ali-vilab/TeaCache

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1369 stars · 60 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

TeaCache is a training-free caching approach that accelerates inference for video diffusion models by estimating output differences across timesteps using timestep-embedding-modulated model inputs. It supports models like CogVideoX, HunyuanVideo, Latte, Open-Sora, and Open-Sora-Plan, achieving up to 4.41x speedup with negligible visual quality loss.

Use cases

• speed up video diffusion model inference
• accelerate CogVideoX video generation
• reduce latency of HunyuanVideo denoising
• cache model outputs in Open-Sora pipelines
• training-free acceleration for video generation models
• make text-to-video generation faster on GPU

When to choose

• you need faster video diffusion inference without retraining or fine-tuning
• you use a supported model like CogVideoX, HunyuanVideo, Latte, or Open-Sora
• you can tolerate minimal visual quality degradation for large speedups

When to avoid

• you need exact, bit-identical outputs from the original diffusion model
• your video model is not among the supported architectures
• you need image-only diffusion acceleration rather than video

Facets

library · maturity active

machine-learning llm-inference video-processing caching deep-learning artificial-intelligence image-processing python diffusion-models inference-acceleration video-generation training-free cogvideox hunyuan-video open-sora latte cvpr-2025 video gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="ali-vilab/TeaCache")