patrickvonplaten commited on
Commit
98e7cdf
1 Parent(s): 48abcc4
feature_extractor/preprocessor_config.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "image_mean": [
12
+ 0.48145466,
13
+ 0.4578275,
14
+ 0.40821073
15
+ ],
16
+ "image_processor_type": "CLIPImageProcessor",
17
+ "image_std": [
18
+ 0.26862954,
19
+ 0.26130258,
20
+ 0.27577711
21
+ ],
22
+ "resample": 3,
23
+ "rescale_factor": 0.00392156862745098,
24
+ "size": {
25
+ "shortest_edge": 224
26
+ }
27
+ }
image_encoder/config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai/clip-vit-large-patch14",
3
+ "architectures": [
4
+ "CLIPVisionModelWithProjection"
5
+ ],
6
+ "attention_dropout": 0.0,
7
+ "dropout": 0.0,
8
+ "hidden_act": "quick_gelu",
9
+ "hidden_size": 1024,
10
+ "image_size": 224,
11
+ "initializer_factor": 1.0,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 4096,
14
+ "layer_norm_eps": 1e-05,
15
+ "model_type": "clip_vision_model",
16
+ "num_attention_heads": 16,
17
+ "num_channels": 3,
18
+ "num_hidden_layers": 24,
19
+ "patch_size": 14,
20
+ "projection_dim": 768,
21
+ "torch_dtype": "float32",
22
+ "transformers_version": "4.28.0.dev0"
23
+ }
image_encoder/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c304e9a1c99835f6c2d355cbb5438e7e6204d4903b2f1b056120be4bd5050f1f
3
+ size 1215996977
image_noising_scheduler/scheduler_config.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "DDPMScheduler",
3
+ "_diffusers_version": "0.15.0.dev0",
4
+ "beta_end": 0.02,
5
+ "beta_schedule": "squaredcos_cap_v2",
6
+ "beta_start": 0.0001,
7
+ "clip_sample": true,
8
+ "clip_sample_range": 1.0,
9
+ "dynamic_thresholding_ratio": 0.995,
10
+ "num_train_timesteps": 1000,
11
+ "prediction_type": "epsilon",
12
+ "sample_max_value": 1.0,
13
+ "thresholding": false,
14
+ "trained_betas": null,
15
+ "variance_type": "fixed_small"
16
+ }
image_normalizer/config.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableUnCLIPImageNormalizer",
3
+ "_diffusers_version": "0.15.0.dev0",
4
+ "embedding_dim": 768
5
+ }
image_normalizer/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68f8c892a0df2c64cb99cb7ffb826d2e7dac3775683fdd5a7436c25495a2a319
3
+ size 7335
model_index.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableUnCLIPImg2ImgPipeline",
3
+ "_diffusers_version": "0.15.0.dev0",
4
+ "feature_extractor": [
5
+ "transformers",
6
+ "CLIPImageProcessor"
7
+ ],
8
+ "image_encoder": [
9
+ "transformers",
10
+ "CLIPVisionModelWithProjection"
11
+ ],
12
+ "image_noising_scheduler": [
13
+ "diffusers",
14
+ "DDPMScheduler"
15
+ ],
16
+ "image_normalizer": [
17
+ "stable_diffusion",
18
+ "StableUnCLIPImageNormalizer"
19
+ ],
20
+ "scheduler": [
21
+ "diffusers",
22
+ "PNDMScheduler"
23
+ ],
24
+ "text_encoder": [
25
+ "transformers",
26
+ "CLIPTextModel"
27
+ ],
28
+ "tokenizer": [
29
+ "transformers",
30
+ "CLIPTokenizer"
31
+ ],
32
+ "unet": [
33
+ "diffusers",
34
+ "UNet2DConditionModel"
35
+ ],
36
+ "vae": [
37
+ "diffusers",
38
+ "AutoencoderKL"
39
+ ]
40
+ }
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,18 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "PNDMScheduler",
3
+ "_diffusers_version": "0.15.0.dev0",
4
+ "beta_end": 0.012,
5
+ "beta_schedule": "scaled_linear",
6
+ "beta_start": 0.00085,
7
+ "clip_sample": false,
8
+ "clip_sample_range": 1.0,
9
+ "dynamic_thresholding_ratio": 0.995,
10
+ "num_train_timesteps": 1000,
11
+ "prediction_type": "v_prediction",
12
+ "sample_max_value": 1.0,
13
+ "set_alpha_to_one": false,
14
+ "skip_prk_steps": true,
15
+ "steps_offset": 1,
16
+ "thresholding": false,
17
+ "trained_betas": null
18
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "stabilityai/stable-diffusion-2",
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": "4.28.0.dev0",
24
+ "vocab_size": 49408
25
+ }
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
tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
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
+ }
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
+ "do_lower_case": true,
12
+ "eos_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "errors": "replace",
21
+ "model_max_length": 77,
22
+ "pad_token": "<|endoftext|>",
23
+ "special_tokens_map_file": "./special_tokens_map.json",
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
+ }
tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
unet/config.json ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "UNet2DConditionModel",
3
+ "_diffusers_version": "0.15.0.dev0",
4
+ "act_fn": "silu",
5
+ "attention_head_dim": [
6
+ 5,
7
+ 10,
8
+ 20,
9
+ 20
10
+ ],
11
+ "block_out_channels": [
12
+ 320,
13
+ 640,
14
+ 1280,
15
+ 1280
16
+ ],
17
+ "center_input_sample": false,
18
+ "class_embed_type": "projection",
19
+ "class_embeddings_concat": false,
20
+ "conv_in_kernel": 3,
21
+ "conv_out_kernel": 3,
22
+ "cross_attention_dim": 1024,
23
+ "down_block_types": [
24
+ "CrossAttnDownBlock2D",
25
+ "CrossAttnDownBlock2D",
26
+ "CrossAttnDownBlock2D",
27
+ "DownBlock2D"
28
+ ],
29
+ "downsample_padding": 1,
30
+ "dual_cross_attention": false,
31
+ "flip_sin_to_cos": true,
32
+ "freq_shift": 0,
33
+ "in_channels": 4,
34
+ "layers_per_block": 2,
35
+ "mid_block_scale_factor": 1,
36
+ "mid_block_type": "UNetMidBlock2DCrossAttn",
37
+ "norm_eps": 1e-05,
38
+ "norm_num_groups": 32,
39
+ "num_class_embeds": null,
40
+ "only_cross_attention": false,
41
+ "out_channels": 4,
42
+ "projection_class_embeddings_input_dim": 1536,
43
+ "resnet_time_scale_shift": "default",
44
+ "sample_size": 96,
45
+ "time_cond_proj_dim": null,
46
+ "time_embedding_type": "positional",
47
+ "timestep_post_act": null,
48
+ "up_block_types": [
49
+ "UpBlock2D",
50
+ "CrossAttnUpBlock2D",
51
+ "CrossAttnUpBlock2D",
52
+ "CrossAttnUpBlock2D"
53
+ ],
54
+ "upcast_attention": false,
55
+ "use_linear_projection": true
56
+ }
unet/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72b89787d984dcb51a08a1f36c665c7bbf9bab1e388c75ff8a62b7d09b968370
3
+ size 3478354717
vae/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.15.0.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
+ "in_channels": 3,
18
+ "latent_channels": 4,
19
+ "layers_per_block": 2,
20
+ "norm_num_groups": 32,
21
+ "out_channels": 3,
22
+ "sample_size": 768,
23
+ "scaling_factor": 0.18215,
24
+ "up_block_types": [
25
+ "UpDecoderBlock2D",
26
+ "UpDecoderBlock2D",
27
+ "UpDecoderBlock2D",
28
+ "UpDecoderBlock2D"
29
+ ]
30
+ }
vae/diffusion_pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36bb8e1b54aba3a0914eb35fba13dcb107e9f18d379d1df2158732cd4bf56a94
3
+ size 334711857