Adding `diffusers` weights of this model
#7
by
Yntec
- opened
- model_index.json +4 -4
- safety_checker/config.json +168 -0
- safety_checker/model.fp16.safetensors +3 -0
- safety_checker/model.safetensors +3 -0
- safety_checker/pytorch_model.bin +3 -0
- safety_checker/pytorch_model.fp16.bin +3 -0
- scheduler/scheduler_config.json +1 -6
- text_encoder/config.json +0 -1
- text_encoder/model.fp16.safetensors +1 -1
- text_encoder/model.safetensors +1 -1
- text_encoder/pytorch_model.bin +1 -1
- text_encoder/pytorch_model.fp16.bin +1 -1
- unet/config.json +3 -1
- unet/diffusion_pytorch_model.bin +1 -1
- unet/diffusion_pytorch_model.fp16.bin +1 -1
- unet/diffusion_pytorch_model.fp16.safetensors +1 -1
- unet/diffusion_pytorch_model.safetensors +1 -1
- vae/config.json +2 -1
- vae/diffusion_pytorch_model.bin +1 -1
- vae/diffusion_pytorch_model.fp16.bin +1 -1
- vae/diffusion_pytorch_model.fp16.safetensors +1 -1
- vae/diffusion_pytorch_model.safetensors +1 -1
model_index.json
CHANGED
@@ -1,14 +1,14 @@
|
|
1 |
{
|
2 |
"_class_name": "StableDiffusionPipeline",
|
3 |
-
"_diffusers_version": "0.
|
4 |
"feature_extractor": [
|
5 |
"transformers",
|
6 |
"CLIPFeatureExtractor"
|
7 |
],
|
8 |
-
"requires_safety_checker":
|
9 |
"safety_checker": [
|
10 |
-
|
11 |
-
|
12 |
],
|
13 |
"scheduler": [
|
14 |
"diffusers",
|
|
|
1 |
{
|
2 |
"_class_name": "StableDiffusionPipeline",
|
3 |
+
"_diffusers_version": "0.19.0.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",
|
safety_checker/config.json
ADDED
@@ -0,0 +1,168 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_commit_hash": "cb41f3a270d63d454d385fc2e4f571c487c253c5",
|
3 |
+
"_name_or_path": "CompVis/stable-diffusion-safety-checker",
|
4 |
+
"architectures": [
|
5 |
+
"StableDiffusionSafetyChecker"
|
6 |
+
],
|
7 |
+
"initializer_factor": 1.0,
|
8 |
+
"logit_scale_init_value": 2.6592,
|
9 |
+
"model_type": "clip",
|
10 |
+
"projection_dim": 768,
|
11 |
+
"text_config": {
|
12 |
+
"_name_or_path": "",
|
13 |
+
"add_cross_attention": false,
|
14 |
+
"architectures": null,
|
15 |
+
"attention_dropout": 0.0,
|
16 |
+
"bad_words_ids": null,
|
17 |
+
"begin_suppress_tokens": null,
|
18 |
+
"bos_token_id": 0,
|
19 |
+
"chunk_size_feed_forward": 0,
|
20 |
+
"cross_attention_hidden_size": null,
|
21 |
+
"decoder_start_token_id": null,
|
22 |
+
"diversity_penalty": 0.0,
|
23 |
+
"do_sample": false,
|
24 |
+
"dropout": 0.0,
|
25 |
+
"early_stopping": false,
|
26 |
+
"encoder_no_repeat_ngram_size": 0,
|
27 |
+
"eos_token_id": 2,
|
28 |
+
"exponential_decay_length_penalty": null,
|
29 |
+
"finetuning_task": null,
|
30 |
+
"forced_bos_token_id": null,
|
31 |
+
"forced_eos_token_id": null,
|
32 |
+
"hidden_act": "quick_gelu",
|
33 |
+
"hidden_size": 768,
|
34 |
+
"id2label": {
|
35 |
+
"0": "LABEL_0",
|
36 |
+
"1": "LABEL_1"
|
37 |
+
},
|
38 |
+
"initializer_factor": 1.0,
|
39 |
+
"initializer_range": 0.02,
|
40 |
+
"intermediate_size": 3072,
|
41 |
+
"is_decoder": false,
|
42 |
+
"is_encoder_decoder": false,
|
43 |
+
"label2id": {
|
44 |
+
"LABEL_0": 0,
|
45 |
+
"LABEL_1": 1
|
46 |
+
},
|
47 |
+
"layer_norm_eps": 1e-05,
|
48 |
+
"length_penalty": 1.0,
|
49 |
+
"max_length": 20,
|
50 |
+
"max_position_embeddings": 77,
|
51 |
+
"min_length": 0,
|
52 |
+
"model_type": "clip_text_model",
|
53 |
+
"no_repeat_ngram_size": 0,
|
54 |
+
"num_attention_heads": 12,
|
55 |
+
"num_beam_groups": 1,
|
56 |
+
"num_beams": 1,
|
57 |
+
"num_hidden_layers": 12,
|
58 |
+
"num_return_sequences": 1,
|
59 |
+
"output_attentions": false,
|
60 |
+
"output_hidden_states": false,
|
61 |
+
"output_scores": false,
|
62 |
+
"pad_token_id": 1,
|
63 |
+
"prefix": null,
|
64 |
+
"problem_type": null,
|
65 |
+
"projection_dim": 512,
|
66 |
+
"pruned_heads": {},
|
67 |
+
"remove_invalid_values": false,
|
68 |
+
"repetition_penalty": 1.0,
|
69 |
+
"return_dict": true,
|
70 |
+
"return_dict_in_generate": false,
|
71 |
+
"sep_token_id": null,
|
72 |
+
"suppress_tokens": null,
|
73 |
+
"task_specific_params": null,
|
74 |
+
"temperature": 1.0,
|
75 |
+
"tf_legacy_loss": false,
|
76 |
+
"tie_encoder_decoder": false,
|
77 |
+
"tie_word_embeddings": true,
|
78 |
+
"tokenizer_class": null,
|
79 |
+
"top_k": 50,
|
80 |
+
"top_p": 1.0,
|
81 |
+
"torch_dtype": null,
|
82 |
+
"torchscript": false,
|
83 |
+
"transformers_version": "4.30.2",
|
84 |
+
"typical_p": 1.0,
|
85 |
+
"use_bfloat16": false,
|
86 |
+
"vocab_size": 49408
|
87 |
+
},
|
88 |
+
"torch_dtype": "float16",
|
89 |
+
"transformers_version": null,
|
90 |
+
"vision_config": {
|
91 |
+
"_name_or_path": "",
|
92 |
+
"add_cross_attention": false,
|
93 |
+
"architectures": null,
|
94 |
+
"attention_dropout": 0.0,
|
95 |
+
"bad_words_ids": null,
|
96 |
+
"begin_suppress_tokens": null,
|
97 |
+
"bos_token_id": null,
|
98 |
+
"chunk_size_feed_forward": 0,
|
99 |
+
"cross_attention_hidden_size": null,
|
100 |
+
"decoder_start_token_id": null,
|
101 |
+
"diversity_penalty": 0.0,
|
102 |
+
"do_sample": false,
|
103 |
+
"dropout": 0.0,
|
104 |
+
"early_stopping": false,
|
105 |
+
"encoder_no_repeat_ngram_size": 0,
|
106 |
+
"eos_token_id": null,
|
107 |
+
"exponential_decay_length_penalty": null,
|
108 |
+
"finetuning_task": null,
|
109 |
+
"forced_bos_token_id": null,
|
110 |
+
"forced_eos_token_id": null,
|
111 |
+
"hidden_act": "quick_gelu",
|
112 |
+
"hidden_size": 1024,
|
113 |
+
"id2label": {
|
114 |
+
"0": "LABEL_0",
|
115 |
+
"1": "LABEL_1"
|
116 |
+
},
|
117 |
+
"image_size": 224,
|
118 |
+
"initializer_factor": 1.0,
|
119 |
+
"initializer_range": 0.02,
|
120 |
+
"intermediate_size": 4096,
|
121 |
+
"is_decoder": false,
|
122 |
+
"is_encoder_decoder": false,
|
123 |
+
"label2id": {
|
124 |
+
"LABEL_0": 0,
|
125 |
+
"LABEL_1": 1
|
126 |
+
},
|
127 |
+
"layer_norm_eps": 1e-05,
|
128 |
+
"length_penalty": 1.0,
|
129 |
+
"max_length": 20,
|
130 |
+
"min_length": 0,
|
131 |
+
"model_type": "clip_vision_model",
|
132 |
+
"no_repeat_ngram_size": 0,
|
133 |
+
"num_attention_heads": 16,
|
134 |
+
"num_beam_groups": 1,
|
135 |
+
"num_beams": 1,
|
136 |
+
"num_channels": 3,
|
137 |
+
"num_hidden_layers": 24,
|
138 |
+
"num_return_sequences": 1,
|
139 |
+
"output_attentions": false,
|
140 |
+
"output_hidden_states": false,
|
141 |
+
"output_scores": false,
|
142 |
+
"pad_token_id": null,
|
143 |
+
"patch_size": 14,
|
144 |
+
"prefix": null,
|
145 |
+
"problem_type": null,
|
146 |
+
"projection_dim": 512,
|
147 |
+
"pruned_heads": {},
|
148 |
+
"remove_invalid_values": false,
|
149 |
+
"repetition_penalty": 1.0,
|
150 |
+
"return_dict": true,
|
151 |
+
"return_dict_in_generate": false,
|
152 |
+
"sep_token_id": null,
|
153 |
+
"suppress_tokens": null,
|
154 |
+
"task_specific_params": null,
|
155 |
+
"temperature": 1.0,
|
156 |
+
"tf_legacy_loss": false,
|
157 |
+
"tie_encoder_decoder": false,
|
158 |
+
"tie_word_embeddings": true,
|
159 |
+
"tokenizer_class": null,
|
160 |
+
"top_k": 50,
|
161 |
+
"top_p": 1.0,
|
162 |
+
"torch_dtype": null,
|
163 |
+
"torchscript": false,
|
164 |
+
"transformers_version": "4.30.2",
|
165 |
+
"typical_p": 1.0,
|
166 |
+
"use_bfloat16": false
|
167 |
+
}
|
168 |
+
}
|
safety_checker/model.fp16.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:08902f19b1cfebd7c989f152fc0507bef6898c706a91d666509383122324b511
|
3 |
+
size 608018440
|
safety_checker/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11cfe53105625af8c00faac32a430626641cce686454f3c39d837f14397d858b
|
3 |
+
size 1215981832
|
safety_checker/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16d28f2b37109f222cdc33620fdd262102ac32112be0352a7f77e9614b35a394
|
3 |
+
size 1216064769
|
safety_checker/pytorch_model.fp16.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:22ba87205445ad5def13e54919b038dcfb7321ec1c3f4b12487d4fba6036125f
|
3 |
+
size 608103564
|
scheduler/scheduler_config.json
CHANGED
@@ -1,20 +1,15 @@
|
|
1 |
{
|
2 |
"_class_name": "PNDMScheduler",
|
3 |
-
"_diffusers_version": "0.
|
4 |
"beta_end": 0.012,
|
5 |
"beta_schedule": "scaled_linear",
|
6 |
"beta_start": 0.00085,
|
7 |
"clip_sample": false,
|
8 |
-
"clip_sample_range": 1.0,
|
9 |
-
"dynamic_thresholding_ratio": 0.995,
|
10 |
"num_train_timesteps": 1000,
|
11 |
"prediction_type": "epsilon",
|
12 |
-
"rescale_betas_zero_snr": false,
|
13 |
-
"sample_max_value": 1.0,
|
14 |
"set_alpha_to_one": false,
|
15 |
"skip_prk_steps": true,
|
16 |
"steps_offset": 1,
|
17 |
-
"thresholding": false,
|
18 |
"timestep_spacing": "leading",
|
19 |
"trained_betas": null
|
20 |
}
|
|
|
1 |
{
|
2 |
"_class_name": "PNDMScheduler",
|
3 |
+
"_diffusers_version": "0.19.0.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 |
],
|
|
|
1 |
{
|
|
|
2 |
"architectures": [
|
3 |
"CLIPTextModel"
|
4 |
],
|
text_encoder/model.fp16.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 246144864
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60d869554f375e8eb0ab5ffbc2e72ca237d9f6258cbd783a2ee6eb07a5213e97
|
3 |
size 246144864
|
text_encoder/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 492265880
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:904bfbe51cc275d73e51839b62c51043fa2179d88ee104fbf4fa1476e880b409
|
3 |
size 492265880
|
text_encoder/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 492307041
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c494bb660ceeae635eac3c3c59c38f707585a738011966b89a474bceec4dc38e
|
3 |
size 492307041
|
text_encoder/pytorch_model.fp16.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 246187076
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b25a07008335f7d8614e660131c851bae503b026260e2c80a4436128c23a24f
|
3 |
size 246187076
|
unet/config.json
CHANGED
@@ -1,9 +1,10 @@
|
|
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,
|
@@ -51,6 +52,7 @@
|
|
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": "0.19.0.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 |
"block_out_channels": [
|
10 |
320,
|
|
|
52 |
"time_embedding_dim": null,
|
53 |
"time_embedding_type": "positional",
|
54 |
"timestep_post_act": null,
|
55 |
+
"transformer_layers_per_block": 1,
|
56 |
"up_block_types": [
|
57 |
"UpBlock2D",
|
58 |
"CrossAttnUpBlock2D",
|
unet/diffusion_pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 3438366373
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:728e3eed99cfbfb7c3b2d8a1146724a7c3872c837db8e20b3ffda530325feffb
|
3 |
size 3438366373
|
unet/diffusion_pytorch_model.fp16.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1719327893
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab313a7b76340a498c0c519d8f23c72efcfff8ed96108e82133d42d157b80410
|
3 |
size 1719327893
|
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 1719125304
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:580eec8dd05aa94da01366aa6b6aef09fed98e42d1dddea428e0e1c96612f005
|
3 |
size 1719125304
|
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 sha256:81d13d968ea64f435c327a17fa743f067af30916e9b4fa4081ee7d05f5a10cc1
|
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,
|
@@ -14,6 +14,7 @@
|
|
14 |
"DownEncoderBlock2D",
|
15 |
"DownEncoderBlock2D"
|
16 |
],
|
|
|
17 |
"in_channels": 3,
|
18 |
"latent_channels": 4,
|
19 |
"layers_per_block": 2,
|
|
|
1 |
{
|
2 |
"_class_name": "AutoencoderKL",
|
3 |
+
"_diffusers_version": "0.19.0.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 |
"layers_per_block": 2,
|
vae/diffusion_pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 334712113
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:220c6ba4e2fa5c798d04b8714ae2ea43a4b9279cd31c0eba9ef0d8ff02aad738
|
3 |
size 334712113
|
vae/diffusion_pytorch_model.fp16.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 167405651
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f12e6afcdd1498aa54ef77554c35be436a99a6835d145e36968c9e169cc6413c
|
3 |
size 167405651
|
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 167335342
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8f8fbf71a97165674d41d43c1bdffd78996f5105cc6611606af91c82e9ccb387
|
3 |
size 167335342
|
vae/diffusion_pytorch_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 334643268
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1bafd7f036b806d2fdb3d205add03d76c37f74abce6ce52e8a913f1606dea3ce
|
3 |
size 334643268
|