FLUX 3 Max tops image-to-video benchmark, generating 10s video in ~12 seconds
heyshrutimishra · x · 2026-10-20
fal and Black Forest Labs launched FLUX 3 Max, a post-trained video model tied for #1 in image-to-video quality on third-party benchmarks. It renders a 10-second 720/768p video in 12 seconds, while Seedance 2.5 at the same score took over 4.5 minutes in fal's tests — the difference between testing one prompt and twenty. The 720/768p cap still matters for final delivery but not for storyboards, pitches or rough cuts. It's 75% off on fal for three weeks, making it the cheapest frontier-quality video model at that tier.
More from Multimodal
- Viggle Releases JST-2, Claiming First Full-Stack Physics-Native 3D World Foundation Model — willeastcott · 2026-10-20
- TerraVis at NeurIPS 2026: New Benchmark Flags Physically Wrong AI Images That Score High — jiqizhixin · 2026-10-20
- New MULTIFINGROUND Benchmark Shows LLMs Recognize Financial Concepts but Fail at Full Evidence Extraction — TheFinAI · 2026-10-20
- iPhone Action Button + Grok voice + HeyGen MCP turns a sentence into an avatar video — HeyGen · 2026-10-20
- AI-generated Tesla Roadster street video is indistinguishable from real footage — Tiny-Meet5202 · 2026-10-20
- Video Geometry Corrector fixes 3D distortions in AI-generated videos, NeurIPS paper — kwangmoo_yi · 2026-10-20