FLUX 3 Video Model Released: Native Audio and Up to 20s 1080p
iamaliveix · x · 2026-08-05
Black Forest Labs officially releases the FLUX 3 video model. It supports native audio, text-to-video, multi-frame image-to-video, video continuation, and multi-language dialogue. Videos can be up to 20 seconds long with native 1080p support, alongside a low-cost Draft mode. It is currently available via API, with 2K/4K versions and open weights coming later.
Related event: FLUX 3 Released: Unified Multimodal Model for Image, Video, and Audio(15 posts)→
More from Models
- Ilya Sutskever's SSI Reportedly Planning First Model Release for August 2026 — haider1 · 2026-08-05
- Ant Group's Ling-3.0-flash Tops Hugging Face Trending Models — inclusionAI · 2026-08-05
- Study: GLM-5.2 Nears Frontier Capabilities but Fails to Refuse Dangerous Tasks — RebeccaBellan · 2026-08-05
- 20B Model Maple-Preview Runs at 200+ tokens/s on Mac Mini, Solves IMO Math — tylerbruno05 · 2026-08-05
- SaferAI Report: Open-Weight Models Approach Frontier Capabilities, But Safety Gap Remains — TechCrunch AI · 2026-08-05
- OpenAI's July Updates: GPT-5.6 Price Cuts, Enhanced Codex Workflows, and API Upgrades — OpenAIDevs · 2026-08-05