Raemu Flux is a finetuned model built on top of Flux.1-dev, specifically focused on anime. It has been finetuned with dataset nearly 1,500 carefully curated, high-quality aesthetic anime images, resulting in noticeable improvements in anime scene rendering and visual quality.

If you enjoy my work and like it, you can support me at Ko-fi

How to prompt

Be sure to include "anime" in your prompt; otherwise, the output may appear realistic. For example: "A woman anime hold sign that says Hello World."

Training details

Trained with kohya-ss/sd-scripts on RTX 4090

All images captioned using Joy-Caption

Trained resolution: 1024x1024

Rank dim/alpha: 128/128

License

The model falls under the FLUX.1 [dev] Non-Commercial License.