Guizmus commited on
Commit
d76c608
1 Parent(s): 3a3913e

model v2 upload (#1)

Browse files

- model v2 upload (4de70c022755ea33001700d0e185bd9b0b266130)
- Create feature_extractor/preprocessor_config.json (9a08b627249b647e11e0b47037dcee02b86d549d)
- Create scheduler/scheduler_config.json (7ce97f65f45c4fe16bed74dc86af5b308eae659d)
- Create text_encoder/config.json (c23b5227852694730b76553de355da25d85c7534)
- Upload pytorch_model.bin (59622cf7b9407c664e73ab126a9ee2e63dd14a3d)
- Create tokenizer/tokenizer_config.json (a53c7d15ec7ec8f20e3e5824db55d63ffa3b8a76)
- Upload 3 files (ae3548fc85fe0c96c8f1a4fd36581ba6676404b6)
- Create unet/config.json (08c51b6d497c85be00caea7774923341519ad844)
- Upload diffusion_pytorch_model.bin (e7ac34cdef8ad60d504085a3b8ac942079a245e6)
- Create vae/config.json (cc79409ee3f56700f17fdf50e9c47c6fb9c4c4cc)
- Upload diffusion_pytorch_model.bin (63a6865474a8701453d8fdf2a7239620839d6f4d)

.gitattributes CHANGED
@@ -31,3 +31,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
31
  *.zip filter=lfs diff=lfs merge=lfs -text
32
  *.zst filter=lfs diff=lfs merge=lfs -text
33
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
31
  *.zip filter=lfs diff=lfs merge=lfs -text
32
  *.zst filter=lfs diff=lfs merge=lfs -text
33
  *tfevents* filter=lfs diff=lfs merge=lfs -text
34
+ DeathNote_v2_4k.ckpt filter=lfs diff=lfs merge=lfs -text
DeathNote_v2_4k.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:337a3714e2789fa96915557db014d4f9c4e51ce1f583b27de182be5a304cb50a
3
+ size 2132856622
README.md ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: creativeml-openrail-m
3
+ ---
4
+ # DeathNote Diffusion
5
+ <p>This is the fine-tuned Stable Diffusion model trained on images from the anime Death Note.<br/>
6
+ The following tokens will add their corresponding concept :<br/>
7
+ <ul>
8
+ <li>**DeathNote notebook** : the Deathnote itself</li>
9
+ <li>**Light Yagami** man : Light Yagami, main character</li>
10
+ <li>**Ryuk** demon : Ryuk, Shinigami</li>
11
+ <li>**LLawliet** man : L, "full" name</li>
12
+ <li>**Misa Amane** girl : Second Kira</li>
13
+ <li>**Soichiro Yagami** man : Soichiro, Father of Light, Policeman</li>
14
+ <li>**Sayou Yagami** girl : Sayou, sister of Light</li>
15
+ <li>**Raye Penber** man : Raye, FBI Agent</li>
16
+ <li>**Naomi Misora** girl : Naomi, fiance of Raye</li>
17
+ <li>**DNStyle style** : style of the anime</li>
18
+ </ul>
19
+
20
+ ### 🧨 Diffusers
21
+
22
+ This model can be used just like any other Stable Diffusion model. For more information,
23
+ please have a look at the [Stable Diffusion](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion).
24
+
25
+ You can also export the model to [ONNX](https://huggingface.co/docs/diffusers/optimization/onnx), [MPS](https://huggingface.co/docs/diffusers/optimization/mps) and/or [FLAX/JAX]().
26
+
27
+ ```python
28
+ from diffusers import StableDiffusionPipeline
29
+ import torch
30
+
31
+ model_id = "Guizmus/DeathNote"
32
+ pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
33
+ pipe = pipe.to("cuda")
34
+
35
+ prompt = "Ryuk demon, intricate, headshot, highly detailed"
36
+ image = pipe(prompt).images[0]
37
+
38
+ image.save("./Ryuk_demon.png")
39
+ ```
args.json ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "pretrained_model_name_or_path": "runwayml/stable-diffusion-v1-5",
3
+ "pretrained_vae_name_or_path": "stabilityai/sd-vae-ft-mse",
4
+ "tokenizer_name": null,
5
+ "instance_data_dir": null,
6
+ "class_data_dir": null,
7
+ "instance_prompt": null,
8
+ "class_prompt": null,
9
+ "save_sample_prompt": "Misa Amane girl",
10
+ "save_sample_negative_prompt": null,
11
+ "n_save_sample": 4,
12
+ "save_guidance_scale": 7.5,
13
+ "save_infer_steps": 50,
14
+ "with_prior_preservation": true,
15
+ "prior_loss_weight": 1.0,
16
+ "num_class_images": 50,
17
+ "output_dir": "/content/drive/MyDrive/drive/MyDrive/DBOutput/DeathNote",
18
+ "seed": 1337,
19
+ "resolution": 512,
20
+ "center_crop": false,
21
+ "train_text_encoder": true,
22
+ "train_batch_size": 1,
23
+ "sample_batch_size": 2,
24
+ "num_train_epochs": 10,
25
+ "max_train_steps": 5000,
26
+ "gradient_accumulation_steps": 1,
27
+ "gradient_checkpointing": false,
28
+ "learning_rate": 1e-06,
29
+ "scale_lr": false,
30
+ "lr_scheduler": "constant",
31
+ "lr_warmup_steps": 0,
32
+ "use_8bit_adam": true,
33
+ "adam_beta1": 0.9,
34
+ "adam_beta2": 0.999,
35
+ "adam_weight_decay": 0.01,
36
+ "adam_epsilon": 1e-08,
37
+ "max_grad_norm": 1.0,
38
+ "push_to_hub": false,
39
+ "hub_token": null,
40
+ "hub_model_id": null,
41
+ "logging_dir": "logs",
42
+ "log_interval": 10,
43
+ "save_interval": 1000,
44
+ "save_min_steps": 0,
45
+ "mixed_precision": "fp16",
46
+ "not_cache_latents": false,
47
+ "local_rank": -1,
48
+ "concepts_list": [
49
+ {
50
+ "instance_prompt": "DeathNote notebook",
51
+ "instance_data_dir": "drive/MyDrive/datasets/DeathNote/Notebook",
52
+ "class_prompt": "anime notebook",
53
+ "class_data_dir": "drive/MyDrive/datasets/Regularisation/AnimeNotebook"
54
+ },
55
+ {
56
+ "instance_prompt": "Light Yagami man",
57
+ "instance_data_dir": "drive/MyDrive/datasets/DeathNote/LightYagami",
58
+ "class_prompt": "anime man",
59
+ "class_data_dir": "drive/MyDrive/datasets/Regularisation/AnimeMan"
60
+ },
61
+ {
62
+ "instance_prompt": "Ryuk demon",
63
+ "instance_data_dir": "drive/MyDrive/datasets/DeathNote/Ryuk",
64
+ "class_prompt": "anime demon",
65
+ "class_data_dir": "drive/MyDrive/datasets/Regularisation/AnimeDemon"
66
+ },
67
+ {
68
+ "instance_prompt": "Sayou Yagami girl",
69
+ "instance_data_dir": "drive/MyDrive/datasets/DeathNote/SayouYagami",
70
+ "class_prompt": "anime girl",
71
+ "class_data_dir": "drive/MyDrive/datasets/Regularisation/AnimeGirl"
72
+ },
73
+ {
74
+ "instance_prompt": "LLawliet man",
75
+ "instance_data_dir": "drive/MyDrive/datasets/DeathNote/LLawliet",
76
+ "class_prompt": "anime man",
77
+ "class_data_dir": "drive/MyDrive/datasets/Regularisation/AnimeMan"
78
+ },
79
+ {
80
+ "instance_prompt": "Naomi Misora girl",
81
+ "instance_data_dir": "drive/MyDrive/datasets/DeathNote/NaomiMisora",
82
+ "class_prompt": "anime girl",
83
+ "class_data_dir": "drive/MyDrive/datasets/Regularisation/AnimeGirl"
84
+ },
85
+ {
86
+ "instance_prompt": "Raye Penber man",
87
+ "instance_data_dir": "drive/MyDrive/datasets/DeathNote/RayePenber",
88
+ "class_prompt": "anime man",
89
+ "class_data_dir": "drive/MyDrive/datasets/Regularisation/AnimeMan"
90
+ },
91
+ {
92
+ "instance_prompt": "Soichiro Yagami man",
93
+ "instance_data_dir": "drive/MyDrive/datasets/DeathNote/SoichiroYagami",
94
+ "class_prompt": "anime man",
95
+ "class_data_dir": "drive/MyDrive/datasets/Regularisation/AnimeMan"
96
+ },
97
+ {
98
+ "instance_prompt": "Misa Amane girl",
99
+ "instance_data_dir": "drive/MyDrive/datasets/DeathNote/MisaAmane",
100
+ "class_prompt": "anime girl",
101
+ "class_data_dir": "drive/MyDrive/datasets/Regularisation/AnimeGirl"
102
+ },
103
+ {
104
+ "instance_prompt": "DNStyle style",
105
+ "instance_data_dir": "drive/MyDrive/datasets/DeathNote/DNStyle",
106
+ "class_prompt": "anime style",
107
+ "class_data_dir": "drive/MyDrive/datasets/Regularisation/AnimeStyle"
108
+ }
109
+ ]
110
+ }
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_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": "4.23.1",
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 sha256:96c15170a0cf658b476b0146e5620f2789b41919acc43920102d1afccd27b58b
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": "/root/.cache/huggingface/diffusers/models--runwayml--stable-diffusion-v1-5/snapshots/51b78538d58bd5526f1cf8e7c03c36e2799e0178/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 sha256:3f06b9d9913b121480f23854c897bf6a3fc0e5ce61be1700e39fb7523a0278e3
3
+ size 3438364325
vae/config.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_class_name": "AutoencoderKL",
3
+ "_diffusers_version": "0.7.0.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
+ "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 sha256:1b4889b6b1d4ce7ae320a02dedaeff1780ad77d415ea0d744b476155c6377ddc
3
+ size 334707217