Together AI has launched FLUX 3, a new multimodal model developed by bfl_ai. FLUX 3 is capable of generating video with synchronized audio, supporting up to 20-second clips, multiple scenes, and control via text, images, or keyframes. The model also offers features like multilingual dialogue with lip-sync and effects, as well as advanced control over video generation. Together AI is offering this model through its Serverless Inference service, providing a managed production path for developers integrating FLUX 3 into creative products and media workflows. AI
IMPACT Enables creation of complex video content with synchronized audio and advanced controls, potentially accelerating automated media workflows.
RANK_REASON Frontier-lab model release with system card.
Read on X — Together (inference / OSS) →
AI-generated summary · Google Gemini · from 3 sources. How we write summaries →
