Upload with huggingface_hub
#1
by
s3nh
- opened
- .ipynb_checkpoints/model_index-checkpoint.json +28 -0
- args.json +58 -0
- feature_extractor/preprocessor_config.json +20 -0
- model.ckpt +3 -0
- model_index.json +28 -0
- scheduler/scheduler_config.json +12 -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/config.json +37 -0
- unet/diffusion_pytorch_model.bin +3 -0
- vae/config.json +30 -0
- vae/diffusion_pytorch_model.bin +3 -0
.ipynb_checkpoints/model_index-checkpoint.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "StableDiffusionPipeline",
|
3 |
+
"_diffusers_version": "0.7.0.dev0",
|
4 |
+
"feature_extractor": [
|
5 |
+
"transformers",
|
6 |
+
"CLIPFeatureExtractor"
|
7 |
+
],
|
8 |
+
"scheduler": [
|
9 |
+
"diffusers",
|
10 |
+
"DDIMScheduler"
|
11 |
+
],
|
12 |
+
"text_encoder": [
|
13 |
+
"transformers",
|
14 |
+
"CLIPTextModel"
|
15 |
+
],
|
16 |
+
"tokenizer": [
|
17 |
+
"transformers",
|
18 |
+
"CLIPTokenizer"
|
19 |
+
],
|
20 |
+
"unet": [
|
21 |
+
"diffusers",
|
22 |
+
"UNet2DConditionModel"
|
23 |
+
],
|
24 |
+
"vae": [
|
25 |
+
"diffusers",
|
26 |
+
"AutoencoderKL"
|
27 |
+
]
|
28 |
+
}
|
args.json
ADDED
@@ -0,0 +1,58 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"pretrained_model_name_or_path": "runwayml/stable-diffusion-v1-5",
|
3 |
+
"pretrained_vae_name_or_path": null,
|
4 |
+
"revision": "fp16",
|
5 |
+
"tokenizer_name": null,
|
6 |
+
"instance_data_dir": "/notebooks/instance_dir/beks/beks",
|
7 |
+
"class_data_dir": "/notebooks/class_prompt/reg/illustration",
|
8 |
+
"instance_prompt": "Portrait of a person, beksinski style",
|
9 |
+
"class_prompt": "Portrait of a person",
|
10 |
+
"save_sample_prompt": null,
|
11 |
+
"save_sample_negative_prompt": null,
|
12 |
+
"n_save_sample": 4,
|
13 |
+
"save_guidance_scale": 7.5,
|
14 |
+
"save_infer_steps": 50,
|
15 |
+
"pad_tokens": false,
|
16 |
+
"with_prior_preservation": true,
|
17 |
+
"prior_loss_weight": 1.0,
|
18 |
+
"num_class_images": 200,
|
19 |
+
"output_dir": "/notebooks/output_dir",
|
20 |
+
"seed": null,
|
21 |
+
"resolution": 512,
|
22 |
+
"center_crop": false,
|
23 |
+
"train_text_encoder": true,
|
24 |
+
"train_batch_size": 1,
|
25 |
+
"sample_batch_size": 4,
|
26 |
+
"num_train_epochs": 1,
|
27 |
+
"max_train_steps": 200,
|
28 |
+
"gradient_accumulation_steps": 1,
|
29 |
+
"gradient_checkpointing": true,
|
30 |
+
"learning_rate": 2e-06,
|
31 |
+
"scale_lr": false,
|
32 |
+
"lr_scheduler": "constant",
|
33 |
+
"lr_warmup_steps": 0,
|
34 |
+
"use_8bit_adam": false,
|
35 |
+
"adam_beta1": 0.9,
|
36 |
+
"adam_beta2": 0.999,
|
37 |
+
"adam_weight_decay": 0.01,
|
38 |
+
"adam_epsilon": 1e-08,
|
39 |
+
"max_grad_norm": 1.0,
|
40 |
+
"push_to_hub": false,
|
41 |
+
"hub_token": null,
|
42 |
+
"hub_model_id": null,
|
43 |
+
"logging_dir": "logs",
|
44 |
+
"log_interval": 10,
|
45 |
+
"save_interval": 10000,
|
46 |
+
"save_min_steps": 0,
|
47 |
+
"mixed_precision": "no",
|
48 |
+
"not_cache_latents": false,
|
49 |
+
"local_rank": -1,
|
50 |
+
"concepts_list": [
|
51 |
+
{
|
52 |
+
"instance_prompt": "Portrait of a person, beksinski style",
|
53 |
+
"class_prompt": "Portrait of a person",
|
54 |
+
"instance_data_dir": "/notebooks/instance_dir/beks/beks",
|
55 |
+
"class_data_dir": "/notebooks/class_prompt/reg/illustration"
|
56 |
+
}
|
57 |
+
]
|
58 |
+
}
|
feature_extractor/preprocessor_config.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": [
|
9 |
+
0.48145466,
|
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 |
+
}
|
model.ckpt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5ca4962613b0ad32f665dc43d8ba175ca06f0be7d51448bc4aefb92d29201644
|
3 |
+
size 2132791380
|
model_index.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "StableDiffusionPipeline",
|
3 |
+
"_diffusers_version": "0.7.0.dev0",
|
4 |
+
"feature_extractor": [
|
5 |
+
"transformers",
|
6 |
+
"CLIPFeatureExtractor"
|
7 |
+
],
|
8 |
+
"scheduler": [
|
9 |
+
"diffusers",
|
10 |
+
"DDIMScheduler"
|
11 |
+
],
|
12 |
+
"text_encoder": [
|
13 |
+
"transformers",
|
14 |
+
"CLIPTextModel"
|
15 |
+
],
|
16 |
+
"tokenizer": [
|
17 |
+
"transformers",
|
18 |
+
"CLIPTokenizer"
|
19 |
+
],
|
20 |
+
"unet": [
|
21 |
+
"diffusers",
|
22 |
+
"UNet2DConditionModel"
|
23 |
+
],
|
24 |
+
"vae": [
|
25 |
+
"diffusers",
|
26 |
+
"AutoencoderKL"
|
27 |
+
]
|
28 |
+
}
|
scheduler/scheduler_config.json
ADDED
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "DDIMScheduler",
|
3 |
+
"_diffusers_version": "0.7.0.dev0",
|
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 |
+
"steps_offset": 1,
|
11 |
+
"trained_betas": null
|
12 |
+
}
|
text_encoder/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "runwayml/stable-diffusion-v1-5",
|
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": "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": "4.24.0",
|
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:bc272635d0c02e0b7541f691ccfdfe16df0454e1b3ca694ce60c975a048ab078
|
3 |
+
size 492309793
|
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": "<|endoftext|>",
|
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": "/root/.cache/huggingface/diffusers/models--runwayml--stable-diffusion-v1-5/snapshots/3beed0bcb34a3d281ce27bd8a6a1efbb68eada38/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/config.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.7.0.dev0",
|
4 |
+
"_name_or_path": "runwayml/stable-diffusion-v1-5",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"attention_head_dim": 8,
|
7 |
+
"block_out_channels": [
|
8 |
+
320,
|
9 |
+
640,
|
10 |
+
1280,
|
11 |
+
1280
|
12 |
+
],
|
13 |
+
"center_input_sample": false,
|
14 |
+
"cross_attention_dim": 768,
|
15 |
+
"down_block_types": [
|
16 |
+
"CrossAttnDownBlock2D",
|
17 |
+
"CrossAttnDownBlock2D",
|
18 |
+
"CrossAttnDownBlock2D",
|
19 |
+
"DownBlock2D"
|
20 |
+
],
|
21 |
+
"downsample_padding": 1,
|
22 |
+
"flip_sin_to_cos": true,
|
23 |
+
"freq_shift": 0,
|
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 |
+
"out_channels": 4,
|
30 |
+
"sample_size": 32,
|
31 |
+
"up_block_types": [
|
32 |
+
"UpBlock2D",
|
33 |
+
"CrossAttnUpBlock2D",
|
34 |
+
"CrossAttnUpBlock2D",
|
35 |
+
"CrossAttnUpBlock2D"
|
36 |
+
]
|
37 |
+
}
|
unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3e7b2b0ad1b9b7a987609549a5363ae45a069e795f5ff9a3ca45cac2e0dcc00d
|
3 |
+
size 3438375973
|
vae/config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "AutoencoderKL",
|
3 |
+
"_diffusers_version": "0.7.0.dev0",
|
4 |
+
"_name_or_path": "runwayml/stable-diffusion-v1-5",
|
5 |
+
"act_fn": "silu",
|
6 |
+
"block_out_channels": [
|
7 |
+
128,
|
8 |
+
256,
|
9 |
+
512,
|
10 |
+
512
|
11 |
+
],
|
12 |
+
"down_block_types": [
|
13 |
+
"DownEncoderBlock2D",
|
14 |
+
"DownEncoderBlock2D",
|
15 |
+
"DownEncoderBlock2D",
|
16 |
+
"DownEncoderBlock2D"
|
17 |
+
],
|
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": 256,
|
24 |
+
"up_block_types": [
|
25 |
+
"UpDecoderBlock2D",
|
26 |
+
"UpDecoderBlock2D",
|
27 |
+
"UpDecoderBlock2D",
|
28 |
+
"UpDecoderBlock2D"
|
29 |
+
]
|
30 |
+
}
|
vae/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6723bacd3c60b11a2b4e6007338a54c6964c210116c3ccecb3bfc80e218afc8f
|
3 |
+
size 334711857
|