Update configs
Browse files- model_index.json +2 -2
- safety_checker/config.json +2 -6
- scheduler/scheduler_config.json +2 -6
- text_encoder/config.json +2 -2
- tokenizer/special_tokens_map.json +1 -24
- tokenizer/tokenizer_config.json +1 -34
- tokenizer/vocab.json +0 -0
- unet/config.json +3 -9
- vae/config.json +1 -3
model_index.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"_class_name": "StableDiffusionPipeline",
|
3 |
-
"_diffusers_version": "0.
|
4 |
"feature_extractor": [
|
5 |
"transformers",
|
6 |
"CLIPFeatureExtractor"
|
@@ -29,4 +29,4 @@
|
|
29 |
"diffusers",
|
30 |
"AutoencoderKL"
|
31 |
]
|
32 |
-
}
|
|
|
1 |
{
|
2 |
"_class_name": "StableDiffusionPipeline",
|
3 |
+
"_diffusers_version": "0.2.4",
|
4 |
"feature_extractor": [
|
5 |
"transformers",
|
6 |
"CLIPFeatureExtractor"
|
|
|
29 |
"diffusers",
|
30 |
"AutoencoderKL"
|
31 |
]
|
32 |
+
}
|
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"
|
@@ -69,7 +68,6 @@
|
|
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,
|
@@ -77,7 +75,7 @@
|
|
77 |
"top_p": 1.0,
|
78 |
"torch_dtype": null,
|
79 |
"torchscript": false,
|
80 |
-
"transformers_version": "4.
|
81 |
"typical_p": 1.0,
|
82 |
"use_bfloat16": false,
|
83 |
"vocab_size": 49408
|
@@ -135,7 +133,6 @@
|
|
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,
|
@@ -153,7 +150,6 @@
|
|
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,
|
@@ -161,7 +157,7 @@
|
|
161 |
"top_p": 1.0,
|
162 |
"torch_dtype": null,
|
163 |
"torchscript": false,
|
164 |
-
"transformers_version": "4.
|
165 |
"typical_p": 1.0,
|
166 |
"use_bfloat16": false
|
167 |
},
|
|
|
1 |
{
|
|
|
2 |
"_name_or_path": "CompVis/stable-diffusion-safety-checker",
|
3 |
"architectures": [
|
4 |
"StableDiffusionSafetyChecker"
|
|
|
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": "4.19.2",
|
79 |
"typical_p": 1.0,
|
80 |
"use_bfloat16": false,
|
81 |
"vocab_size": 49408
|
|
|
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,
|
|
|
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": "4.19.2",
|
161 |
"typical_p": 1.0,
|
162 |
"use_bfloat16": false
|
163 |
},
|
scheduler/scheduler_config.json
CHANGED
@@ -1,13 +1,9 @@
|
|
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 |
"num_train_timesteps": 1000,
|
8 |
-
"
|
9 |
-
"set_alpha_to_one": false,
|
10 |
-
"skip_prk_steps": true,
|
11 |
-
"steps_offset": 1,
|
12 |
-
"trained_betas": null
|
13 |
}
|
|
|
1 |
{
|
2 |
"_class_name": "PNDMScheduler",
|
3 |
+
"_diffusers_version": "0.2.4",
|
4 |
"beta_end": 0.012,
|
5 |
"beta_schedule": "scaled_linear",
|
6 |
"beta_start": 0.00085,
|
7 |
"num_train_timesteps": 1000,
|
8 |
+
"skip_prk_steps": true
|
|
|
|
|
|
|
|
|
9 |
}
|
text_encoder/config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"CLIPTextModel"
|
5 |
],
|
@@ -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 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "openai/clip-vit-large-patch14",
|
3 |
"architectures": [
|
4 |
"CLIPTextModel"
|
5 |
],
|
|
|
20 |
"pad_token_id": 1,
|
21 |
"projection_dim": 768,
|
22 |
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.19.2",
|
24 |
"vocab_size": 49408
|
25 |
}
|
tokenizer/special_tokens_map.json
CHANGED
@@ -1,24 +1 @@
|
|
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 |
-
}
|
|
|
1 |
+
{"bos_token": {"content": "<|startoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true}, "pad_token": "<|endoftext|>"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer/tokenizer_config.json
CHANGED
@@ -1,34 +1 @@
|
|
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": "H:\\AI_Dataset\\SD\\StableDiffusionModel\\sd1.5-fine-tunable-for-dreamboothTrain\\tokenizer",
|
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 |
-
}
|
|
|
1 |
+
{"errors": "replace", "unk_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "bos_token": {"content": "<|startoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "eos_token": {"content": "<|endoftext|>", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "__type": "AddedToken"}, "pad_token": "<|endoftext|>", "add_prefix_space": false, "do_lower_case": true, "name_or_path": "openai/clip-vit-large-patch14", "model_max_length": 77, "special_tokens_map_file": "./special_tokens_map.json", "tokenizer_class": "CLIPTokenizer"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer/vocab.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
unet/config.json
CHANGED
@@ -1,7 +1,6 @@
|
|
1 |
{
|
2 |
"_class_name": "UNet2DConditionModel",
|
3 |
-
"_diffusers_version": "0.
|
4 |
-
"_name_or_path": "H:\\AI_Dataset\\SD\\StableDiffusionModel\\sd1.5-fine-tunable-for-dreamboothTrain",
|
5 |
"act_fn": "silu",
|
6 |
"attention_head_dim": 8,
|
7 |
"block_out_channels": [
|
@@ -19,7 +18,6 @@
|
|
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,
|
@@ -27,16 +25,12 @@
|
|
27 |
"mid_block_scale_factor": 1,
|
28 |
"norm_eps": 1e-05,
|
29 |
"norm_num_groups": 32,
|
30 |
-
"num_class_embeds": null,
|
31 |
-
"only_cross_attention": false,
|
32 |
"out_channels": 4,
|
33 |
-
"sample_size":
|
34 |
"up_block_types": [
|
35 |
"UpBlock2D",
|
36 |
"CrossAttnUpBlock2D",
|
37 |
"CrossAttnUpBlock2D",
|
38 |
"CrossAttnUpBlock2D"
|
39 |
-
]
|
40 |
-
"upcast_attention": false,
|
41 |
-
"use_linear_projection": false
|
42 |
}
|
|
|
1 |
{
|
2 |
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.2.4",
|
|
|
4 |
"act_fn": "silu",
|
5 |
"attention_head_dim": 8,
|
6 |
"block_out_channels": [
|
|
|
18 |
"DownBlock2D"
|
19 |
],
|
20 |
"downsample_padding": 1,
|
|
|
21 |
"flip_sin_to_cos": true,
|
22 |
"freq_shift": 0,
|
23 |
"in_channels": 4,
|
|
|
25 |
"mid_block_scale_factor": 1,
|
26 |
"norm_eps": 1e-05,
|
27 |
"norm_num_groups": 32,
|
|
|
|
|
28 |
"out_channels": 4,
|
29 |
+
"sample_size": 32,
|
30 |
"up_block_types": [
|
31 |
"UpBlock2D",
|
32 |
"CrossAttnUpBlock2D",
|
33 |
"CrossAttnUpBlock2D",
|
34 |
"CrossAttnUpBlock2D"
|
35 |
+
]
|
|
|
|
|
36 |
}
|
vae/config.json
CHANGED
@@ -1,7 +1,6 @@
|
|
1 |
{
|
2 |
"_class_name": "AutoencoderKL",
|
3 |
-
"_diffusers_version": "0.
|
4 |
-
"_name_or_path": "H:\\AI_Dataset\\SD\\StableDiffusionModel\\sd1.5-fine-tunable-for-dreamboothTrain\\vae",
|
5 |
"act_fn": "silu",
|
6 |
"block_out_channels": [
|
7 |
128,
|
@@ -18,7 +17,6 @@
|
|
18 |
"in_channels": 3,
|
19 |
"latent_channels": 4,
|
20 |
"layers_per_block": 2,
|
21 |
-
"norm_num_groups": 32,
|
22 |
"out_channels": 3,
|
23 |
"sample_size": 512,
|
24 |
"up_block_types": [
|
|
|
1 |
{
|
2 |
"_class_name": "AutoencoderKL",
|
3 |
+
"_diffusers_version": "0.2.4",
|
|
|
4 |
"act_fn": "silu",
|
5 |
"block_out_channels": [
|
6 |
128,
|
|
|
17 |
"in_channels": 3,
|
18 |
"latent_channels": 4,
|
19 |
"layers_per_block": 2,
|
|
|
20 |
"out_channels": 3,
|
21 |
"sample_size": 512,
|
22 |
"up_block_types": [
|