add bf16 weights
Browse files- StableCascade-prior/feature_extractor/preprocessor_config.json +27 -0
- StableCascade-prior/image_encoder/config.json +23 -0
- StableCascade-prior/image_encoder/model.bf16.safetensors +3 -0
- StableCascade-prior/model_index.json +29 -0
- StableCascade-prior/prior/config.json +64 -0
- StableCascade-prior/prior/diffusion_pytorch_model.bf16.safetensors +3 -0
- StableCascade-prior/scheduler/scheduler_config.json +6 -0
- StableCascade-prior/text_encoder/config.json +25 -0
- StableCascade-prior/text_encoder/model.bf16.safetensors +3 -0
- StableCascade-prior/tokenizer/merges.txt +0 -0
- StableCascade-prior/tokenizer/special_tokens_map.json +30 -0
- StableCascade-prior/tokenizer/tokenizer.json +0 -0
- StableCascade-prior/tokenizer/tokenizer_config.json +30 -0
- StableCascade-prior/tokenizer/vocab.json +0 -0
- prior/diffusion_pytorch_model.bf16.safetensors +3 -0
- text_encoder/model.bf16.safetensors +3 -0
StableCascade-prior/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 |
+
}
|
StableCascade-prior/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": "bfloat16",
|
22 |
+
"transformers_version": "4.38.2"
|
23 |
+
}
|
StableCascade-prior/image_encoder/model.bf16.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4b33d864f89a793357a768cb07d0dc18d6a14e6664f4110a0d535ca9ba78da8
|
3 |
+
size 607980488
|
StableCascade-prior/model_index.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "StableCascadePriorPipeline",
|
3 |
+
"_diffusers_version": "0.27.0.dev0",
|
4 |
+
"feature_extractor": [
|
5 |
+
"transformers",
|
6 |
+
"CLIPImageProcessor"
|
7 |
+
],
|
8 |
+
"image_encoder": [
|
9 |
+
"transformers",
|
10 |
+
"CLIPVisionModelWithProjection"
|
11 |
+
],
|
12 |
+
"prior": [
|
13 |
+
"diffusers",
|
14 |
+
"StableCascadeUNet"
|
15 |
+
],
|
16 |
+
"resolution_multiple": 42.67,
|
17 |
+
"scheduler": [
|
18 |
+
"diffusers",
|
19 |
+
"DDPMWuerstchenScheduler"
|
20 |
+
],
|
21 |
+
"text_encoder": [
|
22 |
+
"transformers",
|
23 |
+
"CLIPTextModelWithProjection"
|
24 |
+
],
|
25 |
+
"tokenizer": [
|
26 |
+
"transformers",
|
27 |
+
"CLIPTokenizerFast"
|
28 |
+
]
|
29 |
+
}
|
StableCascade-prior/prior/config.json
ADDED
@@ -0,0 +1,64 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "StableCascadeUNet",
|
3 |
+
"_diffusers_version": "0.27.0.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 |
+
}
|
StableCascade-prior/prior/diffusion_pytorch_model.bf16.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44a4cd9540f327f2fb4ac09179e4e87912a01cdb1b3b86c79f0f853976fb4c98
|
3 |
+
size 7178377816
|
StableCascade-prior/scheduler/scheduler_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "DDPMWuerstchenScheduler",
|
3 |
+
"_diffusers_version": "0.27.0.dev0",
|
4 |
+
"s": 0.008,
|
5 |
+
"scaler": 1.0
|
6 |
+
}
|
StableCascade-prior/text_encoder/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "laion/CLIP-ViT-bigG-14-laion2B-39B-b160k",
|
3 |
+
"architectures": [
|
4 |
+
"CLIPTextModelWithProjection"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 49406,
|
8 |
+
"dropout": 0.0,
|
9 |
+
"eos_token_id": 49407,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_size": 1280,
|
12 |
+
"initializer_factor": 1.0,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 5120,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 77,
|
17 |
+
"model_type": "clip_text_model",
|
18 |
+
"num_attention_heads": 20,
|
19 |
+
"num_hidden_layers": 32,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"projection_dim": 1280,
|
22 |
+
"torch_dtype": "bfloat16",
|
23 |
+
"transformers_version": "4.38.2",
|
24 |
+
"vocab_size": 49408
|
25 |
+
}
|
StableCascade-prior/text_encoder/model.bf16.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:260e0127aca3c89db813637ae659ebb822cb07af71fedc16cbd980e9518dfdcd
|
3 |
+
size 1389382688
|
StableCascade-prior/tokenizer/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
StableCascade-prior/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 |
+
}
|
StableCascade-prior/tokenizer/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
StableCascade-prior/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 |
+
}
|
StableCascade-prior/tokenizer/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
prior/diffusion_pytorch_model.bf16.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44a4cd9540f327f2fb4ac09179e4e87912a01cdb1b3b86c79f0f853976fb4c98
|
3 |
+
size 7178377816
|
text_encoder/model.bf16.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:260e0127aca3c89db813637ae659ebb822cb07af71fedc16cbd980e9518dfdcd
|
3 |
+
size 1389382688
|