Fal releases H3 Max: 3-second 720p video generation model
QuixiAI · x · 2026-08-27
Fal Research has released H3 Max, a post-trained video model that ranks #1 in quality and prompt understanding across benchmarks. It generates 5-second 720p videos in under 3 seconds. The model is currently 50% off. However, it has sparked controversy as Fal took open weights, optimized them, and closed the source to offer the model exclusively via a paid API.
Related event: fal's H3 Max: Post-trained MiniMax H3 Tops Image-to-Video Leaderboards(29 posts)→
More from Companies & People
- ROBIB robotics meetup #3 lands in Ghent on Nov 19 with academic and industry speakers — MarwaEldiwiny · 2026-10-15
- Bank of America puts 4,000 people on fixing vulnerabilities uncovered by AI models — The Decoder · 2026-10-15
- G2's 2026 AI Agents report: Distrust Tax, Shadow Agents and enterprise adoption — sanderssays · 2026-10-15
- Anthropic is hiring a DevRel for scientists to grow its Claude research community — AI4Code · 2026-10-15
- Lexsi's AI Safety & Alignment Hackathon offers $30K+ prizes with Cohere Labs and Hugging Face — Cohere_Labs · 2026-10-15
- Source: Anthropic meeting discussed no September-quarter or full-year ARR outlook — matt_slotnick · 2026-10-15