August Video Gen Shakeout: fal-Post-Trained MiniMax H3 Max Tops Image-to-Video
isidentical · x · 2026-09-04
DesignArena's August recap of video generation:
- MiniMax H3 Max, post-trained by fal, took the top spot on Image-to-Video, cutting generation time by 46x vs H3;
- Wan 3.0 by Alibaba jumped 12 positions to 3rd overall;
- Black Forest Labs debuted FLUX 3 Video with strong overall performance;
- Google DeepMind's Omni 1.1 introduced cheaper, faster drafts.
Four August releases now sit in the top 11, including two of the top three. fal also says its frontier RL infrastructure is working with leading gen-media model companies to make models higher quality, faster, and more "vibey".
More from Multimodal
- fal dev spills: MiniMax H3 'quality' mode matches balanced in 99.9% of cases but adds 60-120s — isidentical · 2026-09-04
- Meta's first image model Muse Image debuts #4 in image editing at just $0.01 per image — ArtificialAnlys · 2026-09-04
- One Prompt, One 3D Render: Astra Turns a Sentence into a Product Visual — iansilber · 2026-09-04
- The Generative Burrito Test puts 24 image models to work recreating one real burrito photo — generativist · 2026-09-04
- Immunologist one-shots a 5-minute T-cell lecture video from a single prompt with GPT-6 — DeryaTR_ · 2026-09-04
- AI filmmaker shares rough sample of animated world 'BOO FOR HIRE' — DavidmComfort · 2026-09-04