Black Forest Labs Unveils FLUX 3, A New Multimodal Frontier Model For Visual Intelligence | The Manila Times

Black Forest Labs has announced the release of FLUX 3, a multimodal frontier model designed to process and generate content across images, video, and audio. The company describes the model as using a unified architecture to learn jointly from these modalities. The announcement was made via a press release.

According to the release, FLUX 3 represents a significant step in visual intelligence AI. The model is intended to handle tasks that require understanding of multiple media types simultaneously. No specific performance metrics or benchmarks were provided in the announcement.

The unveiling comes amid a growing number of multimodal AI models from various companies. Black Forest Labs did not disclose availability, pricing, or safety measures associated with FLUX 3. The model joins a competitive landscape increasingly focused on combining multiple forms of data into single AI systems.