Diversity-Preserved Distribution Matching Distillation for Fast Visual Synthesis
Paper • 2602.03139 • Published • 45
Anima lora for turbo generation, implemented with DP-DMD
Try new anima_turbo_S.safetensors
trained with 12k steps, 18h in single 5070ti using anima_lora
Reproducible by CFG=1.0, steps=4, er_sde sampler
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for sorryhyun/anima-turbo-4step
Base model
nvidia/Cosmos-Predict2-2B-Text2Image Finetuned
circlestone-labs/Anima