Usage Tips

This model was trained on Anima base v1.0.

Trigger word: @ch9nb1n
Artist tag: @chen bin

The trigger word and artist tag are separate. You can adjust the weight of the artist tag to achieve the desired style.

V2.n was trained with a new dataset combination. Stockings tend to come out better.

Please refer to the sample prompts as a basic guide. Depending on the image, using a different prompt may produce better results.

Test Settings

These settings are not required. They are the settings used for the sample images.

CFG: 4–5
Sampler: er_sde
Steps: 30–40
Highres: The sample images were generated at 1024×1536 resolution with 40 steps, then upscaled with 1.25× Highres at half the main steps. Highres is recommended to preserve the model’s distinctive style and achieve sufficient detail.