Black Forest Labs Flux 3 Video
Black Forest Labs' multimodal video model: text, image, or video in, with synchronized audio, lip-sync, and a cheap draft mode.
Flux 3 Video is a cloud video-generation model built by Black Forest Labs. It produces short video clips from a text prompt, a starting image, or by interpolating between a first and last frame. It can also take reference video to guide the result. Clips run up to 20s at 4K with a synchronized audio track. It also supports reference images. It runs through Black Forest Labs, OpenRouter, Runware, and Replicate using your own API key, from about $0.15 per second of output.
- Released
- Jul 2026
- Pricing
- $0.15 per second
- Max resolution
- 4K
- Aspect ratios
- 21:9, 16:9, 4:3 +4 more
- Clip length
- Up to 20s
- Audio
- Synchronized track
- Image-to-video
- Start & end frame + reference images
- Text to video rank
- #3
Samples
Generated with Flux 3 Video via Replicate. The same two prompts run against every video model in the catalog (one landscape, one portrait), so the only thing that changes between two models’ clips is the model.
Camera motion, scene coherence over time
Fluid motion, fine detail, temporal stability
Black Forest Labs
Black Forest Labs makes the FLUX family of image models — state-of-the-art open-weight image generation.
blackforestlabs.ai ↗Professional-grade Flux model for photorealistic and artistic image synthesis.
Black Forest Labs' top-tier Flux 2 model — highest fidelity, strongest prompt adherence, and most stable multi-reference editing.
Black Forest Labs' image model on the FLUX 3 backbone: text-to-image, precise local edits, up to ten references, accurate typography, and native 4K output.
Black Forest Labs' smaller, faster FLUX 3 image model with open weights: text-to-image, image editing and multi-reference generation, with native 4K output.
Black Forest Labs' fast video editing model: rewrites a source clip from a text prompt, adding, removing or replacing objects and settings while keeping its length, aspect ratio and audio.
Black Forest Labs' video upscaler: enlarges a source clip by 1.5 to 3 times, either staying faithful to the footage or adding fine detail, with an optional prompt to steer it.