Adding `diffusers` weights of this model
#2
by
johniel
- opened
- feature_extractor/preprocessor_config.json +10 -3
- model_index.json +7 -2
- safety_checker/config.json +2 -149
- safety_checker/model.fp16.safetensors +2 -2
- safety_checker/model.safetensors +2 -2
- scheduler/scheduler_config.json +2 -1
- text_encoder/config.json +2 -3
- text_encoder/model.fp16.safetensors +3 -0
- text_encoder/model.safetensors +3 -0
- tokenizer/special_tokens_map.json +9 -3
- tokenizer/tokenizer_config.json +20 -23
- unet/config.json +19 -3
- unet/diffusion_pytorch_model.fp16.safetensors +3 -0
- unet/diffusion_pytorch_model.safetensors +3 -0
- vae/config.json +2 -2
- vae/diffusion_pytorch_model.fp16.safetensors +3 -0
- vae/diffusion_pytorch_model.safetensors +3 -0
feature_extractor/preprocessor_config.json
CHANGED
@@ -1,20 +1,27 @@
|
|
1 |
{
|
2 |
-
"crop_size":
|
|
|
|
|
|
|
3 |
"do_center_crop": true,
|
4 |
"do_convert_rgb": true,
|
5 |
"do_normalize": true,
|
|
|
6 |
"do_resize": true,
|
7 |
-
"feature_extractor_type": "CLIPFeatureExtractor",
|
8 |
"image_mean": [
|
9 |
0.48145466,
|
10 |
0.4578275,
|
11 |
0.40821073
|
12 |
],
|
|
|
13 |
"image_std": [
|
14 |
0.26862954,
|
15 |
0.26130258,
|
16 |
0.27577711
|
17 |
],
|
18 |
"resample": 3,
|
19 |
-
"
|
|
|
|
|
|
|
20 |
}
|
|
|
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": "CLIPFeatureExtractor",
|
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 |
}
|
model_index.json
CHANGED
@@ -1,10 +1,15 @@
|
|
1 |
{
|
2 |
"_class_name": "StableDiffusionPipeline",
|
3 |
-
"_diffusers_version": "0.
|
4 |
"feature_extractor": [
|
5 |
"transformers",
|
6 |
-
"
|
7 |
],
|
|
|
|
|
|
|
|
|
|
|
8 |
"safety_checker": [
|
9 |
"stable_diffusion",
|
10 |
"StableDiffusionSafetyChecker"
|
|
|
1 |
{
|
2 |
"_class_name": "StableDiffusionPipeline",
|
3 |
+
"_diffusers_version": "0.27.0.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"
|
safety_checker/config.json
CHANGED
@@ -1,5 +1,4 @@
|
|
1 |
{
|
2 |
-
"_commit_hash": "4bb648a606ef040e7685bde262611766a5fdd67b",
|
3 |
"_name_or_path": "CompVis/stable-diffusion-safety-checker",
|
4 |
"architectures": [
|
5 |
"StableDiffusionSafetyChecker"
|
@@ -9,165 +8,19 @@
|
|
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 |
-
"bos_token_id": 0,
|
18 |
-
"chunk_size_feed_forward": 0,
|
19 |
-
"cross_attention_hidden_size": null,
|
20 |
-
"decoder_start_token_id": null,
|
21 |
-
"diversity_penalty": 0.0,
|
22 |
-
"do_sample": false,
|
23 |
"dropout": 0.0,
|
24 |
-
"early_stopping": false,
|
25 |
-
"encoder_no_repeat_ngram_size": 0,
|
26 |
-
"eos_token_id": 2,
|
27 |
-
"exponential_decay_length_penalty": null,
|
28 |
-
"finetuning_task": null,
|
29 |
-
"forced_bos_token_id": null,
|
30 |
-
"forced_eos_token_id": null,
|
31 |
-
"hidden_act": "quick_gelu",
|
32 |
"hidden_size": 768,
|
33 |
-
"id2label": {
|
34 |
-
"0": "LABEL_0",
|
35 |
-
"1": "LABEL_1"
|
36 |
-
},
|
37 |
-
"initializer_factor": 1.0,
|
38 |
-
"initializer_range": 0.02,
|
39 |
"intermediate_size": 3072,
|
40 |
-
"is_decoder": false,
|
41 |
-
"is_encoder_decoder": false,
|
42 |
-
"label2id": {
|
43 |
-
"LABEL_0": 0,
|
44 |
-
"LABEL_1": 1
|
45 |
-
},
|
46 |
-
"layer_norm_eps": 1e-05,
|
47 |
-
"length_penalty": 1.0,
|
48 |
-
"max_length": 20,
|
49 |
-
"max_position_embeddings": 77,
|
50 |
-
"min_length": 0,
|
51 |
"model_type": "clip_text_model",
|
52 |
-
"
|
53 |
-
"num_attention_heads": 12,
|
54 |
-
"num_beam_groups": 1,
|
55 |
-
"num_beams": 1,
|
56 |
-
"num_hidden_layers": 12,
|
57 |
-
"num_return_sequences": 1,
|
58 |
-
"output_attentions": false,
|
59 |
-
"output_hidden_states": false,
|
60 |
-
"output_scores": false,
|
61 |
-
"pad_token_id": 1,
|
62 |
-
"prefix": null,
|
63 |
-
"problem_type": null,
|
64 |
-
"pruned_heads": {},
|
65 |
-
"remove_invalid_values": false,
|
66 |
-
"repetition_penalty": 1.0,
|
67 |
-
"return_dict": true,
|
68 |
-
"return_dict_in_generate": false,
|
69 |
-
"sep_token_id": null,
|
70 |
-
"task_specific_params": null,
|
71 |
-
"temperature": 1.0,
|
72 |
-
"tf_legacy_loss": false,
|
73 |
-
"tie_encoder_decoder": false,
|
74 |
-
"tie_word_embeddings": true,
|
75 |
-
"tokenizer_class": null,
|
76 |
-
"top_k": 50,
|
77 |
-
"top_p": 1.0,
|
78 |
-
"torch_dtype": null,
|
79 |
-
"torchscript": false,
|
80 |
-
"transformers_version": "4.22.0.dev0",
|
81 |
-
"typical_p": 1.0,
|
82 |
-
"use_bfloat16": false,
|
83 |
-
"vocab_size": 49408
|
84 |
-
},
|
85 |
-
"text_config_dict": {
|
86 |
-
"hidden_size": 768,
|
87 |
-
"intermediate_size": 3072,
|
88 |
-
"num_attention_heads": 12,
|
89 |
-
"num_hidden_layers": 12
|
90 |
},
|
91 |
"torch_dtype": "float32",
|
92 |
-
"transformers_version":
|
93 |
"vision_config": {
|
94 |
-
"_name_or_path": "",
|
95 |
-
"add_cross_attention": false,
|
96 |
-
"architectures": null,
|
97 |
-
"attention_dropout": 0.0,
|
98 |
-
"bad_words_ids": null,
|
99 |
-
"bos_token_id": null,
|
100 |
-
"chunk_size_feed_forward": 0,
|
101 |
-
"cross_attention_hidden_size": null,
|
102 |
-
"decoder_start_token_id": null,
|
103 |
-
"diversity_penalty": 0.0,
|
104 |
-
"do_sample": false,
|
105 |
"dropout": 0.0,
|
106 |
-
"early_stopping": false,
|
107 |
-
"encoder_no_repeat_ngram_size": 0,
|
108 |
-
"eos_token_id": null,
|
109 |
-
"exponential_decay_length_penalty": null,
|
110 |
-
"finetuning_task": null,
|
111 |
-
"forced_bos_token_id": null,
|
112 |
-
"forced_eos_token_id": null,
|
113 |
-
"hidden_act": "quick_gelu",
|
114 |
"hidden_size": 1024,
|
115 |
-
"id2label": {
|
116 |
-
"0": "LABEL_0",
|
117 |
-
"1": "LABEL_1"
|
118 |
-
},
|
119 |
-
"image_size": 224,
|
120 |
-
"initializer_factor": 1.0,
|
121 |
-
"initializer_range": 0.02,
|
122 |
"intermediate_size": 4096,
|
123 |
-
"is_decoder": false,
|
124 |
-
"is_encoder_decoder": false,
|
125 |
-
"label2id": {
|
126 |
-
"LABEL_0": 0,
|
127 |
-
"LABEL_1": 1
|
128 |
-
},
|
129 |
-
"layer_norm_eps": 1e-05,
|
130 |
-
"length_penalty": 1.0,
|
131 |
-
"max_length": 20,
|
132 |
-
"min_length": 0,
|
133 |
"model_type": "clip_vision_model",
|
134 |
-
"no_repeat_ngram_size": 0,
|
135 |
-
"num_attention_heads": 16,
|
136 |
-
"num_beam_groups": 1,
|
137 |
-
"num_beams": 1,
|
138 |
-
"num_channels": 3,
|
139 |
-
"num_hidden_layers": 24,
|
140 |
-
"num_return_sequences": 1,
|
141 |
-
"output_attentions": false,
|
142 |
-
"output_hidden_states": false,
|
143 |
-
"output_scores": false,
|
144 |
-
"pad_token_id": null,
|
145 |
-
"patch_size": 14,
|
146 |
-
"prefix": null,
|
147 |
-
"problem_type": null,
|
148 |
-
"pruned_heads": {},
|
149 |
-
"remove_invalid_values": false,
|
150 |
-
"repetition_penalty": 1.0,
|
151 |
-
"return_dict": true,
|
152 |
-
"return_dict_in_generate": false,
|
153 |
-
"sep_token_id": 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": "4.22.0.dev0",
|
165 |
-
"typical_p": 1.0,
|
166 |
-
"use_bfloat16": false
|
167 |
-
},
|
168 |
-
"vision_config_dict": {
|
169 |
-
"hidden_size": 1024,
|
170 |
-
"intermediate_size": 4096,
|
171 |
"num_attention_heads": 16,
|
172 |
"num_hidden_layers": 24,
|
173 |
"patch_size": 14
|
|
|
1 |
{
|
|
|
2 |
"_name_or_path": "CompVis/stable-diffusion-safety-checker",
|
3 |
"architectures": [
|
4 |
"StableDiffusionSafetyChecker"
|
|
|
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": "4.37.2",
|
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
|
safety_checker/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:fb351a5ded815c3ff744968ad9c6b218d071b9d313d04f35e813b84b4c0ffde8
|
3 |
+
size 1215979664
|
safety_checker/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:fb351a5ded815c3ff744968ad9c6b218d071b9d313d04f35e813b84b4c0ffde8
|
3 |
+
size 1215979664
|
scheduler/scheduler_config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"_class_name": "PNDMScheduler",
|
3 |
-
"_diffusers_version": "0.
|
4 |
"beta_end": 0.012,
|
5 |
"beta_schedule": "scaled_linear",
|
6 |
"beta_start": 0.00085,
|
@@ -10,5 +10,6 @@
|
|
10 |
"set_alpha_to_one": false,
|
11 |
"skip_prk_steps": true,
|
12 |
"steps_offset": 1,
|
|
|
13 |
"trained_betas": null
|
14 |
}
|
|
|
1 |
{
|
2 |
"_class_name": "PNDMScheduler",
|
3 |
+
"_diffusers_version": "0.27.0.dev0",
|
4 |
"beta_end": 0.012,
|
5 |
"beta_schedule": "scaled_linear",
|
6 |
"beta_start": 0.00085,
|
|
|
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": "/content/models/jb2",
|
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": "4.37.2",
|
23 |
"vocab_size": 49408
|
24 |
}
|
text_encoder/model.fp16.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b90f582cd6e497944ff72dc17572aac06dee8db3d863c144b866c21dd2bfa3c
|
3 |
+
size 492265168
|
text_encoder/model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6b90f582cd6e497944ff72dc17572aac06dee8db3d863c144b866c21dd2bfa3c
|
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
@@ -1,9 +1,12 @@
|
|
1 |
{
|
2 |
"_class_name": "UNet2DConditionModel",
|
3 |
-
"_diffusers_version": "0.
|
4 |
-
"_name_or_path": "/content/stable-diffusion-v1-5",
|
5 |
"act_fn": "silu",
|
|
|
|
|
|
|
6 |
"attention_head_dim": 8,
|
|
|
7 |
"block_out_channels": [
|
8 |
320,
|
9 |
640,
|
@@ -12,9 +15,11 @@
|
|
12 |
],
|
13 |
"center_input_sample": false,
|
14 |
"class_embed_type": null,
|
|
|
15 |
"conv_in_kernel": 3,
|
16 |
"conv_out_kernel": 3,
|
17 |
"cross_attention_dim": 768,
|
|
|
18 |
"down_block_types": [
|
19 |
"CrossAttnDownBlock2D",
|
20 |
"CrossAttnDownBlock2D",
|
@@ -22,30 +27,41 @@
|
|
22 |
"DownBlock2D"
|
23 |
],
|
24 |
"downsample_padding": 1,
|
|
|
25 |
"dual_cross_attention": false,
|
|
|
|
|
26 |
"flip_sin_to_cos": true,
|
27 |
"freq_shift": 0,
|
28 |
"in_channels": 4,
|
29 |
"layers_per_block": 2,
|
|
|
30 |
"mid_block_scale_factor": 1,
|
31 |
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
32 |
"norm_eps": 1e-05,
|
33 |
"norm_num_groups": 32,
|
|
|
34 |
"num_class_embeds": null,
|
35 |
"only_cross_attention": false,
|
36 |
"out_channels": 4,
|
37 |
"projection_class_embeddings_input_dim": null,
|
|
|
|
|
38 |
"resnet_time_scale_shift": "default",
|
|
|
39 |
"sample_size": 64,
|
40 |
"time_cond_proj_dim": null,
|
|
|
|
|
41 |
"time_embedding_type": "positional",
|
42 |
"timestep_post_act": null,
|
|
|
43 |
"up_block_types": [
|
44 |
"UpBlock2D",
|
45 |
"CrossAttnUpBlock2D",
|
46 |
"CrossAttnUpBlock2D",
|
47 |
"CrossAttnUpBlock2D"
|
48 |
],
|
49 |
-
"upcast_attention":
|
50 |
"use_linear_projection": false
|
51 |
}
|
|
|
1 |
{
|
2 |
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.27.0.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,
|
|
|
15 |
],
|
16 |
"center_input_sample": false,
|
17 |
"class_embed_type": null,
|
18 |
+
"class_embeddings_concat": false,
|
19 |
"conv_in_kernel": 3,
|
20 |
"conv_out_kernel": 3,
|
21 |
"cross_attention_dim": 768,
|
22 |
+
"cross_attention_norm": null,
|
23 |
"down_block_types": [
|
24 |
"CrossAttnDownBlock2D",
|
25 |
"CrossAttnDownBlock2D",
|
|
|
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,
|
34 |
"flip_sin_to_cos": true,
|
35 |
"freq_shift": 0,
|
36 |
"in_channels": 4,
|
37 |
"layers_per_block": 2,
|
38 |
+
"mid_block_only_cross_attention": null,
|
39 |
"mid_block_scale_factor": 1,
|
40 |
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
41 |
"norm_eps": 1e-05,
|
42 |
"norm_num_groups": 32,
|
43 |
+
"num_attention_heads": null,
|
44 |
"num_class_embeds": null,
|
45 |
"only_cross_attention": false,
|
46 |
"out_channels": 4,
|
47 |
"projection_class_embeddings_input_dim": 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": 64,
|
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",
|
62 |
"CrossAttnUpBlock2D",
|
63 |
"CrossAttnUpBlock2D"
|
64 |
],
|
65 |
+
"upcast_attention": null,
|
66 |
"use_linear_projection": false
|
67 |
}
|
unet/diffusion_pytorch_model.fp16.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:58f109d2c140547779d33613bb3f4dbc06c97b227d593262dc9f9b7e37f7fe70
|
3 |
+
size 3438167536
|
unet/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:58f109d2c140547779d33613bb3f4dbc06c97b227d593262dc9f9b7e37f7fe70
|
3 |
+
size 3438167536
|
vae/config.json
CHANGED
@@ -1,7 +1,6 @@
|
|
1 |
{
|
2 |
"_class_name": "AutoencoderKL",
|
3 |
-
"_diffusers_version": "0.
|
4 |
-
"_name_or_path": "/content/stable-diffusion-v1-5/vae",
|
5 |
"act_fn": "silu",
|
6 |
"block_out_channels": [
|
7 |
128,
|
@@ -15,6 +14,7 @@
|
|
15 |
"DownEncoderBlock2D",
|
16 |
"DownEncoderBlock2D"
|
17 |
],
|
|
|
18 |
"in_channels": 3,
|
19 |
"latent_channels": 4,
|
20 |
"layers_per_block": 2,
|
|
|
1 |
{
|
2 |
"_class_name": "AutoencoderKL",
|
3 |
+
"_diffusers_version": "0.27.0.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.fp16.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc436097e5cbb105c44df4403ae84acf7e81de1f64acfedc334888e9a8eea223
|
3 |
+
size 334643268
|
vae/diffusion_pytorch_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc436097e5cbb105c44df4403ae84acf7e81de1f64acfedc334888e9a8eea223
|
3 |
+
size 334643268
|