Black Forest Labs says Flux 3 video generation is open source and full multimodal
op7418 · x · 2026-07-23
Black Forest Labs is said to have released and open-sourced Flux 3 video generation.
- The model supports text-to-video, image-to-video, video reference generation, audio/video extension, keyframe control, multilingual dialogue, and smart multi-shot editing.
- It can also generate text, motion design, and still images.
- The post says Flux 3 Dev will be open source, but early access is currently required; API access is planned in the coming weeks before the open-source release.
Related event: Black Forest Labs Launches FLUX 3 Omni-Modal Model(19 posts)→
More from Multimodal
- Microsoft previews MAI-Image-2.5-Pro as its highest-fidelity professional image model — mustafasuleyman · 2026-07-24
- Stable Diffusion unveils FLUX 3 with image, video and native audio generation — imjustnewatai · 2026-07-24
- Microsoft launches MAI-Voice-2-Flash, saying it is 2x faster and 32% cheaper — mustafasuleyman · 2026-07-24
- Zo-built app remixes any uploaded file into music through Instagram — henloitsjoyce · 2026-07-24
- IMG2THREEJS turns one reference image into a procedural Three.js model — SysPsych · 2026-07-24
- ChatGPT 5.6 Sol powers an interactive 3D Mediterranean world built with Three.js — techartist_ · 2026-07-24