Black Forest Labs Unveils FLUX 3 Multimodal Model with Native Audio Video Generation
Black Forest Labs officially released FLUX 3, a unified multimodal model trained on image, video, and audio. Its core highlight is the ability to generate up to 20-second HD videos with synchronized native audio in a single request, marking a significant step toward building a true 'world model'. The model is now in early access, with API and web interface available.
Confirmed
- FLUX 3 supports text-to-video, image-to-video (with first/last frame or multi-keyframe control), video continuation, and multilingual dialogue.
- Video generation offers 720p and 1080p resolutions, up to 20 seconds per clip, with native audio (including sound effects and ambient sound), plus a low-cost Draft mode.
- The model uses a unified architecture trained jointly, enabling scene and camera angle changes within a single generation; reference-image-based variants are planned.
- FLUX 3 is now publicly available via API and on Runware and Magnific, offering integrated generation and upscaling workflows.
- The web interface is live; users can purchase credits to generate videos. Currently only video generation is available; other features like image generation will follow.
- The model is available on Cloudflare AI Gateway, supporting text-to-video, image-to-video, and video-to-video continuation.
- The company announced that model weights will be open-sourced soon; API access is already open to partners like Replicate, Krea, and Fal.
Unconfirmed
- The exact timeline for open-sourcing weights has not been announced.
- Details on model parameter size and training data have not been disclosed.
Why it matters
- The company argues that a single modality only captures a projection of reality, while multimodal joint learning can better understand the underlying physics of the world through mutual constraints (e.g., sound matching impacts, motion following mass). FLUX 3's release is not just an improvement in video generation but a key attempt toward the technical vision of building a true 'world model'.
2026-08-04 ~ 2026-08-05 · 19 related posts
- Episode 1: Black Forest Labs Launches FLUX 3: A Unified Multimodal Foundation Model(2026-07-22, 28 posts)
- Episode 2: Black Forest Labs FLUX.3 Enters Early Testing, Pivoting to Omni-Modal Generation(2026-07-23, 11 posts)
- Episode 3: BFL Launches FLUX 3: A Unified Multimodal Model for Video and Robotics(2026-07-24, 12 posts)
- Episode 4: Black Forest Labs Rumored to Release FLUX 3(2026-07-26, 2 posts)
- Episode 5: Black Forest Labs Launches FLUX 3 with Native Audio Video Generation(2026-07-28, 2 posts)
- Episode 6: Black Forest Labs Unveils FLUX 3 Multimodal Model with Native Audio Video Generation(2026-08-04, 19 posts)
- Episode 7: Black Forest Labs' FLUX 3 Video Model Sparks Viral Sensation(2026-08-06, 3 posts)
- Episode 8: Flux 3 Launch Sparks Benchmarking Frenzy, Multi-Model Comparison Heats Up(2026-08-06, 10 posts)
- Episode 9: Together AI Launches FLUX 3 Serverless API(2026-08-07, 2 posts)
- Episode 10: Black Forest Labs Launches FLUX 3 Multimodal Model(2026-08-11, 2 posts)
- Episode 11: FLUX 3 Video Ranks Second Globally, Free Access for Limited Time(2026-08-12, 5 posts)
- Episode 12: Flux 3 Text-to-Video Tests Impress with Realism and Cinematography(2026-08-12, 2 posts)
- Episode 13: FLUX 3 Video Debuts at No.5 on Image-to-Video Arena(2026-08-13, 2 posts)
Primary sources
- Black Forest Labs Launches FLUX 3: A Unified Multimodal Model for Image, Video, and Audio — dl_weekly · 2026-08-04
- FLUX 3 Video Model Hits Runware API: Supports 1080p 20s Clips — aziz4ai · 2026-08-04
- [source] Black Forest Labs Launches FLUX 3 Video with Native Audio and 1080p — bfl_ai · 2026-08-05
- [source] Black Forest Labs Launches FLUX 3: Unified Multimodal Model for Image, Video, and Audio — bfl_ai · 2026-08-05
- Black Forest Labs Launches FLUX 3 Video Multimodal Model — robrombach · 2026-08-05
- FLUX 3 Video Breakdown: Focuses on Native Multimodal Alignment and Long Video Generation — robrombach · 2026-08-05
- [source] FLUX 3 Vision: Unified Architecture Learns Image, Video, and Audio to Build Real-World Models — robrombach · 2026-08-05
- Black Forest Labs' FLUX 3 Video Hits Magnific with Full Generation & Upscaling Pipelines — LudovicCreator · 2026-08-05
- FLUX 3 Video Generation Goes Live, Available on Web for All Users — mark_k · 2026-08-05
- Runway Launches FLUX 3: Generate and Edit Up to 20-Second Videos with Audio — aziz4ai · 2026-08-05
- Flux 3 Video Model Coming Soon: API Now Available Across Platforms — Lucaspittol · 2026-08-05
- Flux 3 Video Open Weights Coming Soon, API Available to All Now — Lucaspittol · 2026-08-05
- Black Forest Labs' FLUX 3 Video Model Now Available on Cloudflare AI Gateway — craigsdennis · 2026-08-05
- BFL Releases FLUX 3 Video Model, Open Weights Confirmed — cloneofsimo · 2026-08-05
5 near-duplicate retellings: pess_r · iamrobotbear · aziz4ai · iamaliveix · MicahBerkley