Upload 16 files
#4
by
AdamOswald1
- opened
- feature_extractor/preprocessor_config.json +2 -10
- safety_checker/config.json +4 -14
- safety_checker/pytorch_model.bin +2 -2
- scheduler/scheduler_config.json +3 -3
- text_encoder/config.json +1 -1
- text_encoder/pytorch_model.bin +1 -1
- tokenizer/tokenizer_config.json +0 -14
- unet/config.json +2 -5
- unet/diffusion_pytorch_model.bin +1 -1
- vae/config.json +2 -2
- vae/diffusion_pytorch_model.bin +1 -1
feature_extractor/preprocessor_config.json
CHANGED
@@ -1,12 +1,8 @@
|
|
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 |
"feature_extractor_type": "CLIPFeatureExtractor",
|
12 |
"image_mean": [
|
@@ -14,15 +10,11 @@
|
|
14 |
0.4578275,
|
15 |
0.40821073
|
16 |
],
|
17 |
-
"image_processor_type": "CLIPFeatureExtractor",
|
18 |
"image_std": [
|
19 |
0.26862954,
|
20 |
0.26130258,
|
21 |
0.27577711
|
22 |
],
|
23 |
"resample": 3,
|
24 |
-
"
|
25 |
-
"size": {
|
26 |
-
"shortest_edge": 224
|
27 |
-
}
|
28 |
}
|
|
|
1 |
{
|
2 |
+
"crop_size": 224,
|
|
|
|
|
|
|
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": [
|
|
|
10 |
0.4578275,
|
11 |
0.40821073
|
12 |
],
|
|
|
13 |
"image_std": [
|
14 |
0.26862954,
|
15 |
0.26130258,
|
16 |
0.27577711
|
17 |
],
|
18 |
"resample": 3,
|
19 |
+
"size": 224
|
|
|
|
|
|
|
20 |
}
|
safety_checker/config.json
CHANGED
@@ -1,8 +1,7 @@
|
|
1 |
{
|
2 |
-
"
|
3 |
-
"_name_or_path": "CompVis/stable-diffusion-safety-checker",
|
4 |
"architectures": [
|
5 |
-
"
|
6 |
],
|
7 |
"initializer_factor": 1.0,
|
8 |
"logit_scale_init_value": 2.6592,
|
@@ -14,7 +13,6 @@
|
|
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,
|
@@ -62,17 +60,14 @@
|
|
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,
|
@@ -80,7 +75,7 @@
|
|
80 |
"top_p": 1.0,
|
81 |
"torch_dtype": null,
|
82 |
"torchscript": false,
|
83 |
-
"transformers_version": "4.
|
84 |
"typical_p": 1.0,
|
85 |
"use_bfloat16": false,
|
86 |
"vocab_size": 49408
|
@@ -99,7 +94,6 @@
|
|
99 |
"architectures": null,
|
100 |
"attention_dropout": 0.0,
|
101 |
"bad_words_ids": null,
|
102 |
-
"begin_suppress_tokens": null,
|
103 |
"bos_token_id": null,
|
104 |
"chunk_size_feed_forward": 0,
|
105 |
"cross_attention_hidden_size": null,
|
@@ -139,7 +133,6 @@
|
|
139 |
"num_attention_heads": 16,
|
140 |
"num_beam_groups": 1,
|
141 |
"num_beams": 1,
|
142 |
-
"num_channels": 3,
|
143 |
"num_hidden_layers": 24,
|
144 |
"num_return_sequences": 1,
|
145 |
"output_attentions": false,
|
@@ -149,17 +142,14 @@
|
|
149 |
"patch_size": 14,
|
150 |
"prefix": null,
|
151 |
"problem_type": null,
|
152 |
-
"projection_dim": 512,
|
153 |
"pruned_heads": {},
|
154 |
"remove_invalid_values": false,
|
155 |
"repetition_penalty": 1.0,
|
156 |
"return_dict": true,
|
157 |
"return_dict_in_generate": false,
|
158 |
"sep_token_id": null,
|
159 |
-
"suppress_tokens": null,
|
160 |
"task_specific_params": null,
|
161 |
"temperature": 1.0,
|
162 |
-
"tf_legacy_loss": false,
|
163 |
"tie_encoder_decoder": false,
|
164 |
"tie_word_embeddings": true,
|
165 |
"tokenizer_class": null,
|
@@ -167,7 +157,7 @@
|
|
167 |
"top_p": 1.0,
|
168 |
"torch_dtype": null,
|
169 |
"torchscript": false,
|
170 |
-
"transformers_version": "4.
|
171 |
"typical_p": 1.0,
|
172 |
"use_bfloat16": false
|
173 |
},
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "clip-vit-large-patch14/",
|
|
|
3 |
"architectures": [
|
4 |
+
"SafetyChecker"
|
5 |
],
|
6 |
"initializer_factor": 1.0,
|
7 |
"logit_scale_init_value": 2.6592,
|
|
|
13 |
"architectures": null,
|
14 |
"attention_dropout": 0.0,
|
15 |
"bad_words_ids": null,
|
|
|
16 |
"bos_token_id": 0,
|
17 |
"chunk_size_feed_forward": 0,
|
18 |
"cross_attention_hidden_size": null,
|
|
|
60 |
"pad_token_id": 1,
|
61 |
"prefix": null,
|
62 |
"problem_type": null,
|
|
|
63 |
"pruned_heads": {},
|
64 |
"remove_invalid_values": false,
|
65 |
"repetition_penalty": 1.0,
|
66 |
"return_dict": true,
|
67 |
"return_dict_in_generate": false,
|
68 |
"sep_token_id": null,
|
|
|
69 |
"task_specific_params": null,
|
70 |
"temperature": 1.0,
|
|
|
71 |
"tie_encoder_decoder": false,
|
72 |
"tie_word_embeddings": true,
|
73 |
"tokenizer_class": null,
|
|
|
75 |
"top_p": 1.0,
|
76 |
"torch_dtype": null,
|
77 |
"torchscript": false,
|
78 |
+
"transformers_version": "4.21.0.dev0",
|
79 |
"typical_p": 1.0,
|
80 |
"use_bfloat16": false,
|
81 |
"vocab_size": 49408
|
|
|
94 |
"architectures": null,
|
95 |
"attention_dropout": 0.0,
|
96 |
"bad_words_ids": null,
|
|
|
97 |
"bos_token_id": null,
|
98 |
"chunk_size_feed_forward": 0,
|
99 |
"cross_attention_hidden_size": null,
|
|
|
133 |
"num_attention_heads": 16,
|
134 |
"num_beam_groups": 1,
|
135 |
"num_beams": 1,
|
|
|
136 |
"num_hidden_layers": 24,
|
137 |
"num_return_sequences": 1,
|
138 |
"output_attentions": false,
|
|
|
142 |
"patch_size": 14,
|
143 |
"prefix": null,
|
144 |
"problem_type": null,
|
|
|
145 |
"pruned_heads": {},
|
146 |
"remove_invalid_values": false,
|
147 |
"repetition_penalty": 1.0,
|
148 |
"return_dict": true,
|
149 |
"return_dict_in_generate": false,
|
150 |
"sep_token_id": null,
|
|
|
151 |
"task_specific_params": null,
|
152 |
"temperature": 1.0,
|
|
|
153 |
"tie_encoder_decoder": false,
|
154 |
"tie_word_embeddings": true,
|
155 |
"tokenizer_class": null,
|
|
|
157 |
"top_p": 1.0,
|
158 |
"torch_dtype": null,
|
159 |
"torchscript": false,
|
160 |
+
"transformers_version": "4.21.0.dev0",
|
161 |
"typical_p": 1.0,
|
162 |
"use_bfloat16": false
|
163 |
},
|
safety_checker/pytorch_model.bin
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 sha256:64b8393f1afd5a0c1ed2aa5f341fa7c08286839a48f3743162a76a2835c808bd
|
3 |
+
size 1216067303
|
scheduler/scheduler_config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
-
"_class_name": "
|
3 |
-
"_diffusers_version": "0.
|
4 |
"beta_end": 0.012,
|
5 |
"beta_schedule": "scaled_linear",
|
6 |
"beta_start": 0.00085,
|
@@ -11,4 +11,4 @@
|
|
11 |
"skip_prk_steps": true,
|
12 |
"steps_offset": 1,
|
13 |
"trained_betas": null
|
14 |
-
}
|
|
|
1 |
{
|
2 |
+
"_class_name": "DDIMScheduler",
|
3 |
+
"_diffusers_version": "0.10.2",
|
4 |
"beta_end": 0.012,
|
5 |
"beta_schedule": "scaled_linear",
|
6 |
"beta_start": 0.00085,
|
|
|
11 |
"skip_prk_steps": true,
|
12 |
"steps_offset": 1,
|
13 |
"trained_betas": null
|
14 |
+
}
|
text_encoder/config.json
CHANGED
@@ -20,6 +20,6 @@
|
|
20 |
"pad_token_id": 1,
|
21 |
"projection_dim": 768,
|
22 |
"torch_dtype": "float32",
|
23 |
-
"transformers_version": "4.
|
24 |
"vocab_size": 49408
|
25 |
}
|
|
|
20 |
"pad_token_id": 1,
|
21 |
"projection_dim": 768,
|
22 |
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.25.1",
|
24 |
"vocab_size": 49408
|
25 |
}
|
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 sha256:8d1524362379cb659b9f0bf9b8e4970cd2aea08a6657dbfd51606c64ebeec8ed
|
3 |
size 492307041
|
tokenizer/tokenizer_config.json
CHANGED
@@ -23,20 +23,6 @@
|
|
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 |
-
"errors": "replace",
|
35 |
-
"model_max_length": 77,
|
36 |
-
"name_or_path": "openai/clip-vit-large-patch14",
|
37 |
-
"pad_token": "<|endoftext|>",
|
38 |
-
"special_tokens_map_file": "./special_tokens_map.json",
|
39 |
-
"tokenizer_class": "CLIPTokenizer",
|
40 |
"unk_token": {
|
41 |
"__type": "AddedToken",
|
42 |
"content": "<|endoftext|>",
|
|
|
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|>",
|
unet/config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"_class_name": "UNet2DConditionModel",
|
3 |
-
"_diffusers_version": "0.
|
4 |
"act_fn": "silu",
|
5 |
"attention_head_dim": 8,
|
6 |
"block_out_channels": [
|
@@ -10,7 +10,6 @@
|
|
10 |
1280
|
11 |
],
|
12 |
"center_input_sample": false,
|
13 |
-
"class_embed_type": null,
|
14 |
"cross_attention_dim": 768,
|
15 |
"down_block_types": [
|
16 |
"CrossAttnDownBlock2D",
|
@@ -25,14 +24,12 @@
|
|
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 |
-
"
|
35 |
-
"sample_size": 64,
|
36 |
"up_block_types": [
|
37 |
"UpBlock2D",
|
38 |
"CrossAttnUpBlock2D",
|
|
|
1 |
{
|
2 |
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.10.2",
|
4 |
"act_fn": "silu",
|
5 |
"attention_head_dim": 8,
|
6 |
"block_out_channels": [
|
|
|
10 |
1280
|
11 |
],
|
12 |
"center_input_sample": false,
|
|
|
13 |
"cross_attention_dim": 768,
|
14 |
"down_block_types": [
|
15 |
"CrossAttnDownBlock2D",
|
|
|
24 |
"in_channels": 4,
|
25 |
"layers_per_block": 2,
|
26 |
"mid_block_scale_factor": 1,
|
|
|
27 |
"norm_eps": 1e-05,
|
28 |
"norm_num_groups": 32,
|
29 |
"num_class_embeds": null,
|
30 |
"only_cross_attention": false,
|
31 |
"out_channels": 4,
|
32 |
+
"sample_size": 32,
|
|
|
33 |
"up_block_types": [
|
34 |
"UpBlock2D",
|
35 |
"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:c727c1864179e43a3338a99e28e08f9c7b12cd46e56e60afb429e17c57644c14
|
3 |
size 3438366373
|
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,
|
@@ -19,7 +19,7 @@
|
|
19 |
"layers_per_block": 2,
|
20 |
"norm_num_groups": 32,
|
21 |
"out_channels": 3,
|
22 |
-
"sample_size":
|
23 |
"up_block_types": [
|
24 |
"UpDecoderBlock2D",
|
25 |
"UpDecoderBlock2D",
|
|
|
1 |
{
|
2 |
"_class_name": "AutoencoderKL",
|
3 |
+
"_diffusers_version": "0.10.2",
|
4 |
"act_fn": "silu",
|
5 |
"block_out_channels": [
|
6 |
128,
|
|
|
19 |
"layers_per_block": 2,
|
20 |
"norm_num_groups": 32,
|
21 |
"out_channels": 3,
|
22 |
+
"sample_size": 256,
|
23 |
"up_block_types": [
|
24 |
"UpDecoderBlock2D",
|
25 |
"UpDecoderBlock2D",
|
vae/diffusion_pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 334711857
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:876a906810a8b2470c3092f307742f6ad8b9dbf759fb7c0ff020d0c610c996da
|
3 |
size 334711857
|