model v2 upload (#1)

- 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

@@ -31,3 +31,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+DeathNote_v2_4k.ckpt filter=lfs diff=lfs merge=lfs -text

DeathNote_v2_4k.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:337a3714e2789fa96915557db014d4f9c4e51ce1f583b27de182be5a304cb50a
+size 2132856622

README.md

@@ -0,0 +1,39 @@
+---
+license: creativeml-openrail-m
+---
+# DeathNote Diffusion
+<p>This is the fine-tuned Stable Diffusion model trained on images from the anime Death Note.<br/>
+The following tokens will add their corresponding concept :<br/>
+<ul>
+	<li>**DeathNote notebook** : the Deathnote itself</li>
+	<li>**Light Yagami** man : Light Yagami, main character</li>
+	<li>**Ryuk** demon : Ryuk, Shinigami</li>
+	<li>**LLawliet** man : L, "full" name</li>
+	<li>**Misa Amane** girl : Second Kira</li>
+	<li>**Soichiro Yagami** man : Soichiro, Father of Light, Policeman</li>
+	<li>**Sayou Yagami** girl : Sayou, sister of Light</li>
+	<li>**Raye Penber** man : Raye, FBI Agent</li>
+	<li>**Naomi Misora** girl : Naomi, fiance of Raye</li>
+	<li>**DNStyle style** : style of the anime</li>
+</ul>
+
+### 🧨 Diffusers
+
+This model can be used just like any other Stable Diffusion model. For more information,
+please have a look at the [Stable Diffusion](https://huggingface.co/docs/diffusers/api/pipelines/stable_diffusion).
+
+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]().
+
+```python
+from diffusers import StableDiffusionPipeline
+import torch
+
+model_id = "Guizmus/DeathNote"
+pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16)
+pipe = pipe.to("cuda")
+
+prompt = "Ryuk demon, intricate, headshot, highly detailed"
+image = pipe(prompt).images[0]
+
+image.save("./Ryuk_demon.png")
+```

args.json

@@ -0,0 +1,110 @@
+{
+  "pretrained_model_name_or_path": "runwayml/stable-diffusion-v1-5",
+  "pretrained_vae_name_or_path": "stabilityai/sd-vae-ft-mse",
+  "tokenizer_name": null,
+  "instance_data_dir": null,
+  "class_data_dir": null,
+  "instance_prompt": null,
+  "class_prompt": null,
+  "save_sample_prompt": "Misa Amane girl",
+  "save_sample_negative_prompt": null,
+  "n_save_sample": 4,
+  "save_guidance_scale": 7.5,
+  "save_infer_steps": 50,
+  "with_prior_preservation": true,
+  "prior_loss_weight": 1.0,
+  "num_class_images": 50,
+  "output_dir": "/content/drive/MyDrive/drive/MyDrive/DBOutput/DeathNote",
+  "seed": 1337,
+  "resolution": 512,
+  "center_crop": false,
+  "train_text_encoder": true,
+  "train_batch_size": 1,
+  "sample_batch_size": 2,
+  "num_train_epochs": 10,
+  "max_train_steps": 5000,
+  "gradient_accumulation_steps": 1,
+  "gradient_checkpointing": false,
+  "learning_rate": 1e-06,
+  "scale_lr": false,
+  "lr_scheduler": "constant",
+  "lr_warmup_steps": 0,
+  "use_8bit_adam": true,
+  "adam_beta1": 0.9,
+  "adam_beta2": 0.999,
+  "adam_weight_decay": 0.01,
+  "adam_epsilon": 1e-08,
+  "max_grad_norm": 1.0,
+  "push_to_hub": false,
+  "hub_token": null,
+  "hub_model_id": null,
+  "logging_dir": "logs",
+  "log_interval": 10,
+  "save_interval": 1000,
+  "save_min_steps": 0,
+  "mixed_precision": "fp16",
+  "not_cache_latents": false,
+  "local_rank": -1,
+  "concepts_list": [
+    {
+      "instance_prompt": "DeathNote notebook",
+      "instance_data_dir": "drive/MyDrive/datasets/DeathNote/Notebook",
+      "class_prompt": "anime notebook",
+      "class_data_dir": "drive/MyDrive/datasets/Regularisation/AnimeNotebook"
+    },
+    {
+      "instance_prompt": "Light Yagami man",
+      "instance_data_dir": "drive/MyDrive/datasets/DeathNote/LightYagami",
+      "class_prompt": "anime man",
+      "class_data_dir": "drive/MyDrive/datasets/Regularisation/AnimeMan"
+    },
+    {
+      "instance_prompt": "Ryuk demon",
+      "instance_data_dir": "drive/MyDrive/datasets/DeathNote/Ryuk",
+      "class_prompt": "anime demon",
+      "class_data_dir": "drive/MyDrive/datasets/Regularisation/AnimeDemon"
+    },
+    {
+      "instance_prompt": "Sayou Yagami girl",
+      "instance_data_dir": "drive/MyDrive/datasets/DeathNote/SayouYagami",
+      "class_prompt": "anime girl",
+      "class_data_dir": "drive/MyDrive/datasets/Regularisation/AnimeGirl"
+    },
+    {
+      "instance_prompt": "LLawliet man",
+      "instance_data_dir": "drive/MyDrive/datasets/DeathNote/LLawliet",
+      "class_prompt": "anime man",
+      "class_data_dir": "drive/MyDrive/datasets/Regularisation/AnimeMan"
+    },
+    {
+      "instance_prompt": "Naomi Misora girl",
+      "instance_data_dir": "drive/MyDrive/datasets/DeathNote/NaomiMisora",
+      "class_prompt": "anime girl",
+      "class_data_dir": "drive/MyDrive/datasets/Regularisation/AnimeGirl"
+    },
+    {
+      "instance_prompt": "Raye Penber man",
+      "instance_data_dir": "drive/MyDrive/datasets/DeathNote/RayePenber",
+      "class_prompt": "anime man",
+      "class_data_dir": "drive/MyDrive/datasets/Regularisation/AnimeMan"
+    },
+    {
+      "instance_prompt": "Soichiro Yagami man",
+      "instance_data_dir": "drive/MyDrive/datasets/DeathNote/SoichiroYagami",
+      "class_prompt": "anime man",
+      "class_data_dir": "drive/MyDrive/datasets/Regularisation/AnimeMan"
+    },
+    {
+      "instance_prompt": "Misa Amane girl",
+      "instance_data_dir": "drive/MyDrive/datasets/DeathNote/MisaAmane",
+      "class_prompt": "anime girl",
+      "class_data_dir": "drive/MyDrive/datasets/Regularisation/AnimeGirl"
+    },
+    {
+      "instance_prompt": "DNStyle style",
+      "instance_data_dir": "drive/MyDrive/datasets/DeathNote/DNStyle",
+      "class_prompt": "anime style",
+      "class_data_dir": "drive/MyDrive/datasets/Regularisation/AnimeStyle"
+    }
+  ]
+}

feature_extractor/preprocessor_config.json

@@ -0,0 +1,20 @@
+{
+  "crop_size": 224,
+  "do_center_crop": true,
+  "do_convert_rgb": true,
+  "do_normalize": true,
+  "do_resize": true,
+  "feature_extractor_type": "CLIPFeatureExtractor",
+  "image_mean": [
+    0.48145466,
+    0.4578275,
+    0.40821073
+  ],
+  "image_std": [
+    0.26862954,
+    0.26130258,
+    0.27577711
+  ],
+  "resample": 3,
+  "size": 224
+}

model_index.json

@@ -0,0 +1,28 @@
+{
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.7.0.dev0",
+  "feature_extractor": [
+    "transformers",
+    "CLIPFeatureExtractor"
+  ],
+  "scheduler": [
+    "diffusers",
+    "DDIMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,12 @@
+{
+  "_class_name": "DDIMScheduler",
+  "_diffusers_version": "0.7.0.dev0",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "num_train_timesteps": 1000,
+  "set_alpha_to_one": false,
+  "steps_offset": 1,
+  "trained_betas": null
+}

text_encoder/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "runwayml/stable-diffusion-v1-5",
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "quick_gelu",
+  "hidden_size": 768,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "projection_dim": 768,
+  "torch_dtype": "float32",
+  "transformers_version": "4.23.1",
+  "vocab_size": 49408
+}

text_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96c15170a0cf658b476b0146e5620f2789b41919acc43920102d1afccd27b58b
+size 492308087

tokenizer/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer/tokenizer_config.json

@@ -0,0 +1,34 @@
+{
+  "add_prefix_space": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "do_lower_case": true,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "errors": "replace",
+  "model_max_length": 77,
+  "name_or_path": "/root/.cache/huggingface/diffusers/models--runwayml--stable-diffusion-v1-5/snapshots/51b78538d58bd5526f1cf8e7c03c36e2799e0178/tokenizer",
+  "pad_token": "<|endoftext|>",
+  "special_tokens_map_file": "./special_tokens_map.json",
+  "tokenizer_class": "CLIPTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

unet/config.json

@@ -0,0 +1,37 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.7.0.dev0",
+  "_name_or_path": "runwayml/stable-diffusion-v1-5",
+  "act_fn": "silu",
+  "attention_head_dim": 8,
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "cross_attention_dim": 768,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "flip_sin_to_cos": true,
+  "freq_shift": 0,
+  "in_channels": 4,
+  "layers_per_block": 2,
+  "mid_block_scale_factor": 1,
+  "norm_eps": 1e-05,
+  "norm_num_groups": 32,
+  "out_channels": 4,
+  "sample_size": 32,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ]
+}

unet/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f06b9d9913b121480f23854c897bf6a3fc0e5ce61be1700e39fb7523a0278e3
+size 3438364325

vae/config.json

@@ -0,0 +1,30 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.7.0.dev0",
+  "_name_or_path": "stabilityai/sd-vae-ft-mse",
+  "act_fn": "silu",
+  "block_out_channels": [
+    128,
+    256,
+    512,
+    512
+  ],
+  "down_block_types": [
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D",
+    "DownEncoderBlock2D"
+  ],
+  "in_channels": 3,
+  "latent_channels": 4,
+  "layers_per_block": 2,
+  "norm_num_groups": 32,
+  "out_channels": 3,
+  "sample_size": 256,
+  "up_block_types": [
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D",
+    "UpDecoderBlock2D"
+  ]
+}

vae/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b4889b6b1d4ce7ae320a02dedaeff1780ad77d415ea0d744b476155c6377ddc
+size 334707217