Upload 33 files
Browse files- SonicDiffusionV2.ckpt +3 -0
- args.json +85 -0
- feature_extractor/preprocessor_config.json +28 -0
- model_index.json +33 -0
- samples/prompt_1/prompt_1_0.png +0 -0
- samples/prompt_1/prompt_1_1.png +0 -0
- samples/prompt_1/prompt_1_2.png +0 -0
- samples/prompt_2/prompt_2_0.png +0 -0
- samples/prompt_2/prompt_2_1.png +0 -0
- samples/prompt_2/prompt_2_2.png +0 -0
- samples/prompt_3/prompt_3_0.png +0 -0
- samples/prompt_3/prompt_3_1.png +0 -0
- samples/prompt_3/prompt_3_2.png +0 -0
- samples/prompt_4/prompt_4_0.png +0 -0
- samples/prompt_4/prompt_4_1.png +0 -0
- samples/prompt_4/prompt_4_2.png +0 -0
- samples/prompt_5/prompt_5_0.png +0 -0
- samples/prompt_5/prompt_5_1.png +0 -0
- samples/prompt_5/prompt_5_2.png +0 -0
- samples/prompt_6/prompt_6_0.png +0 -0
- samples/prompt_6/prompt_6_1.png +0 -0
- samples/prompt_6/prompt_6_2.png +0 -0
- scheduler/scheduler_config.json +20 -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 +42 -0
- unet/diffusion_pytorch_model.bin +3 -0
- vae/config.json +30 -0
- vae/diffusion_pytorch_model.bin +3 -0
SonicDiffusionV2.ckpt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4b08d91ba6e4efb6317a272684ef821d91fa33bda1078d051964b7866ef6f8c1
|
3 |
+
size 2132856686
|
args.json
ADDED
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"disable_cudnn_benchmark": true,
|
3 |
+
"use_text_files_as_captions": false,
|
4 |
+
"stop_text_encoder_training": 1000,
|
5 |
+
"use_bucketing": false,
|
6 |
+
"regenerate_latent_cache": false,
|
7 |
+
"save_latents_cache": true,
|
8 |
+
"sample_on_training_start": false,
|
9 |
+
"add_class_images_to_dataset": false,
|
10 |
+
"auto_balance_concept_datasets": false,
|
11 |
+
"sample_aspect_ratios": false,
|
12 |
+
"dataset_repeats": 1,
|
13 |
+
"save_every_n_epoch": 10,
|
14 |
+
"pretrained_model_name_or_path": "Linaqruf/anything-v3.0",
|
15 |
+
"pretrained_vae_name_or_path": "",
|
16 |
+
"tokenizer_name": null,
|
17 |
+
"instance_data_dir": null,
|
18 |
+
"class_data_dir": null,
|
19 |
+
"instance_prompt": null,
|
20 |
+
"class_prompt": null,
|
21 |
+
"save_sample_prompt": null,
|
22 |
+
"n_save_sample": 3,
|
23 |
+
"sample_height": 512,
|
24 |
+
"sample_width": 512,
|
25 |
+
"save_guidance_scale": 7.5,
|
26 |
+
"save_infer_steps": 30,
|
27 |
+
"with_prior_preservation": false,
|
28 |
+
"prior_loss_weight": 1.0,
|
29 |
+
"num_class_images": 200,
|
30 |
+
"output_dir": "C:/Users/metal/Documents/programming/StableTuner/models/A3B1_203",
|
31 |
+
"seed": 3434554,
|
32 |
+
"resolution": 512,
|
33 |
+
"center_crop": false,
|
34 |
+
"train_text_encoder": true,
|
35 |
+
"train_batch_size": 1,
|
36 |
+
"sample_batch_size": 4,
|
37 |
+
"num_train_epochs": 1000,
|
38 |
+
"max_train_steps": 196000,
|
39 |
+
"gradient_accumulation_steps": 1,
|
40 |
+
"gradient_checkpointing": true,
|
41 |
+
"learning_rate": 5e-07,
|
42 |
+
"scale_lr": false,
|
43 |
+
"lr_scheduler": "constant",
|
44 |
+
"lr_warmup_steps": 0,
|
45 |
+
"use_8bit_adam": false,
|
46 |
+
"adam_beta1": 0.9,
|
47 |
+
"adam_beta2": 0.999,
|
48 |
+
"adam_weight_decay": 0.01,
|
49 |
+
"adam_epsilon": 1e-08,
|
50 |
+
"max_grad_norm": 1.0,
|
51 |
+
"push_to_hub": false,
|
52 |
+
"hub_token": null,
|
53 |
+
"hub_model_id": null,
|
54 |
+
"logging_dir": "logs",
|
55 |
+
"log_interval": 10,
|
56 |
+
"sample_step_interval": 10000,
|
57 |
+
"mixed_precision": "fp16",
|
58 |
+
"not_cache_latents": false,
|
59 |
+
"local_rank": -1,
|
60 |
+
"concepts_list": [
|
61 |
+
{
|
62 |
+
"instance_prompt": "",
|
63 |
+
"class_prompt": "",
|
64 |
+
"instance_data_dir": "C:/Users/metal/Downloads/sonic_training/redketchup",
|
65 |
+
"class_data_dir": "",
|
66 |
+
"do_not_balance": 1
|
67 |
+
}
|
68 |
+
],
|
69 |
+
"save_sample_controlled_seed": null,
|
70 |
+
"delete_checkpoints_when_full_drive": false,
|
71 |
+
"send_telegram_updates": false,
|
72 |
+
"telegram_chat_id": "0",
|
73 |
+
"telegram_token": "0",
|
74 |
+
"use_deepspeed_adam": false,
|
75 |
+
"append_sample_controlled_seed_action": null,
|
76 |
+
"add_sample_prompt": [
|
77 |
+
"mobian school girl,",
|
78 |
+
"mobian mage",
|
79 |
+
"mobian studying",
|
80 |
+
"mobian drinking coffee at a cafe",
|
81 |
+
"mobians at a birthday party",
|
82 |
+
"mobian in swimsuit at the beach, portrait"
|
83 |
+
],
|
84 |
+
"use_image_names_as_captions": true
|
85 |
+
}
|
feature_extractor/preprocessor_config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": [
|
13 |
+
0.48145466,
|
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
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "StableDiffusionPipeline",
|
3 |
+
"_diffusers_version": "0.10.0",
|
4 |
+
"feature_extractor": [
|
5 |
+
"transformers",
|
6 |
+
"CLIPImageProcessor"
|
7 |
+
],
|
8 |
+
"requires_safety_checker": true,
|
9 |
+
"safety_checker": [
|
10 |
+
null,
|
11 |
+
null
|
12 |
+
],
|
13 |
+
"scheduler": [
|
14 |
+
"diffusers",
|
15 |
+
"PNDMScheduler"
|
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/prompt_1/prompt_1_0.png
ADDED
![]() |
samples/prompt_1/prompt_1_1.png
ADDED
![]() |
samples/prompt_1/prompt_1_2.png
ADDED
![]() |
samples/prompt_2/prompt_2_0.png
ADDED
![]() |
samples/prompt_2/prompt_2_1.png
ADDED
![]() |
samples/prompt_2/prompt_2_2.png
ADDED
![]() |
samples/prompt_3/prompt_3_0.png
ADDED
![]() |
samples/prompt_3/prompt_3_1.png
ADDED
![]() |
samples/prompt_3/prompt_3_2.png
ADDED
![]() |
samples/prompt_4/prompt_4_0.png
ADDED
![]() |
samples/prompt_4/prompt_4_1.png
ADDED
![]() |
samples/prompt_4/prompt_4_2.png
ADDED
![]() |
samples/prompt_5/prompt_5_0.png
ADDED
![]() |
samples/prompt_5/prompt_5_1.png
ADDED
![]() |
samples/prompt_5/prompt_5_2.png
ADDED
![]() |
samples/prompt_6/prompt_6_0.png
ADDED
![]() |
samples/prompt_6/prompt_6_1.png
ADDED
![]() |
samples/prompt_6/prompt_6_2.png
ADDED
![]() |
scheduler/scheduler_config.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "DPMSolverMultistepScheduler",
|
3 |
+
"_diffusers_version": "0.10.0",
|
4 |
+
"algorithm_type": "dpmsolver++",
|
5 |
+
"beta_end": 0.012,
|
6 |
+
"beta_schedule": "scaled_linear",
|
7 |
+
"beta_start": 0.00085,
|
8 |
+
"dynamic_thresholding_ratio": 0.995,
|
9 |
+
"lower_order_final": true,
|
10 |
+
"num_train_timesteps": 1000,
|
11 |
+
"prediction_type": "epsilon",
|
12 |
+
"sample_max_value": 1.0,
|
13 |
+
"set_alpha_to_one": false,
|
14 |
+
"skip_prk_steps": true,
|
15 |
+
"solver_order": 2,
|
16 |
+
"solver_type": "midpoint",
|
17 |
+
"steps_offset": 1,
|
18 |
+
"thresholding": false,
|
19 |
+
"trained_betas": null
|
20 |
+
}
|
text_encoder/config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Linaqruf/anything-v3.0",
|
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": "4.25.1",
|
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 sha256:62d7d67a6a947aba5e40f4225f2af42735fadf41f9c0d162120befa4d0defd19
|
3 |
+
size 492308087
|
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": "C:\\Users\\metal/.cache\\huggingface\\diffusers\\models--Linaqruf--anything-v3.0\\snapshots\\cfac9b867297a302d5d53876f9d0ef1a44017c25\\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 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "UNet2DConditionModel",
|
3 |
+
"_diffusers_version": "0.10.0",
|
4 |
+
"_name_or_path": "Linaqruf/anything-v3.0",
|
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 |
+
"dual_cross_attention": false,
|
23 |
+
"flip_sin_to_cos": true,
|
24 |
+
"freq_shift": 0,
|
25 |
+
"in_channels": 4,
|
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": null,
|
31 |
+
"only_cross_attention": false,
|
32 |
+
"out_channels": 4,
|
33 |
+
"sample_size": 64,
|
34 |
+
"up_block_types": [
|
35 |
+
"UpBlock2D",
|
36 |
+
"CrossAttnUpBlock2D",
|
37 |
+
"CrossAttnUpBlock2D",
|
38 |
+
"CrossAttnUpBlock2D"
|
39 |
+
],
|
40 |
+
"upcast_attention": false,
|
41 |
+
"use_linear_projection": false
|
42 |
+
}
|
unet/diffusion_pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f5bc3d5b3d988465a4589ce57d4237b99e68f692c84973907d2513950d63be3f
|
3 |
+
size 3438364325
|
vae/config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_class_name": "AutoencoderKL",
|
3 |
+
"_diffusers_version": "0.10.0",
|
4 |
+
"_name_or_path": "Linaqruf/anything-v3.0",
|
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:a5957cb736a8b033eba68c89e74a6d89a3d67090fadb8fe3bb11349953e6d290
|
3 |
+
size 334707217
|