Commit
•
3524c1a
1
Parent(s):
dcf70b5
Add Diffusers weights (#6)
Browse files- Add Diffusers weights (87b86148e9fd5009790a8b31212be8ea9515d845)
Co-authored-by: Patrick von Platen <patrickvonplaten@users.noreply.huggingface.co>
- model_index.json +33 -0
- text_encoder/config.json +25 -0
- text_encoder/pytorch_model.bin +3 -0
- tokenizer/merges.txt +0 -0
- tokenizer/special_tokens_map.json +24 -0
- tokenizer/tokenizer_config.json +34 -0
- tokenizer/vocab.json +0 -0
- unet/config.json +44 -0
- unet/diffusion_pytorch_model.bin +3 -0
- vae/config.json +29 -0
- vae/diffusion_pytorch_model.bin +3 -0
model_index.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "StableDiffusionPipeline",
|
3 |
+
"_diffusers_version": "0.12.0.dev0",
|
4 |
+
"feature_extractor": [
|
5 |
+
"transformers",
|
6 |
+
"CLIPFeatureExtractor"
|
7 |
+
],
|
8 |
+
"requires_safety_checker": true,
|
9 |
+
"safety_checker": [
|
10 |
+
"stable_diffusion",
|
11 |
+
"StableDiffusionSafetyChecker"
|
12 |
+
],
|
13 |
+
"scheduler": [
|
14 |
+
"diffusers",
|
15 |
+
"PNDMScheduler"
|
16 |
+
],
|
17 |
+
"text_encoder": [
|
18 |
+
"transformers",
|
19 |
+
"CLIPTextModel"
|
20 |
+
],
|
21 |
+
"tokenizer": [
|
22 |
+
"transformers",
|
23 |
+
"CLIPTokenizer"
|
24 |
+
],
|
25 |
+
"unet": [
|
26 |
+
"diffusers",
|
27 |
+
"UNet2DConditionModel"
|
28 |
+
],
|
29 |
+
"vae": [
|
30 |
+
"diffusers",
|
31 |
+
"AutoencoderKL"
|
32 |
+
]
|
33 |
+
}
|
text_encoder/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "openai/clip-vit-large-patch14",
|
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": "quick_gelu",
|
11 |
+
"hidden_size": 768,
|
12 |
+
"initializer_factor": 1.0,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 77,
|
17 |
+
"model_type": "clip_text_model",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"projection_dim": 768,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.26.0.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 sha256:352041f6439c89e676a91a9f59ab7dec0028ae2b3b0c955b3dccf28a5630762d
|
3 |
+
size 492307041
|
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": "<|endoftext|>",
|
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 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"name_or_path": "openai/clip-vit-large-patch14",
|
23 |
+
"pad_token": "<|endoftext|>",
|
24 |
+
"special_tokens_map_file": "./special_tokens_map.json",
|
25 |
+
"tokenizer_class": "CLIPTokenizer",
|
26 |
+
"unk_token": {
|
27 |
+
"__type": "AddedToken",
|
28 |
+
"content": "<|endoftext|>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": true,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false
|
33 |
+
}
|
34 |
+
}
|
tokenizer/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
unet/config.json
ADDED
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.12.0.dev0",
|
4 |
+
"act_fn": "silu",
|
5 |
+
"attention_head_dim": 8,
|
6 |
+
"block_out_channels": [
|
7 |
+
320,
|
8 |
+
640,
|
9 |
+
1280,
|
10 |
+
1280
|
11 |
+
],
|
12 |
+
"center_input_sample": false,
|
13 |
+
"class_embed_type": null,
|
14 |
+
"cross_attention_dim": 768,
|
15 |
+
"down_block_types": [
|
16 |
+
"CrossAttnDownBlock2D",
|
17 |
+
"CrossAttnDownBlock2D",
|
18 |
+
"CrossAttnDownBlock2D",
|
19 |
+
"DownBlock2D"
|
20 |
+
],
|
21 |
+
"downsample_padding": 1,
|
22 |
+
"dual_cross_attention": false,
|
23 |
+
"flip_sin_to_cos": true,
|
24 |
+
"freq_shift": 0,
|
25 |
+
"in_channels": 4,
|
26 |
+
"layers_per_block": 2,
|
27 |
+
"mid_block_scale_factor": 1,
|
28 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
29 |
+
"norm_eps": 1e-05,
|
30 |
+
"norm_num_groups": 32,
|
31 |
+
"num_class_embeds": null,
|
32 |
+
"only_cross_attention": false,
|
33 |
+
"out_channels": 4,
|
34 |
+
"resnet_time_scale_shift": "default",
|
35 |
+
"sample_size": 64,
|
36 |
+
"up_block_types": [
|
37 |
+
"UpBlock2D",
|
38 |
+
"CrossAttnUpBlock2D",
|
39 |
+
"CrossAttnUpBlock2D",
|
40 |
+
"CrossAttnUpBlock2D"
|
41 |
+
],
|
42 |
+
"upcast_attention": false,
|
43 |
+
"use_linear_projection": false
|
44 |
+
}
|
unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cdadf4e2f37dd3fdd0c4d0f1d4a3e34fe6271dff1257a69b2fa2c4cafd9e3573
|
3 |
+
size 220442624
|
vae/config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "AutoencoderKL",
|
3 |
+
"_diffusers_version": "0.12.0.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": 512,
|
23 |
+
"up_block_types": [
|
24 |
+
"UpDecoderBlock2D",
|
25 |
+
"UpDecoderBlock2D",
|
26 |
+
"UpDecoderBlock2D",
|
27 |
+
"UpDecoderBlock2D"
|
28 |
+
]
|
29 |
+
}
|
vae/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:da06c597093f08bf8dac0a5a3e26f31d16eab981b5d864891c30edebc498fd05
|
3 |
+
size 334711857
|