Commit
•
17f4960
1
Parent(s):
cf950f6
Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- args.json +78 -0
- model.ckpt +3 -0
- model_index.json +33 -0
- samples/0.png +0 -0
- samples/1.png +3 -0
- samples/2.png +0 -0
- samples/3.png +0 -0
- scheduler/scheduler_config.json +18 -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 +33 -0
- tokenizer/vocab.json +0 -0
- unet/config.json +57 -0
- unet/diffusion_pytorch_model.bin +3 -0
- vae/config.json +31 -0
- vae/diffusion_pytorch_model.bin +3 -0
.gitattributes
CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
36 |
+
samples/1.png filter=lfs diff=lfs merge=lfs -text
|
args.json
ADDED
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"pretrained_model_name_or_path": "stabilityai/stable-diffusion-2",
|
3 |
+
"pretrained_vae_name_or_path": "stabilityai/sd-vae-ft-mse",
|
4 |
+
"revision": "fp16",
|
5 |
+
"tokenizer_name": null,
|
6 |
+
"instance_data_dir": null,
|
7 |
+
"class_data_dir": null,
|
8 |
+
"instance_prompt": null,
|
9 |
+
"class_prompt": null,
|
10 |
+
"save_sample_prompt": "This style showcases the shoulders and collarbones, creating a feminine and alluring look",
|
11 |
+
"save_sample_negative_prompt": null,
|
12 |
+
"n_save_sample": 4,
|
13 |
+
"save_guidance_scale": 7.5,
|
14 |
+
"save_infer_steps": 20,
|
15 |
+
"pad_tokens": false,
|
16 |
+
"with_prior_preservation": true,
|
17 |
+
"prior_loss_weight": 1.0,
|
18 |
+
"num_class_images": 10,
|
19 |
+
"output_dir": "/content/stable_diffusion_weights/avatarbrb",
|
20 |
+
"seed": 1337,
|
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": 8,
|
27 |
+
"max_train_steps": 6000,
|
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": true,
|
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": 5000,
|
46 |
+
"save_min_steps": 0,
|
47 |
+
"mixed_precision": "fp16",
|
48 |
+
"not_cache_latents": false,
|
49 |
+
"hflip": false,
|
50 |
+
"local_rank": -1,
|
51 |
+
"concepts_list": [
|
52 |
+
{
|
53 |
+
"instance_prompt": "photo of avt Little Black Dress",
|
54 |
+
"class_prompt": "Little Black Dress ",
|
55 |
+
"instance_data_dir": "/content/dataset/Little Black Dress (LBD)",
|
56 |
+
"class_data_dir": "/content/dataset/LBD"
|
57 |
+
},
|
58 |
+
{
|
59 |
+
"instance_prompt": "photo of zwx Maxi Dress",
|
60 |
+
"class_prompt": "Maxi Dress",
|
61 |
+
"instance_data_dir": "/content/dataset/Maxi Dress",
|
62 |
+
"class_data_dir": "/content/dataset/zwx"
|
63 |
+
},
|
64 |
+
{
|
65 |
+
"instance_prompt": "photo of ukj Wrap Dress",
|
66 |
+
"class_prompt": "Wrap Dress",
|
67 |
+
"instance_data_dir": "/content/dataset/Wrap Dress",
|
68 |
+
"class_data_dir": "/content/dataset/ukj"
|
69 |
+
},
|
70 |
+
{
|
71 |
+
"instance_prompt": "photo of ukg Off-the-Shoulder Dress",
|
72 |
+
"class_prompt": "Off-the-Shoulder Dress",
|
73 |
+
"instance_data_dir": "/content/dataset/Off-the-Shoulder Dress",
|
74 |
+
"class_data_dir": "/content/dataset/ukg"
|
75 |
+
}
|
76 |
+
],
|
77 |
+
"read_prompts_from_txts": false
|
78 |
+
}
|
model.ckpt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:44587fda7d71e195b64d0aa9a1a8fe5475f6e33599a362149b118d5cf4479b8f
|
3 |
+
size 2580250395
|
model_index.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "StableDiffusionPipeline",
|
3 |
+
"_diffusers_version": "0.15.0.dev0",
|
4 |
+
"feature_extractor": [
|
5 |
+
null,
|
6 |
+
null
|
7 |
+
],
|
8 |
+
"requires_safety_checker": false,
|
9 |
+
"safety_checker": [
|
10 |
+
null,
|
11 |
+
null
|
12 |
+
],
|
13 |
+
"scheduler": [
|
14 |
+
"diffusers",
|
15 |
+
"DDIMScheduler"
|
16 |
+
],
|
17 |
+
"text_encoder": [
|
18 |
+
"transformers",
|
19 |
+
"CLIPTextModel"
|
20 |
+
],
|
21 |
+
"tokenizer": [
|
22 |
+
"transformers",
|
23 |
+
"CLIPTokenizer"
|
24 |
+
],
|
25 |
+
"unet": [
|
26 |
+
"diffusers",
|
27 |
+
"UNet2DConditionModel"
|
28 |
+
],
|
29 |
+
"vae": [
|
30 |
+
"diffusers",
|
31 |
+
"AutoencoderKL"
|
32 |
+
]
|
33 |
+
}
|
samples/0.png
ADDED
![]() |
samples/1.png
ADDED
![]() |
Git LFS Details
|
samples/2.png
ADDED
![]() |
samples/3.png
ADDED
![]() |
scheduler/scheduler_config.json
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "DDIMScheduler",
|
3 |
+
"_diffusers_version": "0.15.0.dev0",
|
4 |
+
"beta_end": 0.012,
|
5 |
+
"beta_schedule": "scaled_linear",
|
6 |
+
"beta_start": 0.00085,
|
7 |
+
"clip_sample": false,
|
8 |
+
"clip_sample_range": 1.0,
|
9 |
+
"dynamic_thresholding_ratio": 0.995,
|
10 |
+
"num_train_timesteps": 1000,
|
11 |
+
"prediction_type": "v_prediction",
|
12 |
+
"sample_max_value": 1.0,
|
13 |
+
"set_alpha_to_one": false,
|
14 |
+
"skip_prk_steps": true,
|
15 |
+
"steps_offset": 1,
|
16 |
+
"thresholding": false,
|
17 |
+
"trained_betas": null
|
18 |
+
}
|
text_encoder/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "stabilityai/stable-diffusion-2",
|
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": "4.33.2",
|
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 sha256:66ffd5defb345ca8c2f7bbc433f1c4cde1c977b0f06117eb29031c81b58cd2b6
|
3 |
+
size 1361678941
|
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 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"clean_up_tokenization_spaces": true,
|
12 |
+
"do_lower_case": true,
|
13 |
+
"eos_token": {
|
14 |
+
"__type": "AddedToken",
|
15 |
+
"content": "<|endoftext|>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"errors": "replace",
|
22 |
+
"model_max_length": 77,
|
23 |
+
"pad_token": "<|endoftext|>",
|
24 |
+
"tokenizer_class": "CLIPTokenizer",
|
25 |
+
"unk_token": {
|
26 |
+
"__type": "AddedToken",
|
27 |
+
"content": "<|endoftext|>",
|
28 |
+
"lstrip": false,
|
29 |
+
"normalized": true,
|
30 |
+
"rstrip": false,
|
31 |
+
"single_word": false
|
32 |
+
}
|
33 |
+
}
|
tokenizer/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
unet/config.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.15.0.dev0",
|
4 |
+
"_name_or_path": "stabilityai/stable-diffusion-2",
|
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,
|
15 |
+
1280,
|
16 |
+
1280
|
17 |
+
],
|
18 |
+
"center_input_sample": false,
|
19 |
+
"class_embed_type": null,
|
20 |
+
"class_embeddings_concat": false,
|
21 |
+
"conv_in_kernel": 3,
|
22 |
+
"conv_out_kernel": 3,
|
23 |
+
"cross_attention_dim": 1024,
|
24 |
+
"down_block_types": [
|
25 |
+
"CrossAttnDownBlock2D",
|
26 |
+
"CrossAttnDownBlock2D",
|
27 |
+
"CrossAttnDownBlock2D",
|
28 |
+
"DownBlock2D"
|
29 |
+
],
|
30 |
+
"downsample_padding": 1,
|
31 |
+
"dual_cross_attention": false,
|
32 |
+
"flip_sin_to_cos": true,
|
33 |
+
"freq_shift": 0,
|
34 |
+
"in_channels": 4,
|
35 |
+
"layers_per_block": 2,
|
36 |
+
"mid_block_scale_factor": 1,
|
37 |
+
"mid_block_type": "UNetMidBlock2DCrossAttn",
|
38 |
+
"norm_eps": 1e-05,
|
39 |
+
"norm_num_groups": 32,
|
40 |
+
"num_class_embeds": null,
|
41 |
+
"only_cross_attention": false,
|
42 |
+
"out_channels": 4,
|
43 |
+
"projection_class_embeddings_input_dim": null,
|
44 |
+
"resnet_time_scale_shift": "default",
|
45 |
+
"sample_size": 96,
|
46 |
+
"time_cond_proj_dim": null,
|
47 |
+
"time_embedding_type": "positional",
|
48 |
+
"timestep_post_act": null,
|
49 |
+
"up_block_types": [
|
50 |
+
"UpBlock2D",
|
51 |
+
"CrossAttnUpBlock2D",
|
52 |
+
"CrossAttnUpBlock2D",
|
53 |
+
"CrossAttnUpBlock2D"
|
54 |
+
],
|
55 |
+
"upcast_attention": false,
|
56 |
+
"use_linear_projection": true
|
57 |
+
}
|
unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:546ce7b800c2788b596acab09035d90eb4640490646ffc3980205e9618b872a5
|
3 |
+
size 3463934693
|
vae/config.json
ADDED
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "AutoencoderKL",
|
3 |
+
"_diffusers_version": "0.15.0.dev0",
|
4 |
+
"_name_or_path": "stabilityai/sd-vae-ft-mse",
|
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 |
+
"scaling_factor": 0.18215,
|
25 |
+
"up_block_types": [
|
26 |
+
"UpDecoderBlock2D",
|
27 |
+
"UpDecoderBlock2D",
|
28 |
+
"UpDecoderBlock2D",
|
29 |
+
"UpDecoderBlock2D"
|
30 |
+
]
|
31 |
+
}
|
vae/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:36bb8e1b54aba3a0914eb35fba13dcb107e9f18d379d1df2158732cd4bf56a94
|
3 |
+
size 334711857
|