anima-turbo
Collection
turbo series • 3 items • Updated
Anima lora for turbo generation, implemented with DP-DMD and Continuous-Time Distillation paper.
This model is presented in the paper When does training on downscaled images yield the same gradients?.
Try new anima_turbo_4step_v2_longer.safetensors
trained with 10k steps, 30h in single 5070ti using anima_lora
Reproducible by CFG=1.0, steps=4, er_sde sampler
Model tree for sorryhyun/anima-turbo-4step
Space using sorryhyun/anima-turbo-4step 1
Collection including sorryhyun/anima-turbo-4step
Papers for sorryhyun/anima-turbo-4step
When does training on downscaled images yield the same gradients?
Paper • 2608.04448 • Published
Continuous-Time Distribution Matching for Few-Step Diffusion Distillation
Paper • 2605.06376 • Published • 27
Diversity-Preserved Distribution Matching Distillation for Fast Visual Synthesis
Paper • 2602.03139 • Published • 45