Black Forest Labs’ Flux 3 is said to be a multimodal image, video, audio model
ZeroStateReflex · x · 2026-07-23
Black Forest Labs’ next model appears to be a multimodal Flux 3 system, not just a video generator.
- A briefly live placeholder page described it as “a breakthrough in control, realism, and world understanding” and said it would generate image, video, audio, and action.
- Early access users are already posting generations, but were apparently asked not to name the model.
- The standout rumor is 20-second video generation, which would put it ahead of much of the industry if true.
Related event: Black Forest Labs Launches FLUX 3: A Unified Multimodal Foundation Model(28 posts)→
More from Models
- GPT-6.1 Terra benchmarks: near-Astra scores at a fraction of the cost — testingcatalog · 2026-10-27
- OpenAI launches GPT-6.1 Terra: ~9x cheaper per task than Claude Opus 5.5 — testingcatalog · 2026-10-27
- GPT-6.1 Terra model card: 1.05M context, $1/$5 pricing, six effort tiers — TinfoilTricorn · 2026-10-27
- GPT-6.1 Terra cuts factual error rate from 22.3% to 4.3%, an ~81% drop — haider1 · 2026-10-27
- GPT-6.1 Terra lands: early users praise speed, value and subagent performance — BenBajarin · 2026-10-27
- Leaked GPT-6.1 Terra benchmarks: cheap but 'boring', still far behind Astra and Claude — Angaisb_ · 2026-10-27