Categories
- All Posts 548
- Practical Open Source Projects 478
- Tutorial Articles 22
- Online Utilities 13
- AI news 7
- Tiny Startups Showcase 7
- Prompt Templates 5
- Claude Code Skills 5
- Hugging Face Spaces 3
- OpenClaw Use Cases 3
- LLM Learning Resources 1
- Online AI Image Tools 1
- OpenClaw Master Skills Collection 1
- Rust Training Resources 1
- AI Short Drama Tools 1
- My Favorites 0
Posts tagged with: diffusion-models
Content related to diffusion-models
Helios: 14B Real-Time Video Gen at 19.5 FPS
March 25, 2026
Discover Helios, the breakthrough 14B parameter video generation model from PKU-YuanGroup that generates minute-scale, high-quality videos at 19.5 FPS on a single H100 GPU. No anti-drifting tricks, no acceleration hacks - just pure architectural innovation. Supports T2V, I2V, V2V, and interactive generation with Day-0 support for Diffusers, SGLang, vLLM-Omni, and Ascend NPU. Run it locally with ~6GB VRAM using group offloading. Complete training code and three model variants (Base, Mid, Distilled) available now.