a distillation lora for anima, trained on ~100 images at 1024x generated by the model itself using 40 steps cfg = 4 er_sde from diverse captions baked-in negative prompt: worst quality, low quality, score_1, score_2, score_3, blurry, jpeg artifacts, sepia may or may not be underbaked/overbaked works best with cfg = 1 and 8 steps for heun/2s samplers, 16 steps for 1s or multistep samplers the training code is a modification of diffusion-pipe for RL/distillation + custom comfyui nodes for data generation TODO: get a larger more diverse RL dataset and filter it for artifacts

[Anima] Flash 8 steps cfg 1 distilled

100 epochs with ga = 1 on 127 images filtered from 239 images

Files with SHA256: 2d73254f7b0ba0c75b7a62111fb7af6a2ee7fcd7c96f21fbcbddf8955fa24a74