Rethinking What to Cache in Few-Step Diffusion Transformers: Solver-Aware Target Selection
This work introduces AutoTarget, a method that chooses the cached tensor for a given model, solver, and reuse schedule, and experiments on distilled image and video DiTs show that the best cache target changes with the model, image resolution, and solver.
Shuo-Shuo Yang, Li-Hao Fang, Yi Zhang et al.
· 0 citations