Disty0 commited on
Commit
d30f0c3
1 Parent(s): e89d463

Upload 14 files

Browse files
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": "/home/disty/.cache/huggingface/hub/models--stabilityai--stable-cascade-prior/snapshots/7ca32c21c3b4d4e35bbb94fcfedfb4fa2259bd91/image_encoder",
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": "float16",
22
+ "transformers_version": "4.36.2"
23
+ }
image_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0dd0c1777bb75e2e9b7aa29b799b3ee8ebaaaa731e2c471a9ec589f12542cce7
3
+ size 607980096
model_index.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableCascadePriorPipeline",
3
+ "_diffusers_version": "0.28.0.dev0",
4
+ "_name_or_path": "Disty0/sotediffusion-wuerstchen3-alpha3",
5
+ "feature_extractor": [
6
+ "transformers",
7
+ "CLIPImageProcessor"
8
+ ],
9
+ "image_encoder": [
10
+ "transformers",
11
+ "CLIPVisionModelWithProjection"
12
+ ],
13
+ "prior": [
14
+ "diffusers",
15
+ "StableCascadeUNet"
16
+ ],
17
+ "resolution_multiple": 42.67,
18
+ "scheduler": [
19
+ "diffusers",
20
+ "DDPMWuerstchenScheduler"
21
+ ],
22
+ "text_encoder": [
23
+ "transformers",
24
+ "CLIPTextModelWithProjection"
25
+ ],
26
+ "tokenizer": [
27
+ "transformers",
28
+ "CLIPTokenizerFast"
29
+ ]
30
+ }
prior/config.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableCascadeUNet",
3
+ "_diffusers_version": "0.28.0.dev0",
4
+ "block_out_channels": [
5
+ 2048,
6
+ 2048
7
+ ],
8
+ "block_types_per_layer": [
9
+ [
10
+ "SDCascadeResBlock",
11
+ "SDCascadeTimestepBlock",
12
+ "SDCascadeAttnBlock"
13
+ ],
14
+ [
15
+ "SDCascadeResBlock",
16
+ "SDCascadeTimestepBlock",
17
+ "SDCascadeAttnBlock"
18
+ ]
19
+ ],
20
+ "clip_image_in_channels": 768,
21
+ "clip_seq": 4,
22
+ "clip_text_in_channels": 1280,
23
+ "clip_text_pooled_in_channels": 1280,
24
+ "conditioning_dim": 2048,
25
+ "down_blocks_repeat_mappers": [
26
+ 1,
27
+ 1
28
+ ],
29
+ "down_num_layers_per_block": [
30
+ 8,
31
+ 24
32
+ ],
33
+ "dropout": [
34
+ 0.1,
35
+ 0.1
36
+ ],
37
+ "effnet_in_channels": null,
38
+ "in_channels": 16,
39
+ "kernel_size": 3,
40
+ "num_attention_heads": [
41
+ 32,
42
+ 32
43
+ ],
44
+ "out_channels": 16,
45
+ "patch_size": 1,
46
+ "pixel_mapper_in_channels": null,
47
+ "self_attn": true,
48
+ "switch_level": [
49
+ false
50
+ ],
51
+ "timestep_conditioning_type": [
52
+ "sca",
53
+ "crp"
54
+ ],
55
+ "timestep_ratio_embedding_dim": 64,
56
+ "up_blocks_repeat_mappers": [
57
+ 1,
58
+ 1
59
+ ],
60
+ "up_num_layers_per_block": [
61
+ 24,
62
+ 8
63
+ ]
64
+ }
prior/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ad2336de1f4be4a7547895b04dc8b2c5bae02dac99606d5708a730da3909b9d
3
+ size 7178376264
scheduler/scheduler_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "DDPMWuerstchenScheduler",
3
+ "_diffusers_version": "0.28.0.dev0",
4
+ "s": 0.008,
5
+ "scaler": 1.0
6
+ }
text_encoder/config.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "CLIPTextModelWithProjection"
4
+ ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 49406,
7
+ "dropout": 0.0,
8
+ "eos_token_id": 49407,
9
+ "hidden_act": "gelu",
10
+ "hidden_size": 1280,
11
+ "initializer_factor": 1.0,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 5120,
14
+ "layer_norm_eps": 1e-05,
15
+ "max_position_embeddings": 77,
16
+ "model_type": "clip_text_model",
17
+ "num_attention_heads": 20,
18
+ "num_hidden_layers": 32,
19
+ "pad_token_id": 1,
20
+ "projection_dim": 1280,
21
+ "torch_dtype": "float16",
22
+ "transformers_version": "4.36.2",
23
+ "vocab_size": 49408
24
+ }
text_encoder/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00ff831dd81b2e2a6b0952fb7f59ea07bcef5046de97e671978e1ad84cb44975
3
+ size 1389382176
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 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<|endoftext|>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer/tokenizer_config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "49406": {
5
+ "content": "<|startoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "49407": {
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ }
20
+ },
21
+ "bos_token": "<|startoftext|>",
22
+ "clean_up_tokenization_spaces": true,
23
+ "do_lower_case": true,
24
+ "eos_token": "<|endoftext|>",
25
+ "errors": "replace",
26
+ "model_max_length": 77,
27
+ "pad_token": "<|endoftext|>",
28
+ "tokenizer_class": "CLIPTokenizer",
29
+ "unk_token": "<|endoftext|>"
30
+ }
tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff