update model
Browse files- feature_extractor/preprocessor_config.json +10 -2
- model_index.json +5 -5
- pixel-art-style.ckpt +2 -2
- pixel-art-style.yaml +0 -68
- safety_checker/config.json +181 -0
- text_encoder/model.safetensors → safety_checker/pytorch_model.bin +2 -2
- scheduler/scheduler_config.json +3 -2
- text_encoder/config.json +8 -8
- text_encoder/pytorch_model.bin +2 -2
- tokenizer/special_tokens_map.json +1 -1
- tokenizer/tokenizer_config.json +1 -1
- unet/config.json +11 -10
- unet/diffusion_pytorch_model.bin +2 -2
- unet/diffusion_pytorch_model.safetensors +0 -3
- vae/config.json +3 -3
- vae/diffusion_pytorch_model.bin +2 -2
- vae/diffusion_pytorch_model.safetensors +0 -3
feature_extractor/preprocessor_config.json
CHANGED
@@ -1,8 +1,12 @@
|
|
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": [
|
@@ -10,11 +14,15 @@
|
|
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 |
"feature_extractor_type": "CLIPFeatureExtractor",
|
12 |
"image_mean": [
|
|
|
14 |
0.4578275,
|
15 |
0.40821073
|
16 |
],
|
17 |
+
"image_processor_type": "CLIPImageProcessor",
|
18 |
"image_std": [
|
19 |
0.26862954,
|
20 |
0.26130258,
|
21 |
0.27577711
|
22 |
],
|
23 |
"resample": 3,
|
24 |
+
"rescale_factor": 0.00392156862745098,
|
25 |
+
"size": {
|
26 |
+
"shortest_edge": 224
|
27 |
+
}
|
28 |
}
|
model_index.json
CHANGED
@@ -1,10 +1,11 @@
|
|
1 |
{
|
2 |
"_class_name": "StableDiffusionPipeline",
|
3 |
-
"_diffusers_version": "0.
|
4 |
"feature_extractor": [
|
5 |
"transformers",
|
6 |
-
"
|
7 |
],
|
|
|
8 |
"safety_checker": [
|
9 |
null,
|
10 |
null
|
@@ -28,6 +29,5 @@
|
|
28 |
"vae": [
|
29 |
"diffusers",
|
30 |
"AutoencoderKL"
|
31 |
-
]
|
32 |
-
|
33 |
-
}
|
|
|
1 |
{
|
2 |
"_class_name": "StableDiffusionPipeline",
|
3 |
+
"_diffusers_version": "0.11.1",
|
4 |
"feature_extractor": [
|
5 |
"transformers",
|
6 |
+
"CLIPImageProcessor"
|
7 |
],
|
8 |
+
"requires_safety_checker": false,
|
9 |
"safety_checker": [
|
10 |
null,
|
11 |
null
|
|
|
29 |
"vae": [
|
30 |
"diffusers",
|
31 |
"AutoencoderKL"
|
32 |
+
]
|
33 |
+
}
|
|
pixel-art-style.ckpt
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 sha256:293e4c037d2d6b6b3970b96f5df7af17554f1e7d5eca132c049ef1eb677196d6
|
3 |
+
size 4098020782
|
pixel-art-style.yaml
DELETED
@@ -1,68 +0,0 @@
|
|
1 |
-
model:
|
2 |
-
base_learning_rate: 1.0e-4
|
3 |
-
target: ldm.models.diffusion.ddpm.LatentDiffusion
|
4 |
-
params:
|
5 |
-
parameterization: "v"
|
6 |
-
linear_start: 0.00085
|
7 |
-
linear_end: 0.0120
|
8 |
-
num_timesteps_cond: 1
|
9 |
-
log_every_t: 200
|
10 |
-
timesteps: 1000
|
11 |
-
first_stage_key: "jpg"
|
12 |
-
cond_stage_key: "txt"
|
13 |
-
image_size: 64
|
14 |
-
channels: 4
|
15 |
-
cond_stage_trainable: false
|
16 |
-
conditioning_key: crossattn
|
17 |
-
monitor: val/loss_simple_ema
|
18 |
-
scale_factor: 0.18215
|
19 |
-
use_ema: False # we set this to false because this is an inference only config
|
20 |
-
|
21 |
-
unet_config:
|
22 |
-
target: ldm.modules.diffusionmodules.openaimodel.UNetModel
|
23 |
-
params:
|
24 |
-
use_checkpoint: True
|
25 |
-
use_fp16: True
|
26 |
-
image_size: 32 # unused
|
27 |
-
in_channels: 4
|
28 |
-
out_channels: 4
|
29 |
-
model_channels: 320
|
30 |
-
attention_resolutions: [ 4, 2, 1 ]
|
31 |
-
num_res_blocks: 2
|
32 |
-
channel_mult: [ 1, 2, 4, 4 ]
|
33 |
-
num_head_channels: 64 # need to fix for flash-attn
|
34 |
-
use_spatial_transformer: True
|
35 |
-
use_linear_in_transformer: True
|
36 |
-
transformer_depth: 1
|
37 |
-
context_dim: 1024
|
38 |
-
legacy: False
|
39 |
-
|
40 |
-
first_stage_config:
|
41 |
-
target: ldm.models.autoencoder.AutoencoderKL
|
42 |
-
params:
|
43 |
-
embed_dim: 4
|
44 |
-
monitor: val/rec_loss
|
45 |
-
ddconfig:
|
46 |
-
#attn_type: "vanilla-xformers"
|
47 |
-
double_z: true
|
48 |
-
z_channels: 4
|
49 |
-
resolution: 256
|
50 |
-
in_channels: 3
|
51 |
-
out_ch: 3
|
52 |
-
ch: 128
|
53 |
-
ch_mult:
|
54 |
-
- 1
|
55 |
-
- 2
|
56 |
-
- 4
|
57 |
-
- 4
|
58 |
-
num_res_blocks: 2
|
59 |
-
attn_resolutions: []
|
60 |
-
dropout: 0.0
|
61 |
-
lossconfig:
|
62 |
-
target: torch.nn.Identity
|
63 |
-
|
64 |
-
cond_stage_config:
|
65 |
-
target: ldm.modules.encoders.modules.FrozenOpenCLIPEmbedder
|
66 |
-
params:
|
67 |
-
freeze: True
|
68 |
-
layer: "penultimate"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
safety_checker/config.json
ADDED
@@ -0,0 +1,181 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_commit_hash": "889b629140e71758e1e0006e355c331a5744b4bf",
|
3 |
+
"_name_or_path": "/root/.cache/huggingface/diffusers/models--runwayml--stable-diffusion-v1-5/snapshots/889b629140e71758e1e0006e355c331a5744b4bf/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": "4.25.1",
|
84 |
+
"typical_p": 1.0,
|
85 |
+
"use_bfloat16": false,
|
86 |
+
"vocab_size": 49408
|
87 |
+
},
|
88 |
+
"text_config_dict": {
|
89 |
+
"hidden_size": 768,
|
90 |
+
"intermediate_size": 3072,
|
91 |
+
"num_attention_heads": 12,
|
92 |
+
"num_hidden_layers": 12
|
93 |
+
},
|
94 |
+
"torch_dtype": "float32",
|
95 |
+
"transformers_version": null,
|
96 |
+
"vision_config": {
|
97 |
+
"_name_or_path": "",
|
98 |
+
"add_cross_attention": false,
|
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,
|
106 |
+
"decoder_start_token_id": null,
|
107 |
+
"diversity_penalty": 0.0,
|
108 |
+
"do_sample": false,
|
109 |
+
"dropout": 0.0,
|
110 |
+
"early_stopping": false,
|
111 |
+
"encoder_no_repeat_ngram_size": 0,
|
112 |
+
"eos_token_id": null,
|
113 |
+
"exponential_decay_length_penalty": null,
|
114 |
+
"finetuning_task": null,
|
115 |
+
"forced_bos_token_id": null,
|
116 |
+
"forced_eos_token_id": null,
|
117 |
+
"hidden_act": "quick_gelu",
|
118 |
+
"hidden_size": 1024,
|
119 |
+
"id2label": {
|
120 |
+
"0": "LABEL_0",
|
121 |
+
"1": "LABEL_1"
|
122 |
+
},
|
123 |
+
"image_size": 224,
|
124 |
+
"initializer_factor": 1.0,
|
125 |
+
"initializer_range": 0.02,
|
126 |
+
"intermediate_size": 4096,
|
127 |
+
"is_decoder": false,
|
128 |
+
"is_encoder_decoder": false,
|
129 |
+
"label2id": {
|
130 |
+
"LABEL_0": 0,
|
131 |
+
"LABEL_1": 1
|
132 |
+
},
|
133 |
+
"layer_norm_eps": 1e-05,
|
134 |
+
"length_penalty": 1.0,
|
135 |
+
"max_length": 20,
|
136 |
+
"min_length": 0,
|
137 |
+
"model_type": "clip_vision_model",
|
138 |
+
"no_repeat_ngram_size": 0,
|
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,
|
146 |
+
"output_hidden_states": false,
|
147 |
+
"output_scores": false,
|
148 |
+
"pad_token_id": null,
|
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,
|
166 |
+
"top_k": 50,
|
167 |
+
"top_p": 1.0,
|
168 |
+
"torch_dtype": null,
|
169 |
+
"torchscript": false,
|
170 |
+
"transformers_version": "4.25.1",
|
171 |
+
"typical_p": 1.0,
|
172 |
+
"use_bfloat16": false
|
173 |
+
},
|
174 |
+
"vision_config_dict": {
|
175 |
+
"hidden_size": 1024,
|
176 |
+
"intermediate_size": 4096,
|
177 |
+
"num_attention_heads": 16,
|
178 |
+
"num_hidden_layers": 24,
|
179 |
+
"patch_size": 14
|
180 |
+
}
|
181 |
+
}
|
text_encoder/model.safetensors → safety_checker/pytorch_model.bin
RENAMED
@@ -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 sha256:16d28f2b37109f222cdc33620fdd262102ac32112be0352a7f77e9614b35a394
|
3 |
+
size 1216064769
|
scheduler/scheduler_config.json
CHANGED
@@ -1,11 +1,12 @@
|
|
1 |
{
|
2 |
-
"_class_name": "
|
3 |
-
"_diffusers_version": "0.
|
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 |
"set_alpha_to_one": false,
|
10 |
"skip_prk_steps": true,
|
11 |
"steps_offset": 1,
|
|
|
1 |
{
|
2 |
+
"_class_name": "PNDMScheduler",
|
3 |
+
"_diffusers_version": "0.11.1",
|
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,
|
text_encoder/config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "/
|
3 |
"architectures": [
|
4 |
"CLIPTextModel"
|
5 |
],
|
@@ -7,19 +7,19 @@
|
|
7 |
"bos_token_id": 0,
|
8 |
"dropout": 0.0,
|
9 |
"eos_token_id": 2,
|
10 |
-
"hidden_act": "
|
11 |
-
"hidden_size":
|
12 |
"initializer_factor": 1.0,
|
13 |
"initializer_range": 0.02,
|
14 |
-
"intermediate_size":
|
15 |
"layer_norm_eps": 1e-05,
|
16 |
"max_position_embeddings": 77,
|
17 |
"model_type": "clip_text_model",
|
18 |
-
"num_attention_heads":
|
19 |
-
"num_hidden_layers":
|
20 |
"pad_token_id": 1,
|
21 |
-
"projection_dim":
|
22 |
"torch_dtype": "float32",
|
23 |
-
"transformers_version": "4.25.
|
24 |
"vocab_size": 49408
|
25 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/root/.cache/huggingface/diffusers/models--runwayml--stable-diffusion-v1-5/snapshots/889b629140e71758e1e0006e355c331a5744b4bf/text_encoder",
|
3 |
"architectures": [
|
4 |
"CLIPTextModel"
|
5 |
],
|
|
|
7 |
"bos_token_id": 0,
|
8 |
"dropout": 0.0,
|
9 |
"eos_token_id": 2,
|
10 |
+
"hidden_act": "quick_gelu",
|
11 |
+
"hidden_size": 768,
|
12 |
"initializer_factor": 1.0,
|
13 |
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 3072,
|
15 |
"layer_norm_eps": 1e-05,
|
16 |
"max_position_embeddings": 77,
|
17 |
"model_type": "clip_text_model",
|
18 |
+
"num_attention_heads": 12,
|
19 |
+
"num_hidden_layers": 12,
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:98124f3d5663b2f14ff08d4c29db93800622b4fcfa3d952bb6f9112f5d6dadd7
|
3 |
+
size 492307041
|
tokenizer/special_tokens_map.json
CHANGED
@@ -13,7 +13,7 @@
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
-
"pad_token": "
|
17 |
"unk_token": {
|
18 |
"content": "<|endoftext|>",
|
19 |
"lstrip": false,
|
|
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
+
"pad_token": "<|endoftext|>",
|
17 |
"unk_token": {
|
18 |
"content": "<|endoftext|>",
|
19 |
"lstrip": false,
|
tokenizer/tokenizer_config.json
CHANGED
@@ -19,7 +19,7 @@
|
|
19 |
},
|
20 |
"errors": "replace",
|
21 |
"model_max_length": 77,
|
22 |
-
"name_or_path": "/
|
23 |
"pad_token": "<|endoftext|>",
|
24 |
"special_tokens_map_file": "./special_tokens_map.json",
|
25 |
"tokenizer_class": "CLIPTokenizer",
|
|
|
19 |
},
|
20 |
"errors": "replace",
|
21 |
"model_max_length": 77,
|
22 |
+
"name_or_path": "/root/.cache/huggingface/diffusers/models--runwayml--stable-diffusion-v1-5/snapshots/889b629140e71758e1e0006e355c331a5744b4bf/tokenizer",
|
23 |
"pad_token": "<|endoftext|>",
|
24 |
"special_tokens_map_file": "./special_tokens_map.json",
|
25 |
"tokenizer_class": "CLIPTokenizer",
|
unet/config.json
CHANGED
@@ -1,14 +1,9 @@
|
|
1 |
{
|
2 |
"_class_name": "UNet2DConditionModel",
|
3 |
-
"_diffusers_version": "0.
|
4 |
-
"_name_or_path": "/
|
5 |
"act_fn": "silu",
|
6 |
-
"attention_head_dim":
|
7 |
-
5,
|
8 |
-
10,
|
9 |
-
20,
|
10 |
-
20
|
11 |
-
],
|
12 |
"block_out_channels": [
|
13 |
320,
|
14 |
640,
|
@@ -16,7 +11,8 @@
|
|
16 |
1280
|
17 |
],
|
18 |
"center_input_sample": false,
|
19 |
-
"
|
|
|
20 |
"down_block_types": [
|
21 |
"CrossAttnDownBlock2D",
|
22 |
"CrossAttnDownBlock2D",
|
@@ -30,9 +26,13 @@
|
|
30 |
"in_channels": 4,
|
31 |
"layers_per_block": 2,
|
32 |
"mid_block_scale_factor": 1,
|
|
|
33 |
"norm_eps": 1e-05,
|
34 |
"norm_num_groups": 32,
|
|
|
|
|
35 |
"out_channels": 4,
|
|
|
36 |
"sample_size": 64,
|
37 |
"up_block_types": [
|
38 |
"UpBlock2D",
|
@@ -40,5 +40,6 @@
|
|
40 |
"CrossAttnUpBlock2D",
|
41 |
"CrossAttnUpBlock2D"
|
42 |
],
|
43 |
-
"
|
|
|
44 |
}
|
|
|
1 |
{
|
2 |
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.11.1",
|
4 |
+
"_name_or_path": "/root/.cache/huggingface/diffusers/models--runwayml--stable-diffusion-v1-5/snapshots/889b629140e71758e1e0006e355c331a5744b4bf/unet",
|
5 |
"act_fn": "silu",
|
6 |
+
"attention_head_dim": 8,
|
|
|
|
|
|
|
|
|
|
|
7 |
"block_out_channels": [
|
8 |
320,
|
9 |
640,
|
|
|
11 |
1280
|
12 |
],
|
13 |
"center_input_sample": false,
|
14 |
+
"class_embed_type": null,
|
15 |
+
"cross_attention_dim": 768,
|
16 |
"down_block_types": [
|
17 |
"CrossAttnDownBlock2D",
|
18 |
"CrossAttnDownBlock2D",
|
|
|
26 |
"in_channels": 4,
|
27 |
"layers_per_block": 2,
|
28 |
"mid_block_scale_factor": 1,
|
29 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
30 |
"norm_eps": 1e-05,
|
31 |
"norm_num_groups": 32,
|
32 |
+
"num_class_embeds": null,
|
33 |
+
"only_cross_attention": false,
|
34 |
"out_channels": 4,
|
35 |
+
"resnet_time_scale_shift": "default",
|
36 |
"sample_size": 64,
|
37 |
"up_block_types": [
|
38 |
"UpBlock2D",
|
|
|
40 |
"CrossAttnUpBlock2D",
|
41 |
"CrossAttnUpBlock2D"
|
42 |
],
|
43 |
+
"upcast_attention": false,
|
44 |
+
"use_linear_projection": false
|
45 |
}
|
unet/diffusion_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 sha256:7356f75b3ee566957a08e727f2e3623fea89d3dfa49c72806c01114527f2adc2
|
3 |
+
size 3438366373
|
unet/diffusion_pytorch_model.safetensors
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:c60b3631cc85148ca0cc524daff7767efb707fd26c40d46cc3cd217dc5252cd0
|
3 |
-
size 3463726498
|
|
|
|
|
|
|
|
vae/config.json
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
{
|
2 |
"_class_name": "AutoencoderKL",
|
3 |
-
"_diffusers_version": "0.
|
4 |
-
"_name_or_path": "/
|
5 |
"act_fn": "silu",
|
6 |
"block_out_channels": [
|
7 |
128,
|
@@ -20,7 +20,7 @@
|
|
20 |
"layers_per_block": 2,
|
21 |
"norm_num_groups": 32,
|
22 |
"out_channels": 3,
|
23 |
-
"sample_size":
|
24 |
"up_block_types": [
|
25 |
"UpDecoderBlock2D",
|
26 |
"UpDecoderBlock2D",
|
|
|
1 |
{
|
2 |
"_class_name": "AutoencoderKL",
|
3 |
+
"_diffusers_version": "0.11.1",
|
4 |
+
"_name_or_path": "stabilityai/sd-vae-ft-mse",
|
5 |
"act_fn": "silu",
|
6 |
"block_out_channels": [
|
7 |
128,
|
|
|
20 |
"layers_per_block": 2,
|
21 |
"norm_num_groups": 32,
|
22 |
"out_channels": 3,
|
23 |
+
"sample_size": 256,
|
24 |
"up_block_types": [
|
25 |
"UpDecoderBlock2D",
|
26 |
"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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:36bb8e1b54aba3a0914eb35fba13dcb107e9f18d379d1df2158732cd4bf56a94
|
3 |
+
size 334711857
|
vae/diffusion_pytorch_model.safetensors
DELETED
@@ -1,3 +0,0 @@
|
|
1 |
-
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:a1d993488569e928462932c8c38a0760b874d166399b14414135bd9c42df5815
|
3 |
-
size 334643276
|
|
|
|
|
|
|
|