X | Civitai | Hugging Face | GitHub | Discord
NoahMix is an easy-to-use Stable Diffusion XL merge model specialized for anime, based on NoobAI + LizMix / HinanoMix.
This model is designed based on the following principles:
Reproduces natural and vibrant coloring in anime and character outputs.
Easy for beginners to handle and supports a wide range of styles.
Merge model created with ComfyUI.
Confirmed to work with ComfyUI, AUTOMATIC1111, and Forge.
Sampler: DPM++ 2M or Euler a recommended.
Steps: 20-
Clipskip: 2
CFG Scale: 6-12
Including quality tags (masterpiece, best quality, etc.) will stabilize the art style.
Load it like a regular SDXL model according to your UI.
Recommended environments:
ComfyUI (latest version)
AUTOMATIC1111,Web UI (SDXL compatible),Forge Classic
1.
HinanoMix V3 x (1-alpha) + NoobAI V-Pred-1.0 x alpha (0.0,1.0,0.9166666667,0.8333333333,0.75,0.6666666667,0.5833333333,0.5,0.4166666667,0.3333333333,0.0,0.0833333333,0.1666666667,0.25,0.3333333333,0.4166666667,0.5,0.5833333333,0.6666666667,0.75,0)
2.
1 + LizMixV16 x alpha (0.0,0.0,0.0833333333,0.1666666667,0.25,0.3333333333,0.4166666667,0.5,0.5833333333,0.6666666667,1.0,0.9166666667,0.8333333333,0.75,0.6666666667,0.5833333333,0.5,0.4166666667,0.3333333333,0.25,0)
3.
A + Original LoRA + additional learning modelsUsers are solely responsible for the results of the generated output.
This model is not designed for the purpose of displaying or sharing ???? content in public places.
Please use in compliance with public guidelines, laws, and platform policies.
This model is distributed under the following license:
[Fair AI Public License 1.0-SD](https://freedevproject.org/faipl-1.0-sd/)
1. The rights to reposted models belong to original creators.
2. Original creators should contact SeaArt.AI staff through official channels to claim their models. We are committed to protecting every creator's rights. Click to Claim
