Hunyuan TeaCache 1.6x speedup
- Fully operational workflows
- No missing nodes or models
- No manual setups required
- Features stunning visuals
Introduction
Hunyuan TeaCache 1.6x speedup, We introduce Timestep Embedding Aware Cache (TeaCache), a training-free caching approach that estimates and leverages the fluctuating differences among model outputs across timesteps, thereby accelerating the inference. TeaCache works well for Video Diffusion Models, Image Diffusion models and Audio Diffusion Models. For more details and results.
