FLUX.3 [dev] is coming with open weights for image, video, audio, and robot action prediction
multimodalart · x · 2026-07-24
The post says FLUX.3 [dev] is coming with open weights and support for image, video, audio, and robotic action prediction.
It also points to the model’s self-flow architecture, described as a new evolution of flow matching. The author praises the team for pushing architectural innovation in addition to scale.
Related event: Black Forest Labs Launches FLUX 3: A Unified Multimodal Foundation Model(28 posts)→
More from Multimodal
- 3D ResNet Paper Crosses 3,000 Citations Eight Years After CVPR 2018 — HirokatuKataoka · 2026-09-11
- Non-coder builds full-featured Android ComfyUI client with ChatGPT, submits to Google Play — ComfierUI · 2026-09-11
- RunningHub open-sources H3Lightning, speeding up MiniMax H3 video generation 12x — 智东西 · 2026-09-11
- FastH3-Live hits 22fps: acceleration node benchmarks and the --vram-headroom trick — spartong945 · 2026-09-11
- Midjourney style code share: --sref 2912175708 — tisch_eins · 2026-09-11
- Astra storyboards plus Minimax H3 per-shot generation boost video success rates — Hailuo_AI · 2026-09-11