.10.2",
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,
text_encoder/config.json CHANGED
@@ -19,7 +19,7 @@
19
  "num_hidden_layers": 12,
20
  "pad_token_id": 1,
21
  "projection_dim": 768,
22
- "torch_dtype": "float32",
23
- "transformers_version": "4.24.0",
24
  "vocab_size": 49408
25
  }
 
19
  "num_hidden_layers": 12,
20
  "pad_token_id": 1,
21
  "projection_dim": 768,
22
+ "torch_dtype": "float16",
23
+ "transformers_version": "4.25.1",
24
  "vocab_size": 49408
25
  }
vae/diffusion_pytorch_model.bin β†’ text_encoder/model.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:36bb8e1b54aba3a0914eb35fba13dcb107e9f18d379d1df2158732cd4bf56a94
3
- size 334711857
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:194dbd7d114894558b4223ebbec17b285693c6bc961daad53ee4cff7be1449d5
3
+ size 246144867
unet/config.json CHANGED
@@ -1,6 +1,7 @@
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
- "_diffusers_version": "0.8.0.dev0",
 
4
  "act_fn": "silu",
5
  "attention_head_dim": 8,
6
  "block_out_channels": [
@@ -18,6 +19,7 @@
18
  "DownBlock2D"
19
  ],
20
  "downsample_padding": 1,
 
21
  "flip_sin_to_cos": true,
22
  "freq_shift": 0,
23
  "in_channels": 4,
@@ -25,12 +27,16 @@
25
  "mid_block_scale_factor": 1,
26
  "norm_eps": 1e-05,
27
  "norm_num_groups": 32,
 
 
28
  "out_channels": 4,
29
- "sample_size": 32,
30
  "up_block_types": [
31
  "UpBlock2D",
32
  "CrossAttnUpBlock2D",
33
  "CrossAttnUpBlock2D",
34
  "CrossAttnUpBlock2D"
35
- ]
 
 
36
  }
 
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.10.2",
4
+ "_name_or_path": "./unet",
5
  "act_fn": "silu",
6
  "attention_head_dim": 8,
7
  "block_out_channels": [
 
19
  "DownBlock2D"
20
  ],
21
  "downsample_padding": 1,
22
+ "dual_cross_attention": false,
23
  "flip_sin_to_cos": true,
24
  "freq_shift": 0,
25
  "in_channels": 4,
 
27
  "mid_block_scale_factor": 1,
28
  "norm_eps": 1e-05,
29
  "norm_num_groups": 32,
30
+ "num_class_embeds": null,
31
+ "only_cross_attention": false,
32
  "out_channels": 4,
33
+ "sample_size": 64,
34
  "up_block_types": [
35
  "UpBlock2D",
36
  "CrossAttnUpBlock2D",
37
  "CrossAttnUpBlock2D",
38
  "CrossAttnUpBlock2D"
39
+ ],
40
+ "upcast_attention": false,
41
+ "use_linear_projection": false
42
  }
safety_checker/pytorch_model.bin β†’ unet/diffusion_pytorch_model.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:16d28f2b37109f222cdc33620fdd262102ac32112be0352a7f77e9614b35a394
3
- size 1216064769
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb9fdfd114ce091c10b4de5a71dbec96b32e07beae937b71429504cd4f13b969
3
+ size 1719125271
vae/config.json CHANGED
@@ -1,6 +1,7 @@
1
  {
2
  "_class_name": "AutoencoderKL",
3
- "_diffusers_version": "0.8.0.dev0",
 
4
  "act_fn": "silu",
5
  "block_out_channels": [
6
  128,
@@ -19,7 +20,7 @@
19
  "layers_per_block": 2,
20
  "norm_num_groups": 32,
21
  "out_channels": 3,
22
- "sample_size": 256,
23
  "up_block_types": [
24
  "UpDecoderBlock2D",
25
  "UpDecoderBlock2D",
 
1
  {
2
  "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.10.2",
4
+ "_name_or_path": "./vae",
5
  "act_fn": "silu",
6
  "block_out_channels": [
7
  128,
 
20
  "layers_per_block": 2,
21
  "norm_num_groups": 32,
22
  "out_channels": 3,
23
+ "sample_size": 512,
24
  "up_block_types": [
25
  "UpDecoderBlock2D",
26
  "UpDecoderBlock2D",
unet/diffusion_pytorch_model.bin β†’ vae/diffusion_pytorch_model.safetensors RENAMED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f9eed11e55d4f2d281f059d83a305b19ca90baac9b3179b3b65026cf18db22f3
3
- size 3438366373
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11e897bda3163f66848a4abe4613001d27502c985c84d33eb10e7387f9010a2c
3
+ size 167335315