Will DePue Praises FLUX 3: Amazing Video Generation and Post-Training

willdepue · x · 2026-07-24

Blogger Will DePue highly praised Black Forest Labs' new multi-modal model, FLUX 3.

He stated that the model's video generation looks incredibly good, showing amazing work especially on post-training. FLUX 3 is positioned as a multi-modal model with a unified architecture, supporting image, video, audio generation, and action prediction, with extensibility for robotics applications.

Related event: Black Forest Labs Unveils Omni-Modal FLUX 3(29 posts)→

Original post →

More from Multimodal

Multimodal channel →