Disty0 commited on
Commit
617c414
1 Parent(s): 869e21e

Upload 13 files

Browse files
decoder/config.json ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableCascadeUNet",
3
+ "_diffusers_version": "0.28.0.dev0",
4
+ "block_out_channels": [
5
+ 320,
6
+ 640,
7
+ 1280,
8
+ 1280
9
+ ],
10
+ "block_types_per_layer": [
11
+ [
12
+ "SDCascadeResBlock",
13
+ "SDCascadeTimestepBlock"
14
+ ],
15
+ [
16
+ "SDCascadeResBlock",
17
+ "SDCascadeTimestepBlock"
18
+ ],
19
+ [
20
+ "SDCascadeResBlock",
21
+ "SDCascadeTimestepBlock",
22
+ "SDCascadeAttnBlock"
23
+ ],
24
+ [
25
+ "SDCascadeResBlock",
26
+ "SDCascadeTimestepBlock",
27
+ "SDCascadeAttnBlock"
28
+ ]
29
+ ],
30
+ "clip_image_in_channels": null,
31
+ "clip_seq": 4,
32
+ "clip_text_in_channels": null,
33
+ "clip_text_pooled_in_channels": 1280,
34
+ "conditioning_dim": 1280,
35
+ "down_blocks_repeat_mappers": [
36
+ 1,
37
+ 1,
38
+ 1,
39
+ 1
40
+ ],
41
+ "down_num_layers_per_block": [
42
+ 2,
43
+ 6,
44
+ 28,
45
+ 6
46
+ ],
47
+ "dropout": [
48
+ 0,
49
+ 0,
50
+ 0.1,
51
+ 0.1
52
+ ],
53
+ "effnet_in_channels": 16,
54
+ "in_channels": 4,
55
+ "kernel_size": 3,
56
+ "num_attention_heads": [
57
+ 0,
58
+ 0,
59
+ 20,
60
+ 20
61
+ ],
62
+ "out_channels": 4,
63
+ "patch_size": 2,
64
+ "pixel_mapper_in_channels": 3,
65
+ "self_attn": true,
66
+ "switch_level": null,
67
+ "timestep_conditioning_type": [
68
+ "sca"
69
+ ],
70
+ "timestep_ratio_embedding_dim": 64,
71
+ "up_blocks_repeat_mappers": [
72
+ 3,
73
+ 3,
74
+ 2,
75
+ 2
76
+ ],
77
+ "up_num_layers_per_block": [
78
+ 6,
79
+ 28,
80
+ 6,
81
+ 2
82
+ ]
83
+ }
decoder/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e73c9e39bdb6e1e4cafd1c8874812bf72d4733257d464194083da088367ab58
3
+ size 3126069360
model_index.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "StableCascadeDecoderPipeline",
3
+ "_diffusers_version": "0.28.0.dev0",
4
+ "_name_or_path": "Disty0/sotediffusion-wuerstchen3-alpha3-decoder",
5
+ "decoder": [
6
+ "diffusers",
7
+ "StableCascadeUNet"
8
+ ],
9
+ "latent_dim_scale": 10.67,
10
+ "scheduler": [
11
+ "diffusers",
12
+ "DDPMWuerstchenScheduler"
13
+ ],
14
+ "text_encoder": [
15
+ "transformers",
16
+ "CLIPTextModelWithProjection"
17
+ ],
18
+ "tokenizer": [
19
+ "transformers",
20
+ "CLIPTokenizerFast"
21
+ ],
22
+ "vqgan": [
23
+ "wuerstchen",
24
+ "PaellaVQModel"
25
+ ]
26
+ }
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
 
vqgan/config.json ADDED
@@ -0,0 +1,14 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "PaellaVQModel",
3
+ "_diffusers_version": "0.28.0.dev0",
4
+ "_name_or_path": "madebyollin/stage-a-ft-hq",
5
+ "bottleneck_blocks": 12,
6
+ "embed_dim": 384,
7
+ "in_channels": 3,
8
+ "latent_channels": 4,
9
+ "levels": 2,
10
+ "num_vq_embeddings": 8192,
11
+ "out_channels": 3,
12
+ "scale_factor": 0.3764,
13
+ "up_down_scale_factor": 2
14
+ }
vqgan/diffusion_pytorch_model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cdaaa4be9238d7e2d68528d284f9b69fb9c34de6c06528c35d6dedd878b29cd0
3
+ size 36825700