patrickvonplaten
commited on
Commit
•
8d254a4
1
Parent(s):
ecbb9f3
correct more
Browse files- model_index.json +23 -25
- scheduler/scheduler_config.json +1 -1
- text_encoder/config.json +3 -3
- text_encoder/pytorch_model.bin +2 -2
- tokenizer/tokenizer_config.json +1 -1
- unet/config.json +3 -2
- unet/diffusion_pytorch_model.bin +2 -2
- vae/config.json +3 -2
- vae/diffusion_pytorch_model.bin +2 -2
model_index.json
CHANGED
@@ -1,26 +1,24 @@
|
|
1 |
{
|
2 |
-
|
3 |
-
|
4 |
-
|
5 |
-
|
6 |
-
|
7 |
-
|
8 |
-
|
9 |
-
"
|
10 |
-
|
11 |
-
|
12 |
-
|
13 |
-
"
|
14 |
-
|
15 |
-
|
16 |
-
|
17 |
-
"
|
18 |
-
|
19 |
-
|
20 |
-
|
21 |
-
"
|
22 |
-
|
23 |
-
|
24 |
-
|
25 |
-
}
|
26 |
-
|
|
|
1 |
{
|
2 |
+
"_class_name": "StableDiffusionLatentUpscalePipeline",
|
3 |
+
"_diffusers_version": "0.13.0.dev0",
|
4 |
+
"scheduler": [
|
5 |
+
"diffusers",
|
6 |
+
"EulerDiscreteScheduler"
|
7 |
+
],
|
8 |
+
"text_encoder": [
|
9 |
+
"transformers",
|
10 |
+
"CLIPTextModel"
|
11 |
+
],
|
12 |
+
"tokenizer": [
|
13 |
+
"transformers",
|
14 |
+
"CLIPTokenizer"
|
15 |
+
],
|
16 |
+
"unet": [
|
17 |
+
"diffusers",
|
18 |
+
"UNet2DConditionModel"
|
19 |
+
],
|
20 |
+
"vae": [
|
21 |
+
"diffusers",
|
22 |
+
"AutoencoderKL"
|
23 |
+
]
|
24 |
+
}
|
|
|
|
scheduler/scheduler_config.json
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
{
|
2 |
"_class_name": "EulerDiscreteScheduler",
|
3 |
-
"_diffusers_version": "0.
|
4 |
"beta_end": 0.012,
|
5 |
"beta_schedule": "scaled_linear",
|
6 |
"beta_start": 0.00085,
|
|
|
1 |
{
|
2 |
"_class_name": "EulerDiscreteScheduler",
|
3 |
+
"_diffusers_version": "0.13.0.dev0",
|
4 |
"beta_end": 0.012,
|
5 |
"beta_schedule": "scaled_linear",
|
6 |
"beta_start": 0.00085,
|
text_encoder/config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"CLIPTextModel"
|
5 |
],
|
@@ -19,7 +19,7 @@
|
|
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 |
+
"_name_or_path": "/home/patrick_huggingface_co/latent-upscaler/text_encoder",
|
3 |
"architectures": [
|
4 |
"CLIPTextModel"
|
5 |
],
|
|
|
19 |
"num_hidden_layers": 12,
|
20 |
"pad_token_id": 1,
|
21 |
"projection_dim": 768,
|
22 |
+
"torch_dtype": "float16",
|
23 |
+
"transformers_version": "4.27.0.dev0",
|
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:a371c4c8b166f660e8a97f5e618f27fb1b21d56dc2d171df1973e09e988d003c
|
3 |
+
size 246186081
|
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": "/home/patrick_huggingface_co/latent-upscaler/tokenizer",
|
23 |
"pad_token": "<|endoftext|>",
|
24 |
"special_tokens_map_file": "./special_tokens_map.json",
|
25 |
"tokenizer_class": "CLIPTokenizer",
|
unet/config.json
CHANGED
@@ -1,6 +1,7 @@
|
|
1 |
{
|
2 |
"_class_name": "UNet2DConditionModel",
|
3 |
-
"_diffusers_version": "0.
|
|
|
4 |
"act_fn": "gelu",
|
5 |
"attention_head_dim": 64,
|
6 |
"attn1_types": [
|
@@ -23,7 +24,6 @@
|
|
23 |
],
|
24 |
"center_input_sample": false,
|
25 |
"class_embed_type": null,
|
26 |
-
"time_cond_proj_dim": 896,
|
27 |
"conv_in_kernel": 1,
|
28 |
"conv_out_kernel": 1,
|
29 |
"cross_attention_dim": 768,
|
@@ -57,6 +57,7 @@
|
|
57 |
"resnet_time_scale_shift": "scale_shift",
|
58 |
"sample_size": null,
|
59 |
"skip_freq": "block",
|
|
|
60 |
"time_embed_dim": 768,
|
61 |
"time_embedding_type": "fourier",
|
62 |
"timestep_act_2": true,
|
|
|
1 |
{
|
2 |
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.13.0.dev0",
|
4 |
+
"_name_or_path": "/home/patrick_huggingface_co/latent-upscaler/unet",
|
5 |
"act_fn": "gelu",
|
6 |
"attention_head_dim": 64,
|
7 |
"attn1_types": [
|
|
|
24 |
],
|
25 |
"center_input_sample": false,
|
26 |
"class_embed_type": null,
|
|
|
27 |
"conv_in_kernel": 1,
|
28 |
"conv_out_kernel": 1,
|
29 |
"cross_attention_dim": 768,
|
|
|
57 |
"resnet_time_scale_shift": "scale_shift",
|
58 |
"sample_size": null,
|
59 |
"skip_freq": "block",
|
60 |
+
"time_cond_proj_dim": 896,
|
61 |
"time_embed_dim": 768,
|
62 |
"time_embedding_type": "fourier",
|
63 |
"timestep_act_2": true,
|
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 sha256:219d18e054ac2288c2bac88930f6ffd47ad23c54030d58724dd5f0c9907ecb6b
|
3 |
+
size 745380071
|
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,
|
@@ -21,6 +21,7 @@
|
|
21 |
"norm_num_groups": 32,
|
22 |
"out_channels": 3,
|
23 |
"sample_size": 256,
|
|
|
24 |
"up_block_types": [
|
25 |
"UpDecoderBlock2D",
|
26 |
"UpDecoderBlock2D",
|
|
|
1 |
{
|
2 |
"_class_name": "AutoencoderKL",
|
3 |
+
"_diffusers_version": "0.13.0.dev0",
|
4 |
+
"_name_or_path": "/home/patrick_huggingface_co/latent-upscaler/vae",
|
5 |
"act_fn": "silu",
|
6 |
"block_out_channels": [
|
7 |
128,
|
|
|
21 |
"norm_num_groups": 32,
|
22 |
"out_channels": 3,
|
23 |
"sample_size": 256,
|
24 |
+
"scaling_factor": 0.18215,
|
25 |
"up_block_types": [
|
26 |
"UpDecoderBlock2D",
|
27 |
"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 sha256:354e94ceb8cebe720c40510b94599b388a8eda407e7694a4db1ed8dc4f678538
|
3 |
+
size 167404145
|