Black Forest Labs teases FLUX.3 as an open-weights multimodal backbone
multimodalart · x · 2026-07-24
Black Forest Labs’ FLUX.3 [dev] is teased as an open-weights multimodal backbone for content creation and action prediction.
According to the post and the accompanying slide, the model is positioned for image, video, audio, and robotic action prediction, with the author highlighting the self-flow architecture as a notable evolution of flow matching. The message is that BFL is continuing to innovate at the architecture level, not just by scaling model size.
Related event: Black Forest Labs Teases Multimodal FLUX.3 Model(3 posts)→
More from Multimodal
- Andrew Dai says visual reasoning is as fundamental to AGI as language — AndrewDai · 2026-07-24
- ComfyUI save-node plugin adds gallery, review triage, and workflow recovery — shootthesound · 2026-07-24
- Seedance 2.0 appears inside CapCut in a polished motion-art demo — bennash · 2026-07-24
- Midjourney’s `--draft --sref random` can produce 24 style directions for one job — ciguleva · 2026-07-24
- Debunked: Viral FLUX 3 Trailer is AI-Generated, Not an Official Release — gandamu_ml · 2026-07-24
- A ComfyUI node now auto-uploads generations to a shareable moodboard — massivebacon · 2026-07-24