Black Forest Labs Launches FLUX 3 Video Multimodal Model
robrombach · x · 2026-08-05
Black Forest Labs has officially released FLUX 3 Video, its first video model. This powerful multimodal foundation model supports generating HD video clips up to 20 seconds long from text and images, alongside native audio. The team noted that future updates will include reference-based generation variants and open weights.
More from Multimodal
- Seedance 2.5 Hits CapCut: Generates Up to 30-Second Single Video Segments — AIwithGhotai · 2026-08-07
- Seedance 2.5 Launches Globally in CapCut, Integrating Video Generation and Editing — AIwithGhotai · 2026-08-07
- Chaining AI Models in fal Workflows to Generate a 15-Second Animated Short — gorkem · 2026-08-07
- Qwen-3D: Enhancing Spatial Reasoning via Multi-View Geometric Cues — udmrzn · 2026-08-07
- MiniMax H3 Test: Generates 15s T2V with Native Audio in 23 Minutes — AxonkaiLab · 2026-08-07
- Exploring Workflows for Using Claude to Assist Veo in Medical Animations — Hipposy · 2026-08-07