💡HunyuanVideo1.5 Update: We are now releasing the 480p I2V step-distilled…
- Source
- x.com
- Date
💡HunyuanVideo1.5 Update: We are now releasing the 480p I2V step-distilled model, which generates videos in 8 or 12 steps (recommended)! On RTX 4090, end-to-end generation time is reduced by 75%, and a single RTX 4090 can generate videos within 75 seconds. The step-distilled model maintains comparable quality to the original model while achieving significant speedup. For even faster generation, you can also try 4 steps (faster speed with slightly reduced quality). 🔗Check out the GitHub Repo:
Context
Tencent's 480p HunyuanVideo-1.5 update shortens image-to-video generation by using a model trained to work with fewer generation steps. The team recommends eight or twelve steps and reports a 75% reduction in end-to-end generation time on a single RTX 4090, with generation taking up to 75 seconds in its reported setup. It describes quality as comparable to the original model; a four-step option trades some quality for further speed. These are the team's results for the December 5, 2025 release.
- distillation — Training a small, cheap model to imitate a big one's outputs, keeping much of the capability at a fraction of the cost.
postExplorationBench tests how models explore, with exactly verifiable grading
postHy Image3.5 preview is live. 🚀 Professional-grade image generation, +30% win…
postTencent Hunyuan's EvolveScaler trips up frontier models on evolving facts
postTencent Hunyuan open-sources AuK, a unified speech generation and editing model
Checking sign-in…
Loading comments…