first commit

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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
+*.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,148 @@
+---
+license: other
+thumbnail: >-
+  https://huggingface.co/ddPn08/subtle/resolve/main/images/main.png
+tags:
+  - stable-diffusion
+  - text-to-image
+  - safetensors
+  - diffusers
+inference: true
+widget:
+  - text: >-
+      masterpiece, best quality, high quality, newest, new, exceptional, best aesthetic, anime, 1girl, short hair, black hair, messy hair, black eyes, ahoge, white shirt, outdoors, dappled sunlight, leaf, looking at viewer,
+    example_title: example 1girl
+  - text: >-
+      masterpiece, best quality, high quality, newest, new, exceptional, best aesthetic, anime, 1boy, short hair, black hair, messy hair, black eyes, ahoge, white shirt, outdoors, dappled sunlight, leaf, looking at viewer,
+    example_title: example 1boy
+language:
+  - en
+library_name: diffusers
+---
+
+<div align="center">
+
+![](./images/main.png)
+
+</div>
+<h1 align="center"><b>Subtly</b></h1>
+<p align="center">A very subtle model. And an animated model that does not use any NAI leaks. </p>
+
+<h1 align="center">Downloads</h1>
+<div align="center">
+
+[![](https://img.shields.io/static/v1?label=Download&message=Checkpoint&labelColor=333333&color=72B76C&style=for-the-badge)](https://huggingface.co/ddPn08/subtle/resolve/main/subtly-fp32.ckpt)
+<span></span>
+[![](https://img.shields.io/static/v1?label=Download&message=SafeTensors&labelColor=333333&color=72B76C&style=for-the-badge)](https://huggingface.co/ddPn08/subtle/resolve/main/subtly-fp32.safetensors)
+
+</div>
+
+
+<br >
+
+# Examples
+![](./images/example-1.png)
+
+<details>
+<summary>Prompt</summary>
+
+```yaml
+prompt: masterpiece, best quality, high quality, newest, new, exceptional, best aesthetic, BREAK
+[anime], 1girl, black hair, short hair, messy hair, wavy mouth, sweat, nude, BREAK
+simple background, looking at viewer,
+negative_prompt: old, oldest, worst quality, low quality, normal quality, deleted, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, jpeg artifacts, signature, watermark, username, blurry, head out of frame,
+Steps: 29
+Sampler: Euler a
+CFG scale: 8
+Seed: 3159754303
+Size: 768x768
+Model hash: aa0bd9fbc5
+Model: subtly-fp32
+Clip skip: 2
+```
+</details>
+
+
+<br>
+
+![](./images/example-2.png)
+
+<details>
+<summary>Prompt</summary>
+
+```yaml
+prompt: masterpiece, best quality, high quality, newest, new, exceptional, best aesthetic, BREAK
+1girl, short hair, messy hair, ahoge, jitome, BREAK
+outdoors, dappled sunlight, leaf, looking at viewer,
+negative_prompt: old, oldest, worst quality, low quality, normal quality, deleted, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, jpeg artifacts, signature, watermark, username, blurry
+Steps: 29
+Sampler: Euler a
+CFG scale: 8
+Seed: 913456778
+Size: 704x704
+Model hash: aa0bd9fbc5
+Model: subtly-fp32
+Clip skip: 2
+```
+</details>
+
+
+<br>
+
+![](./images/example-3.png)
+
+<details>
+<summary>Prompt</summary>
+
+```yaml
+prompt: masterpiece, best quality, high quality, newest, new, exceptional, best aesthetic, BREAK
+[anime], 1girl, long hair, black hair, black eyes, open mouth, bikini, BREAK
+outdoors, ocean, beach, palm tree,
+negative_prompt: worst quality, low quality, normal quality, deleted, lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, jpeg artifacts, signature, watermark, username, blurry, old, oldest
+
+Steps: 29
+Sampler: Euler a
+CFG scale: 8
+Seed: 3704255935
+Size: 704x704
+Model hash: aa0bd9fbc5
+Model: subtly-fp32
+Clip skip: 2
+ENSD: 31337
+```
+</details>
+
+
+<br>
+
+# About this
+This model is trained based on Waifu Diffusion 1.5. NovelAI leakage models are not included at all. But it still won't beat NovelAI. (Subtle, isn't it?)
+
+The Waifu Diffusion 1.5 prompt differs slightly from the NAI-based model.
+
+For more information, please refer to this release note.
+
+https://cafeai.notion.site/WD-1-5-Beta-Release-Notes-967d3a5ece054d07bb02cba02e8199b7
+
+<br>
+
+# limitation
+
+## Realistic pictures are output.
+Waifu Diffusion 1.5 learns many images from Instagram and does not output anime images by default. Therefore, you need to put `anime` in the prompt. (You may still get realistic images. Subtle.)
+
+It can also be controlled by putting `instagram`, `real-life` in the negative prompt. However, these are not recommended because they may affect the human anatomy and the background.
+
+
+<br >
+
+## NSFW
+This model is very vulnerable to NSFW. It is weak in it's own right. We are currently working on making it stronger to NSFW but it is not going well. (It's subtle.)
+
+I would like to know if anyone has any knowledge about this.
+
+
+<br >
+
+# License
+Subtly is released under the Fair AI Public License 1.0-SD (https://freedevproject.org/faipl-1.0-sd/).

model_index.json

@@ -0,0 +1,33 @@
+{
+  "_class_name": "StableDiffusionPipeline",
+  "_diffusers_version": "0.10.2",
+  "feature_extractor": [
+    null,
+    null
+  ],
+  "requires_safety_checker": null,
+  "safety_checker": [
+    null,
+    null
+  ],
+  "scheduler": [
+    "diffusers",
+    "DDIMScheduler"
+  ],
+  "text_encoder": [
+    "transformers",
+    "CLIPTextModel"
+  ],
+  "tokenizer": [
+    "transformers",
+    "CLIPTokenizer"
+  ],
+  "unet": [
+    "diffusers",
+    "UNet2DConditionModel"
+  ],
+  "vae": [
+    "diffusers",
+    "AutoencoderKL"
+  ]
+}

scheduler/scheduler_config.json

@@ -0,0 +1,14 @@
+{
+  "_class_name": "DDIMScheduler",
+  "_diffusers_version": "0.10.2",
+  "beta_end": 0.012,
+  "beta_schedule": "scaled_linear",
+  "beta_start": 0.00085,
+  "clip_sample": false,
+  "num_train_timesteps": 1000,
+  "prediction_type": "v_prediction",
+  "set_alpha_to_one": false,
+  "skip_prk_steps": true,
+  "steps_offset": 1,
+  "trained_betas": null
+}

subtly-fp16.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:767ba95f77c67f26839af3e8559aafe4c7144eb470d40a503e05c590ea6e7768
+size 2580321435

subtly-fp16.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:562e2f5b87dbc5faad82c3a2ae2e7c550105013705be812357f1d078ddb9a86c
+size 2580068398

subtly-fp32.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a7ac82220a8e56421027a84187c1d7f8f0d50c023c89e3c2c5443105592d260
+size 5160227439

subtly-fp32.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa0bd9fbc5829d5b510cd1cc6e308c412f1a3ba184454ef013e81aa52462d289
+size 5159974886

text_encoder/config.json

@@ -0,0 +1,24 @@
+{
+  "architectures": [
+    "CLIPTextModel"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "dropout": 0.0,
+  "eos_token_id": 2,
+  "hidden_act": "gelu",
+  "hidden_size": 1024,
+  "initializer_factor": 1.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 77,
+  "model_type": "clip_text_model",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 23,
+  "pad_token_id": 1,
+  "projection_dim": 512,
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.0",
+  "vocab_size": 49408
+}

text_encoder/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5162e48803d14cb34adba2d974d7d4b1a97eef7b2d1fc3565fcef80d1b5ef08f
+size 1361674657

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": "!",
+  "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": "waifu-diffusion/wd-1-5-beta",
+  "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 +1,46 @@
+{
+  "_class_name": "UNet2DConditionModel",
+  "_diffusers_version": "0.10.2",
+  "act_fn": "silu",
+  "attention_head_dim": [
+    5,
+    10,
+    20,
+    20
+  ],
+  "block_out_channels": [
+    320,
+    640,
+    1280,
+    1280
+  ],
+  "center_input_sample": false,
+  "cross_attention_dim": 1024,
+  "down_block_types": [
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "CrossAttnDownBlock2D",
+    "DownBlock2D"
+  ],
+  "downsample_padding": 1,
+  "dual_cross_attention": false,
+  "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,
+  "num_class_embeds": null,
+  "only_cross_attention": false,
+  "out_channels": 4,
+  "sample_size": 64,
+  "up_block_types": [
+    "UpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D",
+    "CrossAttnUpBlock2D"
+  ],
+  "upcast_attention": false,
+  "use_linear_projection": false
+}

unet/diffusion_pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c7ac56b03278ee5a5676645b6190942e404262690195c1ef5bbd5f1ccf1bd60
+size 3463925413

vae/config.json

@@ -0,0 +1,29 @@
+{
+  "_class_name": "AutoencoderKL",
+  "_diffusers_version": "0.10.2",
+  "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 sha256:3e174991e5609bc5c2b3995e3f223fb2c5f0ae3be307fa9591b351d837a08770
+size 334711857