PKU-YuanGroup/Helios
Helios: Real Real-Time Long Video Generation Model
Generates minute-scale video without anti-drifting strategies or standard acceleration techniques, achieving 19.5 FPS on single H100 GPU through novel architectural optimizations. Integrates with Diffusers, SGLang-Diffusion, vLLM-Omni, and Ascend-NPU, with support for group offloading and context parallelism across multiple GPUs while maintaining low VRAM footprint (~6GB).
1,332 stars. Actively maintained with 61 commits in the last 30 days.
Stars
1,332
Forks
97
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 18, 2026
Commits (30d)
61
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/PKU-YuanGroup/Helios"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related models
hao-ai-lab/FastVideo
A unified inference and post-training framework for accelerated video generation.
thu-ml/TurboDiffusion
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
ModelTC/LightX2V
Light Image Video Generation Inference Framework
PKU-YuanGroup/MagicTime
[TPAMI 2025🔥] MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators
thu-ml/DiT-Extrapolation
Official implementation for "RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion...