FLUX 3
A multimodal generative model for images, video, and native audio
About FLUX 3
FLUX 3 is a multimodal foundation model introduced by Black Forest Labs that jointly learns images, video, and audio in a unified architecture and rolls out related capabilities in phases. The page lists text-to-video generation, image-to-video animation, video-to-video reference transfer, generative video-audio continuation, and keyframe-to-video control; video output can include native audio and be up to 20 seconds long. The user groups listed on the page include creators, marketers, designers, and robotics teams.
Best for
Best use cases
Text-to-video generation
Image-to-video animation
Video-to-video reference transfer
Keyframe-to-video control
Features
Text- and image-driven video
Supports text-to-video generation and image-to-video animation.
Video reference transfer
Supports video-to-video reference transfer.
Native audio generation
Supports video generation with synchronized native audio.
Keyframe control
Supports keyframe-to-video control.
Pros
- Unified architecture jointly learns images, video, and audio
- Videos can be generated with synchronized native audio
Cons
- Video duration is up to 20 seconds
Pricing Plans
Basic
- For individuals and enthusiasts
Basic
- For individuals and enthusiasts
Plus
- For creators and professionals
Plus
- For creators and professionals
* Pricing information is for reference only. Please refer to the latest announcement on FLUX 3's official website.