Adding `diffusers` weights of this model (#3)
Browse files- Adding `diffusers` weights of this model (b4eacebcfcc20245dad2c0865bc9ad302f13f03c)
- feature_extractor/preprocessor_config.json +17 -1
- model_index.json +8 -4
- safety_checker/config.json +28 -0
- safety_checker/model.fp16.safetensors +3 -0
- safety_checker/model.safetensors +3 -0
- scheduler/scheduler_config.json +4 -15
- text_encoder/config.json +2 -3
- text_encoder/model.fp16.safetensors +2 -2
- text_encoder/model.safetensors +2 -2
- tokenizer/special_tokens_map.json +9 -3
- tokenizer/tokenizer_config.json +20 -23
- unet/config.json +6 -1
- unet/diffusion_pytorch_model.fp16.safetensors +2 -2
- unet/diffusion_pytorch_model.safetensors +1 -1
- vae/config.json +4 -1
- vae/diffusion_pytorch_model.fp16.safetensors +2 -2
feature_extractor/preprocessor_config.json
CHANGED
@@ -1,4 +1,21 @@
|
|
1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
"crop_size": {
|
3 |
"height": 224,
|
4 |
"width": 224
|
@@ -8,7 +25,6 @@
|
|
8 |
"do_normalize": true,
|
9 |
"do_rescale": true,
|
10 |
"do_resize": true,
|
11 |
-
"feature_extractor_type": "CLIPFeatureExtractor",
|
12 |
"image_mean": [
|
13 |
0.48145466,
|
14 |
0.4578275,
|
|
|
1 |
{
|
2 |
+
"_valid_processor_keys": [
|
3 |
+
"images",
|
4 |
+
"do_resize",
|
5 |
+
"size",
|
6 |
+
"resample",
|
7 |
+
"do_center_crop",
|
8 |
+
"crop_size",
|
9 |
+
"do_rescale",
|
10 |
+
"rescale_factor",
|
11 |
+
"do_normalize",
|
12 |
+
"image_mean",
|
13 |
+
"image_std",
|
14 |
+
"do_convert_rgb",
|
15 |
+
"return_tensors",
|
16 |
+
"data_format",
|
17 |
+
"input_data_format"
|
18 |
+
],
|
19 |
"crop_size": {
|
20 |
"height": 224,
|
21 |
"width": 224
|
|
|
25 |
"do_normalize": true,
|
26 |
"do_rescale": true,
|
27 |
"do_resize": true,
|
|
|
28 |
"image_mean": [
|
29 |
0.48145466,
|
30 |
0.4578275,
|
model_index.json
CHANGED
@@ -1,18 +1,22 @@
|
|
1 |
{
|
2 |
"_class_name": "StableDiffusionPipeline",
|
3 |
-
"_diffusers_version": "0.
|
4 |
"feature_extractor": [
|
5 |
"transformers",
|
6 |
"CLIPFeatureExtractor"
|
7 |
],
|
8 |
-
"
|
9 |
-
"safety_checker": [
|
10 |
null,
|
11 |
null
|
12 |
],
|
|
|
|
|
|
|
|
|
|
|
13 |
"scheduler": [
|
14 |
"diffusers",
|
15 |
-
"
|
16 |
],
|
17 |
"text_encoder": [
|
18 |
"transformers",
|
|
|
1 |
{
|
2 |
"_class_name": "StableDiffusionPipeline",
|
3 |
+
"_diffusers_version": "0.28.0.dev0",
|
4 |
"feature_extractor": [
|
5 |
"transformers",
|
6 |
"CLIPFeatureExtractor"
|
7 |
],
|
8 |
+
"image_encoder": [
|
|
|
9 |
null,
|
10 |
null
|
11 |
],
|
12 |
+
"requires_safety_checker": true,
|
13 |
+
"safety_checker": [
|
14 |
+
"stable_diffusion",
|
15 |
+
"StableDiffusionSafetyChecker"
|
16 |
+
],
|
17 |
"scheduler": [
|
18 |
"diffusers",
|
19 |
+
"PNDMScheduler"
|
20 |
],
|
21 |
"text_encoder": [
|
22 |
"transformers",
|
safety_checker/config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "CompVis/stable-diffusion-safety-checker",
|
3 |
+
"architectures": [
|
4 |
+
"StableDiffusionSafetyChecker"
|
5 |
+
],
|
6 |
+
"initializer_factor": 1.0,
|
7 |
+
"logit_scale_init_value": 2.6592,
|
8 |
+
"model_type": "clip",
|
9 |
+
"projection_dim": 768,
|
10 |
+
"text_config": {
|
11 |
+
"dropout": 0.0,
|
12 |
+
"hidden_size": 768,
|
13 |
+
"intermediate_size": 3072,
|
14 |
+
"model_type": "clip_text_model",
|
15 |
+
"num_attention_heads": 12
|
16 |
+
},
|
17 |
+
"torch_dtype": "float32",
|
18 |
+
"transformers_version": "4.41.1",
|
19 |
+
"vision_config": {
|
20 |
+
"dropout": 0.0,
|
21 |
+
"hidden_size": 1024,
|
22 |
+
"intermediate_size": 4096,
|
23 |
+
"model_type": "clip_vision_model",
|
24 |
+
"num_attention_heads": 16,
|
25 |
+
"num_hidden_layers": 24,
|
26 |
+
"patch_size": 14
|
27 |
+
}
|
28 |
+
}
|
safety_checker/model.fp16.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb351a5ded815c3ff744968ad9c6b218d071b9d313d04f35e813b84b4c0ffde8
|
3 |
+
size 1215979664
|
safety_checker/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb351a5ded815c3ff744968ad9c6b218d071b9d313d04f35e813b84b4c0ffde8
|
3 |
+
size 1215979664
|
scheduler/scheduler_config.json
CHANGED
@@ -1,26 +1,15 @@
|
|
1 |
{
|
2 |
-
"_class_name": "
|
3 |
-
"_diffusers_version": "0.
|
4 |
-
|
5 |
"beta_end": 0.012,
|
6 |
"beta_schedule": "scaled_linear",
|
7 |
"beta_start": 0.00085,
|
8 |
"clip_sample": false,
|
9 |
-
"clip_sample_range": 1.0,
|
10 |
-
"dynamic_thresholding_ratio": 0.995,
|
11 |
-
|
12 |
-
|
13 |
"num_train_timesteps": 1000,
|
14 |
"prediction_type": "epsilon",
|
15 |
-
"rescale_betas_zero_snr": false,
|
16 |
-
"sample_max_value": 1.0,
|
17 |
"set_alpha_to_one": false,
|
18 |
-
|
19 |
-
|
20 |
"steps_offset": 1,
|
21 |
-
"thresholding": false,
|
22 |
"timestep_spacing": "leading",
|
23 |
"trained_betas": null
|
24 |
-
|
25 |
-
|
26 |
-
}
|
|
|
1 |
{
|
2 |
+
"_class_name": "PNDMScheduler",
|
3 |
+
"_diffusers_version": "0.28.0.dev0",
|
|
|
4 |
"beta_end": 0.012,
|
5 |
"beta_schedule": "scaled_linear",
|
6 |
"beta_start": 0.00085,
|
7 |
"clip_sample": false,
|
|
|
|
|
|
|
|
|
8 |
"num_train_timesteps": 1000,
|
9 |
"prediction_type": "epsilon",
|
|
|
|
|
10 |
"set_alpha_to_one": false,
|
11 |
+
"skip_prk_steps": true,
|
|
|
12 |
"steps_offset": 1,
|
|
|
13 |
"timestep_spacing": "leading",
|
14 |
"trained_betas": null
|
15 |
+
}
|
|
|
|
text_encoder/config.json
CHANGED
@@ -1,5 +1,4 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "openai/clip-vit-large-patch14",
|
3 |
"architectures": [
|
4 |
"CLIPTextModel"
|
5 |
],
|
@@ -19,7 +18,7 @@
|
|
19 |
"num_hidden_layers": 12,
|
20 |
"pad_token_id": 1,
|
21 |
"projection_dim": 768,
|
22 |
-
"torch_dtype": "
|
23 |
-
"transformers_version": "4.
|
24 |
"vocab_size": 49408
|
25 |
}
|
|
|
1 |
{
|
|
|
2 |
"architectures": [
|
3 |
"CLIPTextModel"
|
4 |
],
|
|
|
18 |
"num_hidden_layers": 12,
|
19 |
"pad_token_id": 1,
|
20 |
"projection_dim": 768,
|
21 |
+
"torch_dtype": "float32",
|
22 |
+
"transformers_version": "4.41.1",
|
23 |
"vocab_size": 49408
|
24 |
}
|
text_encoder/model.fp16.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d2d181c4bcfd100251a578659a6a47aae539365c9b857ff06d5731e72a19625
|
3 |
+
size 492265168
|
text_encoder/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d2d181c4bcfd100251a578659a6a47aae539365c9b857ff06d5731e72a19625
|
3 |
+
size 492265168
|
tokenizer/special_tokens_map.json
CHANGED
@@ -9,15 +9,21 @@
|
|
9 |
"eos_token": {
|
10 |
"content": "<|endoftext|>",
|
11 |
"lstrip": false,
|
12 |
-
"normalized":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
-
"pad_token": "<|endoftext|>",
|
17 |
"unk_token": {
|
18 |
"content": "<|endoftext|>",
|
19 |
"lstrip": false,
|
20 |
-
"normalized":
|
21 |
"rstrip": false,
|
22 |
"single_word": false
|
23 |
}
|
|
|
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 |
}
|
tokenizer/tokenizer_config.json
CHANGED
@@ -1,33 +1,30 @@
|
|
1 |
{
|
2 |
"add_prefix_space": false,
|
3 |
-
"
|
4 |
-
"
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
10 |
},
|
|
|
11 |
"clean_up_tokenization_spaces": true,
|
12 |
"do_lower_case": true,
|
13 |
-
"eos_token":
|
14 |
-
"__type": "AddedToken",
|
15 |
-
"content": "<|endoftext|>",
|
16 |
-
"lstrip": false,
|
17 |
-
"normalized": true,
|
18 |
-
"rstrip": false,
|
19 |
-
"single_word": false
|
20 |
-
},
|
21 |
"errors": "replace",
|
22 |
"model_max_length": 77,
|
23 |
"pad_token": "<|endoftext|>",
|
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 |
}
|
|
|
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 |
}
|
unet/config.json
CHANGED
@@ -1,10 +1,12 @@
|
|
1 |
{
|
2 |
"_class_name": "UNet2DConditionModel",
|
3 |
-
"_diffusers_version": "0.
|
4 |
"act_fn": "silu",
|
5 |
"addition_embed_type": null,
|
6 |
"addition_embed_type_num_heads": 64,
|
|
|
7 |
"attention_head_dim": 8,
|
|
|
8 |
"block_out_channels": [
|
9 |
320,
|
10 |
640,
|
@@ -25,6 +27,7 @@
|
|
25 |
"DownBlock2D"
|
26 |
],
|
27 |
"downsample_padding": 1,
|
|
|
28 |
"dual_cross_attention": false,
|
29 |
"encoder_hid_dim": null,
|
30 |
"encoder_hid_dim_type": null,
|
@@ -45,12 +48,14 @@
|
|
45 |
"resnet_out_scale_factor": 1.0,
|
46 |
"resnet_skip_time_act": false,
|
47 |
"resnet_time_scale_shift": "default",
|
|
|
48 |
"sample_size": 96,
|
49 |
"time_cond_proj_dim": null,
|
50 |
"time_embedding_act_fn": null,
|
51 |
"time_embedding_dim": null,
|
52 |
"time_embedding_type": "positional",
|
53 |
"timestep_post_act": null,
|
|
|
54 |
"up_block_types": [
|
55 |
"UpBlock2D",
|
56 |
"CrossAttnUpBlock2D",
|
|
|
1 |
{
|
2 |
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.28.0.dev0",
|
4 |
"act_fn": "silu",
|
5 |
"addition_embed_type": null,
|
6 |
"addition_embed_type_num_heads": 64,
|
7 |
+
"addition_time_embed_dim": null,
|
8 |
"attention_head_dim": 8,
|
9 |
+
"attention_type": "default",
|
10 |
"block_out_channels": [
|
11 |
320,
|
12 |
640,
|
|
|
27 |
"DownBlock2D"
|
28 |
],
|
29 |
"downsample_padding": 1,
|
30 |
+
"dropout": 0.0,
|
31 |
"dual_cross_attention": false,
|
32 |
"encoder_hid_dim": null,
|
33 |
"encoder_hid_dim_type": null,
|
|
|
48 |
"resnet_out_scale_factor": 1.0,
|
49 |
"resnet_skip_time_act": false,
|
50 |
"resnet_time_scale_shift": "default",
|
51 |
+
"reverse_transformer_layers_per_block": null,
|
52 |
"sample_size": 96,
|
53 |
"time_cond_proj_dim": null,
|
54 |
"time_embedding_act_fn": null,
|
55 |
"time_embedding_dim": null,
|
56 |
"time_embedding_type": "positional",
|
57 |
"timestep_post_act": null,
|
58 |
+
"transformer_layers_per_block": 1,
|
59 |
"up_block_types": [
|
60 |
"UpBlock2D",
|
61 |
"CrossAttnUpBlock2D",
|
unet/diffusion_pytorch_model.fp16.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:508afbf95236d8603e16948a04fc823b13bec82a6f7b19ed972b06ac2d1cc8fa
|
3 |
+
size 3438167536
|
unet/diffusion_pytorch_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3438167536
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:508afbf95236d8603e16948a04fc823b13bec82a6f7b19ed972b06ac2d1cc8fa
|
3 |
size 3438167536
|
vae/config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"_class_name": "AutoencoderKL",
|
3 |
-
"_diffusers_version": "0.
|
4 |
"act_fn": "silu",
|
5 |
"block_out_channels": [
|
6 |
128,
|
@@ -14,8 +14,11 @@
|
|
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,
|
|
|
1 |
{
|
2 |
"_class_name": "AutoencoderKL",
|
3 |
+
"_diffusers_version": "0.28.0.dev0",
|
4 |
"act_fn": "silu",
|
5 |
"block_out_channels": [
|
6 |
128,
|
|
|
14 |
"DownEncoderBlock2D",
|
15 |
"DownEncoderBlock2D"
|
16 |
],
|
17 |
+
"force_upcast": true,
|
18 |
"in_channels": 3,
|
19 |
"latent_channels": 4,
|
20 |
+
"latents_mean": null,
|
21 |
+
"latents_std": null,
|
22 |
"layers_per_block": 2,
|
23 |
"norm_num_groups": 32,
|
24 |
"out_channels": 3,
|
vae/diffusion_pytorch_model.fp16.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9cb4ca8cd1bbfb8cb23cc8e76465542419caf6a4f35a0702c8fbab0c8eb84ed7
|
3 |
+
size 334643268
|