Radar / AI media tools / FLUX 3 Max
FLUX 3 Max: fal and Black Forest Labs ship top-tier image-to-video at 22x the speed
fal and Black Forest Labs announced FLUX 3 Max on Oct 19: a post-trained FLUX 3 built for image-to-video that scores 1,139 Elo on the Artificial Analysis Video Arena and renders a 10-second clip in about 11 seconds, 22x faster than Seedance 2.5 at the same quality tier. Available via fal's API for 5-20s clips, with promo 720p pricing of $0.425 per 10s clip through Nov 7.
Why it matters
The best reported speed/quality tradeoff for image-to-video to date: frontier-tier Arena scores with generation times close to real-time, from fal's inference-optimization stack rather than a raw research checkpoint.
What you could build with it
A marketing team or solo creator could iterate on product stills through FLUX 3 Max's fast image-to-video pipeline, generating dozens of short ad variants in one afternoon and A/B testing the winners the same day.
Does it hold up?
Too early to judge: launched Oct 19. The independent Video Arena score is strong, but it covers image-to-video only, and fal's speed claims have not been independently reproduced yet.
Built with FLUX 3 Max
- fal's official launch release via PR Newswirearticle · Full launch details: fal Research post-training with Black Forest Labs, 1,139 Arena Elo across 4,868 votes, 10.95s per 10s clip, pricing and promo terms.
- Superpower Daily: 22-fold speed claim, with caveatsarticle · Critical read: speed figures are fal's own (release says 10.95s, VentureBeat quotes 12.45s), Arena confidence intervals overlap the leading models, and the $1.70 regular price per 10s clip sets the revision-loop economics.
- Wisevoter coverage of the FLUX 3 Max launcharticle · Launch summary: 720p with optional 1080p upscaling, keyframes endpoint for up to 10 images per sequence, 75% intro discount expiring Nov 7.
Learn more
First spotted on article: source.
More AI media tools
VoiceStudio — open-source, fully-local ElevenLabs alternativeOpen-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation…media · JEV 0.73OpenMontage: open-source agentic video production systemTurns an AI coding assistant into a full video studio: 12 pipelines and 100+ tools for scripting, footage, narration…media · JEV 0.73LingBot-Map: streaming 3D reconstruction foundation model (ECCV 2026 best-paper candidate)Feed-forward 3D foundation model that reconstructs scenes from streaming video at ~20 FPS with drift correction over…media · JEV 0.7HyperFramesHeyGen's open-source framework that turns HTML/CSS/GSAP into deterministic MP4 video via 21 agent skills and a router…media · JEV 0.69ArtCraft pivots to seven open-source Adobe clones built with Claude Opus 5.5Brandon Thomas pivoted his AI art IDE into a seven-app open-source creative suite…media · JEV 0.67SolidCraft: open-source parametric CAD in Rust that agents can drive over MCPSolidCraft is an open-source parametric 3D CAD application written in pure Rust (desktop, browser via WebAssembly…media · JEV 0.67
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.