add diffusers model
Browse files- low_res_scheduler/scheduler_config.json +12 -0
- model_index.json +29 -0
- scheduler/scheduler_config.json +14 -0
- text_encoder/config.json +25 -0
- text_encoder/pytorch_model.bin +3 -0
- tokenizer/merges.txt +0 -0
- tokenizer/special_tokens_map.json +24 -0
- tokenizer/tokenizer_config.json +34 -0
- tokenizer/vocab.json +0 -0
- unet/.ipynb_checkpoints/config-checkpoint.json +46 -0
- unet/config.json +46 -0
- unet/diffusion_pytorch_model.bin +3 -0
- vae/config.json +27 -0
- vae/diffusion_pytorch_model.bin +3 -0
low_res_scheduler/scheduler_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "DDPMScheduler",
|
3 |
+
"_diffusers_version": "0.9.0.dev0",
|
4 |
+
"beta_end": 0.02,
|
5 |
+
"beta_schedule": "scaled_linear",
|
6 |
+
"beta_start": 0.0001,
|
7 |
+
"clip_sample": true,
|
8 |
+
"num_train_timesteps": 1000,
|
9 |
+
"prediction_type": "epsilon",
|
10 |
+
"trained_betas": null,
|
11 |
+
"variance_type": "fixed_small"
|
12 |
+
}
|
model_index.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "StableDiffusionUpscalePipeline",
|
3 |
+
"_diffusers_version": "0.9.0.dev0",
|
4 |
+
"low_res_scheduler": [
|
5 |
+
"diffusers",
|
6 |
+
"DDPMScheduler"
|
7 |
+
],
|
8 |
+
"max_noise_level": 350,
|
9 |
+
"scheduler": [
|
10 |
+
"diffusers",
|
11 |
+
"DDIMScheduler"
|
12 |
+
],
|
13 |
+
"text_encoder": [
|
14 |
+
"transformers",
|
15 |
+
"CLIPTextModel"
|
16 |
+
],
|
17 |
+
"tokenizer": [
|
18 |
+
"transformers",
|
19 |
+
"CLIPTokenizer"
|
20 |
+
],
|
21 |
+
"unet": [
|
22 |
+
"diffusers",
|
23 |
+
"UNet2DConditionModel"
|
24 |
+
],
|
25 |
+
"vae": [
|
26 |
+
"diffusers",
|
27 |
+
"AutoencoderKL"
|
28 |
+
]
|
29 |
+
}
|
scheduler/scheduler_config.json
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "DDIMScheduler",
|
3 |
+
"_diffusers_version": "0.9.0.dev0",
|
4 |
+
"beta_end": 0.02,
|
5 |
+
"beta_schedule": "scaled_linear",
|
6 |
+
"beta_start": 0.0001,
|
7 |
+
"clip_sample": false,
|
8 |
+
"num_train_timesteps": 1000,
|
9 |
+
"prediction_type": "v_prediction",
|
10 |
+
"set_alpha_to_one": false,
|
11 |
+
"skip_prk_steps": true,
|
12 |
+
"steps_offset": 1,
|
13 |
+
"trained_betas": null
|
14 |
+
}
|
text_encoder/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "hf-models/stable-diffusion-x4-upscaler/text_encoder",
|
3 |
+
"architectures": [
|
4 |
+
"CLIPTextModel"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 0,
|
8 |
+
"dropout": 0.0,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "gelu",
|
11 |
+
"hidden_size": 1024,
|
12 |
+
"initializer_factor": 1.0,
|
13 |
+
"initializer_range": 0.02,
|
14 |
+
"intermediate_size": 4096,
|
15 |
+
"layer_norm_eps": 1e-05,
|
16 |
+
"max_position_embeddings": 77,
|
17 |
+
"model_type": "clip_text_model",
|
18 |
+
"num_attention_heads": 16,
|
19 |
+
"num_hidden_layers": 23,
|
20 |
+
"pad_token_id": 1,
|
21 |
+
"projection_dim": 512,
|
22 |
+
"torch_dtype": "float32",
|
23 |
+
"transformers_version": "4.25.0.dev0",
|
24 |
+
"vocab_size": 49408
|
25 |
+
}
|
text_encoder/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2188379b05015f531d61503e714234d00a64939792f3098b324e516547f0194f
|
3 |
+
size 1361674657
|
tokenizer/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer/special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "!",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<|endoftext|>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": true,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer/tokenizer_config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "hf-models/stable-diffusion-x4-upscaler/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 |
+
}
|
tokenizer/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
unet/.ipynb_checkpoints/config-checkpoint.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.8.0",
|
4 |
+
"_name_or_path": "hf-models/stable-diffusion-x4-upscaler/unet",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"attention_head_dim": 8,
|
7 |
+
"block_out_channels": [
|
8 |
+
256,
|
9 |
+
512,
|
10 |
+
512,
|
11 |
+
1024
|
12 |
+
],
|
13 |
+
"center_input_sample": false,
|
14 |
+
"cross_attention_dim": 1024,
|
15 |
+
"down_block_types": [
|
16 |
+
"DownBlock2D",
|
17 |
+
"CrossAttnDownBlock2D",
|
18 |
+
"CrossAttnDownBlock2D",
|
19 |
+
"CrossAttnDownBlock2D"
|
20 |
+
],
|
21 |
+
"downsample_padding": 1,
|
22 |
+
"dual_cross_attention": false,
|
23 |
+
"flip_sin_to_cos": true,
|
24 |
+
"freq_shift": 0,
|
25 |
+
"in_channels": 7,
|
26 |
+
"layers_per_block": 2,
|
27 |
+
"mid_block_scale_factor": 1,
|
28 |
+
"norm_eps": 1e-05,
|
29 |
+
"norm_num_groups": 32,
|
30 |
+
"num_class_embeds": 1000,
|
31 |
+
"only_cross_attention": [
|
32 |
+
true,
|
33 |
+
true,
|
34 |
+
true,
|
35 |
+
false
|
36 |
+
],
|
37 |
+
"out_channels": 4,
|
38 |
+
"sample_size": 128,
|
39 |
+
"up_block_types": [
|
40 |
+
"CrossAttnUpBlock2D",
|
41 |
+
"CrossAttnUpBlock2D",
|
42 |
+
"CrossAttnUpBlock2D",
|
43 |
+
"UpBlock2D"
|
44 |
+
],
|
45 |
+
"use_linear_projection": true
|
46 |
+
}
|
unet/config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.9.0.dev0",
|
4 |
+
"_name_or_path": "hf-models/stable-diffusion-x4-upscaler/unet",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"attention_head_dim": 8,
|
7 |
+
"block_out_channels": [
|
8 |
+
256,
|
9 |
+
512,
|
10 |
+
512,
|
11 |
+
1024
|
12 |
+
],
|
13 |
+
"center_input_sample": false,
|
14 |
+
"cross_attention_dim": 1024,
|
15 |
+
"down_block_types": [
|
16 |
+
"DownBlock2D",
|
17 |
+
"CrossAttnDownBlock2D",
|
18 |
+
"CrossAttnDownBlock2D",
|
19 |
+
"CrossAttnDownBlock2D"
|
20 |
+
],
|
21 |
+
"downsample_padding": 1,
|
22 |
+
"dual_cross_attention": false,
|
23 |
+
"flip_sin_to_cos": true,
|
24 |
+
"freq_shift": 0,
|
25 |
+
"in_channels": 7,
|
26 |
+
"layers_per_block": 2,
|
27 |
+
"mid_block_scale_factor": 1,
|
28 |
+
"norm_eps": 1e-05,
|
29 |
+
"norm_num_groups": 32,
|
30 |
+
"num_class_embeds": 1000,
|
31 |
+
"only_cross_attention": [
|
32 |
+
true,
|
33 |
+
true,
|
34 |
+
true,
|
35 |
+
false
|
36 |
+
],
|
37 |
+
"out_channels": 4,
|
38 |
+
"sample_size": 128,
|
39 |
+
"up_block_types": [
|
40 |
+
"CrossAttnUpBlock2D",
|
41 |
+
"CrossAttnUpBlock2D",
|
42 |
+
"CrossAttnUpBlock2D",
|
43 |
+
"UpBlock2D"
|
44 |
+
],
|
45 |
+
"use_linear_projection": true
|
46 |
+
}
|
unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7bee7a4acd3ccb2ee9c470d7e9105dffd48d449da4d3d4a5056f7d9e51f4fc5e
|
3 |
+
size 1893874611
|
vae/config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "AutoencoderKL",
|
3 |
+
"_diffusers_version": "0.9.0.dev0",
|
4 |
+
"_name_or_path": "hf-models/stable-diffusion-x4-upscaler/vae",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"block_out_channels": [
|
7 |
+
128,
|
8 |
+
256,
|
9 |
+
512
|
10 |
+
],
|
11 |
+
"down_block_types": [
|
12 |
+
"DownEncoderBlock2D",
|
13 |
+
"DownEncoderBlock2D",
|
14 |
+
"DownEncoderBlock2D"
|
15 |
+
],
|
16 |
+
"in_channels": 3,
|
17 |
+
"latent_channels": 4,
|
18 |
+
"layers_per_block": 2,
|
19 |
+
"norm_num_groups": 32,
|
20 |
+
"out_channels": 3,
|
21 |
+
"sample_size": 256,
|
22 |
+
"up_block_types": [
|
23 |
+
"UpDecoderBlock2D",
|
24 |
+
"UpDecoderBlock2D",
|
25 |
+
"UpDecoderBlock2D"
|
26 |
+
]
|
27 |
+
}
|
vae/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9701b233be392017374527288e155239afa0450365fea2a6a779faa33afc8c37
|
3 |
+
size 221382665
|