Home
Black Forest Labs Unveils Flux3: First Native Multimodal Model for 20-Second Audio-Visual Generation
Black Forest Labs, a German AI startup, has launched Flux3, a multimodal foundation model built on the Self-Flow architecture. It integrates dedicated codecs for image, video, audio, and motion, enabling a unified understanding and generation of both physical and digital environments.
Flux3’s standout feature is native audio-video synchronization. As the first multimodal model to support direct audio generation, it produces synchronized clips up to 20 seconds long. The model handles text-to-image, image-to-video, keyframe-based transitions, and multi-character dialogue, merging visual and auditory capabilities into a single base.

Early benchmarks show Flux3 outperforming competitors. At 720p resolution with 10-second clips, it achieved a 93% win rate against Luma Ray3.2 and a 77% advantage over Runway Gen-4.5, while maintaining a slight edge over top-tier models like Seedance2.0 and Gemini Omni Flash.
Black Forest Labs has also extended these capabilities to robotics through Flux-mimic, developed in collaboration with Mimic Robotics. Currently undergoing production tests at an Audi factory, this model demonstrates the shift of multimodal AI from screens to industrial applications. Regarding availability, Flux3Video is already live, with Flux3Image and the open-source "Flux3Dev" weights scheduled for release soon.
Related article
WeChat Unveils 1 Billion Token AI Image Generation Quota, Free for Users
Tencent Cloud Development has unveiled a major update today, significantly accelerating the WeChat AI Mini Program Growth Plan. To ensure developers' innovative ideas are never constrained by computing limits, Tencent is providing up to 1 billion tok
Microsoft Confirms Win11 2026 Update: Taskbar Returns, AI Activates Digital Detox
After years of system bloat and controversial reputation, Microsoft has finally decided to perform a "major surgery" on Windows 11. Pavan Davuluri, head of Microsoft Windows, recently confirmed that a series of core improvements aimed at enhancing sp
Google Launches Gemini Enterprise Legal Tools for Law Firms
On Tuesday, Google broadened its Gemini Enterprise platform by introducing Gemini Enterprise for Legal, a dedicated solution for attorneys and law firms, marking a significant escalation in the race among major tech companies to capture AI-driven dem
Related Special Topic Recommendations
Comments (0)
0/500
Black Forest Labs, a German AI startup, has launched Flux3, a multimodal foundation model built on the Self-Flow architecture. It integrates dedicated codecs for image, video, audio, and motion, enabling a unified understanding and generation of both physical and digital environments.
Flux3’s standout feature is native audio-video synchronization. As the first multimodal model to support direct audio generation, it produces synchronized clips up to 20 seconds long. The model handles text-to-image, image-to-video, keyframe-based transitions, and multi-character dialogue, merging visual and auditory capabilities into a single base.

Early benchmarks show Flux3 outperforming competitors. At 720p resolution with 10-second clips, it achieved a 93% win rate against Luma Ray3.2 and a 77% advantage over Runway Gen-4.5, while maintaining a slight edge over top-tier models like Seedance2.0 and Gemini Omni Flash.
Black Forest Labs has also extended these capabilities to robotics through Flux-mimic, developed in collaboration with Mimic Robotics. Currently undergoing production tests at an Audi factory, this model demonstrates the shift of multimodal AI from screens to industrial applications. Regarding availability, Flux3Video is already live, with Flux3Image and the open-source "Flux3Dev" weights scheduled for release soon.
WeChat Unveils 1 Billion Token AI Image Generation Quota, Free for Users
Tencent Cloud Development has unveiled a major update today, significantly accelerating the WeChat AI Mini Program Growth Plan. To ensure developers' innovative ideas are never constrained by computing limits, Tencent is providing up to 1 billion tok
Microsoft Confirms Win11 2026 Update: Taskbar Returns, AI Activates Digital Detox
After years of system bloat and controversial reputation, Microsoft has finally decided to perform a "major surgery" on Windows 11. Pavan Davuluri, head of Microsoft Windows, recently confirmed that a series of core improvements aimed at enhancing sp
Google Launches Gemini Enterprise Legal Tools for Law Firms
On Tuesday, Google broadened its Gemini Enterprise platform by introducing Gemini Enterprise for Legal, a dedicated solution for attorneys and law firms, marking a significant escalation in the race among major tech companies to capture AI-driven dem











