Black Forest Labs launches FLUX 3 capable of generating images and 20-second video with audio — but in limited release to start

Black Forest Labs launched FLUX 3, a multimodal model that can generate images and up to 20-second audio-video clips from a single prompt. The company says the model is jointly trained across modalities and will ship through FLUX 3 Video, Image, Action, and an upcoming open source Dev version, though access is initially limited.

FLUX 3 reflects a broader push toward multimodal AI systems that combine creative generation, simulation, and agentic capabilities under one architecture. However, the lack of pricing, benchmarks, and service commitments makes it difficult for enterprise customers to assess readiness or compare it with rival frontier models.