This is the initial release of the LoRA trained by @1041uuu (TOYOI Yuuta) pixel artworks.
⚠️ Pixel perfection is NOT guaranteed. This LoRA is incompatible with the Pixelate x4 VAE. For best results, I recommend generating at 512x512 or higher using base-v01 with 30 steps / 5 CFG and EulerER_SDE / Simple. However, please note that it still will not achieve flawless pixel perfection.
I attempted to clean up the messy or broken pixels using post-processing tools like PixelOE and ComfyUI-AI-Pixel-Art-Enhancer, but in my testing, it was impossible to fix them without losing the original aesthetic and atmosphere of the style. Therefore, for this v0.0.0 release, I have decided to publish it as-is, in its "pixel-imperfect" state.
Recommended Settings
Recommended Weight:
1.0Optional Positive Prompts:
jaggy lines, dithering, no lineart, limited paletteOptional Negative Prompts:
jpeg artifacts, isometric, letterboxed, pillarboxed, dated
Description
Initial (experimental).
A LoRA weight of 1.5 or higher is recommended.
Pixel-perfect results are not guaranteed. The LoRA often produces ambiguous or poorly defined pixels, so artifacts may need to be removed using tools such as the PixelOE node.
Captioning was performed almost entirely using Danbooru tags, with the same captions as the Krea 2 and Anima versions. The captioning method recommended in MOSS's USERGUIDE.md was not used.
LORA, MOSS Image Base, dim32/alpha32, AdamW8bit, LR 1e-4, constant 1700steps, 100images(x8 scaled), 1024² res.