Upload 7 files

.gitattributes

@@ -36,3 +36,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 images/A1579/logo.png filter=lfs diff=lfs merge=lfs -text
 images/A1579/sample1.png filter=lfs diff=lfs merge=lfs -text
 images/A1579/sample2.png filter=lfs diff=lfs merge=lfs -text
+images/A1818/logo.png filter=lfs diff=lfs merge=lfs -text
+images/A1818/sample1.png filter=lfs diff=lfs merge=lfs -text
+images/A1818/sample2.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -90,6 +90,88 @@ orange eyes,arms behind back,close view,from front,[smile,close mouth],
 </div>
 </details>
 
+<details>
+<summary>FlatpieceCoreXL A1818</summary>
+<div>
+
+![](images/A1818/logo.png)
+
+# ▼ 本モデルの概要 (Overview of this model)
+
+本モデルは<a href="https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/LICENSE.md" target="_blank">CreativeML OpenRAIL++-M</a>ライセンスの訓練モデル、SDXL1.0追加学習モデル、またそれらのみをマージしたモデルを使用して製作されています。<br>
+<br>
+FlatpieceCoreXL A1818は、前作のA1579をベースに更に描写を改善し、アニメ調の特徴であるベタ塗りを強調したモデルとなります。<br>
+また、顔の描写もアニメ調具合を更に向上させ、出力の安定性を改善しています。<br>
+シンプルなプロンプトでも精細な出力が実現できるように、調整しております。<br>
+<br>
+This model will be a merged model, using only the training model and SDXL1.0 additional learning model from the <a href="https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0/blob/main/LICENSE.md" target="_blank">CreativeML OpenRAIL++-M</a> license.<br>
+<br>
+FlatpieceCoreXL A1818 is based on the previous A1579 model, with further improved depiction, emphasizing the solid coloring that is characteristic of the anime style.<br>
+It also improves the stability of the output by further enhancing the anime-like quality of the face.<br>
+I have made adjustments so that even simple prompts can achieve a highly detailed output.br><br>
+
+
+# ▼ 推奨設定 (Recommended settings)
+
+- Sampler: DPM++ 2M Karras
+- Step: 35 - 40
+- CFG scale: 8.0 - 10.0
+- Denoising strength: 0.7 - 0.8
+- Clip skip: 1
+- Hires upscale: 1.5 - 2.0
+- Hires steps: 15 - 18
+- Hires upscaler: R-ESRGAN 4x+ Anime6B
+- ENSD (Eta noise seed delta): 31337
+- VAE: <a href="https://huggingface.co/konapieces/FlatpieceCoreXL/blob/main/vae/flatpiece.xl.vae.safetensors" target="_blank">flatpiece.xl.vae</a>
+- Extension: FreeU, Tiled VAE
+- Embeddings: negativeXL, unaestheticXL
+- Size: 768 x 768 or higher
+
+# ▼ 推奨事項 (Recommendations)
+
+- SDXLの学習解像度の関係上、解像度は768pixel以上が推奨です。
+- Denoising Strengthは0.7以上を推奨します。
+- モデル本来の色彩はBrightnessが強めである為、推奨VAEを使用することをお勧めします。
+
+- Due to SDXL's learning resolution, a resolution of 768 pixels or higher is recommended.
+- Denoising Strength is recommended to be 0.6 or higher.
+- Since the original color of the model has a strong Brightness, it is recommended to use the recommended VAE.
+
+# ▼ 出力サンプル (Sample)
+
+[Prompt]<br>
+
+```
+4k wallpaper,highres,kawaii,1 woman, solo,light smile, open mouth,burgundy hair, high ponytail,frost eyes,
+Bow-front blouse with a sweetheart neckline and puff shoulders,simple background
+```
+
+[Negative prompt]<br>
+```
+negativeXL_D,unaestheticXL_Sky3.1,(worst quality:1.5),(low quality:1.5),(normal quality:1.5),(monochrome),(grayscale),(watermark),(white letters),signature,
+username,text,error,(manicure),(nsfw),(earing),(lipgloss)
+```
+
+<img src="https://huggingface.co/konapieces/FlatpieceCoreXL/resolve/main/images/A1818/sample1.png" width="768">
+
+[Prompt]<br>
+
+```
+4k wallpaper,highres,kawaii,1 woman, solo,light smile, open mouth,from side,aquamarine hair, bangs,
+mint eyes,Lace knit cardigan,bokeh, space elevator
+```
+
+[Negative prompt]<br>
+```
+negativeXL_D,unaestheticXL_Sky3.1,(worst quality:1.5),(low quality:1.5),(normal quality:1.5),(monochrome),(grayscale),(watermark),(white letters),signature,
+username,text,error,(manicure),(nsfw),(earing),(lipgloss)
+```
+
+<img src="https://huggingface.co/konapieces/FlatpieceCoreXL/resolve/main/images/A1818/sample2.png" width="768">
+
+</div>
+</details>
+
 ----
 
 # ▼ 免責事項 (Disclaimer)