Lora trained on the oldest style of artwork from the artist Thepit. Trained on Anima v1.0.

Trigger word: @tr1gg3r

Generation settings recommendation: sampler: er_sde / scheduler: normal / steps: 28-50 / cfg: 3.5-5.

Recommended lora strength: 0.9 or lower for more flexibility.

For faster generation, I usually generate at 768*1024, then upscale 1.5x with 4x_ultrasharp and 0.3-0.4 denoising (12-16 steps).