Mini toolsFLUX 3
Model family: FLUX
FLUX 3 is a multimodal foundation model built on Self-Flow, an approach for aligning multimodal generation and understanding within one architecture. Trained jointly across video, image, and audio, it forms a unified representation of how objects move, interact, and sound rather than learning each modality in isolation. FLUX 3 Video generates diverse videos with native audio up to 20 seconds from text prompts, starting images, reference video clips, or keyframes, and can chain multiple clips into longer multi-shot sequences with consistent characters. It supports multilingual dialogue and a broad range of visual styles and aspect ratios. Image synthesis and editing, along with action prediction for robotics through the FLUX-mimic collaboration, are being introduced through later early access phases of the same underlying model.
Overview
FLUX 3 is a multimodal foundation model from Black Forest Labs that jointly learns from images, video, and audio within one unified architecture. It generates and edits video with native synchronized audio up to 20 seconds, supports image and video conditioning, keyframe control, and multilingual dialogue, and produces a wide range of visual styles. Image synthesis and action-prediction capabilities are being rolled out in later early access phases.
About Black Forest Labs
Born from foundational research, we continually build state-of-the-art technology that advances how the world is seen and understood.
View Company Profile
Last updated: July 27, 2026
