Black Forest Labs Launches FLUX 3 Capable of Generating Images and 20-Second Videos
The new multimodal model FLUX 3 is now available in limited release.
1Launch of FLUX 3
Black Forest Labs has expanded its FLUX family with the announcement of FLUX 3, a new model capable of generating images, 20-second videos, and audio under a single architecture. The company refers to these capabilities as 'visual intelligence,' emphasizing perception, prediction, and action across physical and digital environments.
2Multimodal Capabilities
FLUX 3 is trained to generate images, video, and audio within a unified architecture, rather than combining separate models. This approach ensures more consistent and integrated outputs. The company highlights potential applications in creative generation, simulation, and robotics.
3Product Lines
FLUX 3 will be offered through four product lines: FLUX 3 Video, FLUX 3 Image, FLUX 3 Action, and the upcoming open-source FLUX 3 Dev. FLUX 3 Video and FLUX 3 Action are currently in an early access program, requiring approval for use. FLUX 3 Image is set to roll out in the coming weeks.
4Limited Availability
FLUX 3 is initially available in limited release, with no public API access yet. This strategy mirrors other leading AI labs. The company has promised faster and open-weight versions later this year.
5Pricing Uncertainty
BFL has not disclosed pricing or service-level commitments for FLUX 3, making it difficult for enterprise buyers to calculate total cost of ownership. Independent benchmarking data is also lacking.
6Lack of Open Source
FLUX 3 is launching without downloadable weights or an open-source license, disappointing developers accustomed to locally deployable FLUX variants. The company assures open-weight versions are coming.
7Comparative Testing
BFL claims FLUX 3 outperforms competitors in early tests, with 93% preference over Luma Ray 3.2 and 77% over Runway Gen-4.5. However, these results are preliminary and may not reflect the final model's performance.
8Competition with Google Gemini Omni
FLUX 3 ties with Google's Gemini Omni Flash at 52% in quality comparisons. Omni is generally available at $0.10 per second for 720p video, but has editing restrictions in Europe, potentially giving FLUX 3 an edge.
9Opportunity in the European Market
As a Germany-based company, BFL may have an advantage in Europe, where Google Omni faces restrictions on editing uploaded videos. This could make FLUX 3 more appealing to European enterprises.
10Enterprise Guide
FLUX 3 Video supports single generations up to 20 seconds, but resolution and pricing details remain undisclosed. Competitors like HappyHorse 1.1 offer 15-second 1080p clips, leaving questions about FLUX 3's competitive positioning.
11Future Commitments
BFL promises FLUX 3 Dev will provide open-weight access to a multimodal backbone for content creation and action prediction, a significant expansion over previous FLUX releases. However, developers will need to wait for this version.
12Conclusion and Significance
FLUX 3 represents a potential leap in multimodal AI, but limited availability and missing details may slow enterprise adoption. Open-source availability and pricing transparency will be critical to its success.