Black Forest Labs Launches FLUX 3: A Unified Multimodal Model for Image, Video, and Audio
dl_weekly · x · 2026-08-04
Black Forest Labs announced that its latest multimodal foundation model, FLUX 3, is now available in Early Access. The model uses a unified architecture to jointly train on images, videos, and audio.
The company stated that this joint learning approach allows the model to better understand the underlying rules of the physical world, such as the causal relationship between object motion and sound. Currently, FLUX 3 can generate 20-second video clips with native audio and shows potential to expand into physical AI applications like robotic action prediction.
More from Models
- Google's "Paid Pro" paywall in Antigravity angers Pixel buyers and bundle subscribers — Chance-Okra-5920 · 2026-10-16
- GLM 5.3 Flash is now free in OpenCode coding tool — DanielLockyer · 2026-10-16
- GPT-6 Sol runs a potion shop flawlessly but its reasoning mistakes stock for its own stats — liminal_bardo · 2026-10-16
- Codex convert says Claude app is 2-3x better optimized with a far smoother UI — ItchyResearcher5671 · 2026-10-16
- willcb: Opus 5.5 doesn't smell bigger, it smells like they fixed the data — willcb · 2026-10-16
- In defense of Mistral: trillion-parameter ML4 MoE nears top open-weight models mid-training — blakesnake86 · 2026-10-16