Pixel Art 像素艺术 XL

Trained using 5,487 distinct styles of anime pixel images, this model will generate pixelated images in various styles at random. Enjoy the surprises!

TAG:

pixel_art

Training model: Animagine XL V3.1

Inference model: Animagine XL V3.1

Training resolution: 1024*1024

--

TAG:

pixel_art

Trained using 2827 images of various pixel art styles. Theoretically, it can generate random pixel art styles. Let's play Gacha and see what we get!

使用2827张不同风格的像素风格的图片训练。理论上会随机生成不同风格的像素画风。来玩抽卡吧

Please note that this model's content includes some covers that have been rated as PG-13/R/xxx

Please choose the appropriate age rating based on your needs.

Training model: Animagine XL V3.1

Inference model: Animagine XL V3.1

Training resolution: 1024*1024

Recommended output resolution: 1024*1280 /832*1216

Recommended model weight: 0.8~1

Discord : https://discord.com/invite/CFpyHceF52

Recommended dataset collection and processing tools: https://github.com/deepghs/waifuc

Possibly the most user-friendly dataset processing UI currently in use.: https://github.com/Eugeoter/sd-dataset-manag