discus0434 commited on
Commit
b3c25df
1 Parent(s): eb694d1

Upload StableDiffusionImg2ImgPipeline

Browse files
model_index.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "_class_name": "StableDiffusionImg2ImgPipeline",
3
  "_diffusers_version": "0.23.1",
4
- "_name_or_path": "./lcm_any_v5",
5
  "feature_extractor": [
6
  "transformers",
7
  "CLIPFeatureExtractor"
@@ -29,6 +29,6 @@
29
  ],
30
  "vae": [
31
  "diffusers",
32
- "AutoencoderKL"
33
  ]
34
  }
 
1
  {
2
  "_class_name": "StableDiffusionImg2ImgPipeline",
3
  "_diffusers_version": "0.23.1",
4
+ "_name_or_path": "stablediffusionapi/anything-v5",
5
  "feature_extractor": [
6
  "transformers",
7
  "CLIPFeatureExtractor"
 
29
  ],
30
  "vae": [
31
  "diffusers",
32
+ "AutoencoderTiny"
33
  ]
34
  }
scheduler/scheduler_config.json CHANGED
@@ -6,14 +6,14 @@
6
  "beta_start": 1e-12,
7
  "clip_sample": false,
8
  "clip_sample_range": 1.0,
9
- "dynamic_thresholding_ratio": 0.99,
10
  "num_train_timesteps": 1000,
11
  "original_inference_steps": 50,
12
  "prediction_type": "v_prediction",
13
  "rescale_betas_zero_snr": true,
14
  "sample_max_value": 1.0,
15
  "set_alpha_to_one": false,
16
- "steps_offset": 1,
17
  "thresholding": true,
18
  "timestep_scaling": 10.0,
19
  "timestep_spacing": "leading",
 
6
  "beta_start": 1e-12,
7
  "clip_sample": false,
8
  "clip_sample_range": 1.0,
9
+ "dynamic_thresholding_ratio": 0.995,
10
  "num_train_timesteps": 1000,
11
  "original_inference_steps": 50,
12
  "prediction_type": "v_prediction",
13
  "rescale_betas_zero_snr": true,
14
  "sample_max_value": 1.0,
15
  "set_alpha_to_one": false,
16
+ "steps_offset": 0,
17
  "thresholding": true,
18
  "timestep_scaling": 10.0,
19
  "timestep_spacing": "leading",
text_encoder/config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "./lcm_any_v5/text_encoder",
3
  "architectures": [
4
  "CLIPTextModel"
5
  ],
 
1
  {
2
+ "_name_or_path": "/root/.cache/huggingface/hub/models--stablediffusionapi--anything-v5/snapshots/b47165cde18e8c2b22c05b38cf5811932a0fff04/text_encoder",
3
  "architectures": [
4
  "CLIPTextModel"
5
  ],
tokenizer/special_tokens_map.json CHANGED
@@ -13,13 +13,7 @@
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
- "pad_token": {
17
- "content": "<|endoftext|>",
18
- "lstrip": false,
19
- "normalized": true,
20
- "rstrip": false,
21
- "single_word": false
22
- },
23
  "unk_token": {
24
  "content": "<|endoftext|>",
25
  "lstrip": false,
 
13
  "rstrip": false,
14
  "single_word": false
15
  },
16
+ "pad_token": "<|endoftext|>",
 
 
 
 
 
 
17
  "unk_token": {
18
  "content": "<|endoftext|>",
19
  "lstrip": false,
unet/config.json CHANGED
@@ -1,7 +1,7 @@
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
  "_diffusers_version": "0.23.1",
4
- "_name_or_path": "./lcm_any_v5/unet",
5
  "act_fn": "silu",
6
  "addition_embed_type": null,
7
  "addition_embed_type_num_heads": 64,
 
1
  {
2
  "_class_name": "UNet2DConditionModel",
3
  "_diffusers_version": "0.23.1",
4
+ "_name_or_path": "/root/.cache/huggingface/hub/models--stablediffusionapi--anything-v5/snapshots/b47165cde18e8c2b22c05b38cf5811932a0fff04/unet",
5
  "act_fn": "silu",
6
  "addition_embed_type": null,
7
  "addition_embed_type_num_heads": 64,
vae/config.json CHANGED
@@ -1,32 +1,38 @@
1
  {
2
- "_class_name": "AutoencoderKL",
3
  "_diffusers_version": "0.23.1",
4
- "_name_or_path": "./lcm_any_v5/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
- "force_upcast": true,
19
  "in_channels": 3,
20
  "latent_channels": 4,
21
- "layers_per_block": 2,
22
- "norm_num_groups": 32,
 
 
 
 
 
 
 
 
 
 
 
 
23
  "out_channels": 3,
24
- "sample_size": 512,
25
- "scaling_factor": 0.18215,
26
- "up_block_types": [
27
- "UpDecoderBlock2D",
28
- "UpDecoderBlock2D",
29
- "UpDecoderBlock2D",
30
- "UpDecoderBlock2D"
31
- ]
32
  }
 
1
  {
2
+ "_class_name": "AutoencoderTiny",
3
  "_diffusers_version": "0.23.1",
4
+ "_name_or_path": "madebyollin/taesd",
5
+ "act_fn": "relu",
6
+ "decoder_block_out_channels": [
7
+ 64,
8
+ 64,
9
+ 64,
10
+ 64
11
  ],
12
+ "encoder_block_out_channels": [
13
+ 64,
14
+ 64,
15
+ 64,
16
+ 64
17
  ],
18
+ "force_upcast": false,
19
  "in_channels": 3,
20
  "latent_channels": 4,
21
+ "latent_magnitude": 3,
22
+ "latent_shift": 0.5,
23
+ "num_decoder_blocks": [
24
+ 3,
25
+ 3,
26
+ 3,
27
+ 1
28
+ ],
29
+ "num_encoder_blocks": [
30
+ 1,
31
+ 3,
32
+ 3,
33
+ 3
34
+ ],
35
  "out_channels": 3,
36
+ "scaling_factor": 1.0,
37
+ "upsampling_scaling_factor": 2
 
 
 
 
 
 
38
  }
vae/diffusion_pytorch_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:97d91e545cafc829a2168479a1ca1cb02be404e3a26c9ff4d6f5ba2ed2dbcf17
3
- size 334643268
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2183b8f7c963176bcb3ee6ecf54fc7d5bca22b9466465afdbb6b12b9a0785d2c
3
+ size 9793292