{"slug": "flux-3-black-forest-labs-launches-one-model-for-video-image-and-robots", "title": "FLUX 3: Black Forest Labs Launches One Model for Video, Image, and Robots", "summary": "Black Forest Labs (BFL) launched FLUX 3 on July 23, a single model that generates synchronized video and audio, edits images, and controls robot arms on Audi production lines, all from one training run. The model, built on a Self-Flow architecture that trains across images, video, audio, and physical actions simultaneously, reduces robot training data requirements by 60x, with FLUX-mimic fine-tuning for new manipulation tasks requiring only 30 minutes of demonstration data versus 30-plus hours previously. FLUX 3 Video is available in early access by application, while the image component has not yet shipped and an open-weight version is planned for 2026.", "body_md": "Black Forest Labs — the Freiburg team that built Stable Diffusion and FLUX.1 — shipped **FLUX 3** on July 23. It generates synchronized video and audio from a text prompt. It edits images. And it currently controls robot arms on Audi production lines. All from one model, one training run, one set of weights. This is not a video generator with image editing bolted on afterward. It is a fundamentally different thesis about what a generative model is.\n\n## One Architecture, Not Three Stitched Together\n\nThe key decision BFL made with FLUX 3 is training across all modalities simultaneously, not sequentially. The underlying approach is called Self-Flow. The reasoning: images, video, audio, and physical actions are all “projections” of the same underlying physical reality. Train on all four at once and the model builds a richer representation of how the world actually works — how objects hold shape, how things move, how events sound, how forces cause effects.\n\nMore than 95% of training compute went to video prediction. That is where the hardest world-modeling happens. The implication for developers building on top of this: one API, one fine-tuning run, and learned representations that transfer across image editing, video generation, audio, and robot control. Fewer vendors, less stitching.\n\n## Robots at Audi, Running Today\n\nThe most concrete demonstration of BFL’s thesis is **FLUX-mimic**, developed with mimic robotics. FLUX-mimic layers a lightweight action decoder on top of FLUX 3’s video prediction path. The logic: the same world-model that makes video look physically realistic — contact dynamics, object weight, cause and effect — already encodes much of what a robot arm needs to know to act.\n\nFLUX-mimic is running dexterous manipulation tasks on Audi production lines right now. Fine-tuning the model for a new manipulation task takes about 30 minutes of robot demonstration data. Prior approaches required 30-plus hours — a 60x reduction in training data requirements. That is a meaningful validation of the core architectural bet: the world-model learned during video training transfers to physical control.\n\n## What Is Actually Available Today\n\nFLUX 3 launched with gated access, and the distinction matters:\n\n**FLUX 3 Video:** Early access, by application at[bfl.ai](https://bfl.ai/blog/flux-3). Generates clips up to 20 seconds with native audio in one pass.**FLUX 3 Action (FLUX-mimic):** Early access to selected robotics and commercial partners only.**FLUX 3 Image:** Not yet released. Coming in the next few weeks.**FLUX 3 Dev:** An open-weight version planned for later in 2026.**Pricing:** Not yet announced.\n\nIf you are a current FLUX.1 or FLUX.2 user waiting to upgrade your image pipeline, you are not there yet. The image component — what most people use FLUX for — has not shipped. FLUX 3 Video is real, but gated. The practical window for most developers opens when FLUX 3 Image arrives.\n\n## On the Benchmarks\n\nBFL published preference benchmarks showing FLUX 3 Video preferred over Seedance 2.0 and Gemini Omni Flash in 52% of head-to-head comparisons, and over Kling v3 Pro in 60%. A few things to note: these are BFL’s own preliminary numbers on a pre-release model candidate. A 52% win rate is within statistical noise — effectively tied with Seedance and Gemini Omni Flash. Seedance 2.5 and Gemini Omni Flash are already production-ready and widely accessible. FLUX 3 is not, yet.\n\nThe benchmarks are directional, not definitive. The interesting claim is not “it beats Kling” — it is the architecture thesis: one model that learns physics well enough to generate convincing video *and* guide a robot arm. [Latent Space’s technical breakdown](https://www.latent.space/p/ainews-black-forest-labs-flux-3-multimodal) and [VentureBeat’s coverage](https://venturebeat.com/technology/black-forest-labs-launches-flux-3-capable-of-generating-images-and-20-second-video-with-audio-but-in-limited-release-to-start/) both flag the limited release context.\n\n## What to Watch\n\nTwo releases matter for developers not in robotics. First, FLUX 3 Image in the coming weeks — that is when the creative tooling and developer ecosystem built on FLUX.1 can actually start evaluating an upgrade. Second, [FLUX 3 Dev](https://bfl.ai/blog/flux-3) later in 2026, the open-weight release. BFL has a strong track record: FLUX.1 models accumulated roughly 500 million downloads combined across the FLUX and Stable Diffusion era.\n\nThe broader claim — that a single architecture trained on the physical world can serve creative professionals and factory robots equally well — is either BFL’s most ambitious idea or its most important one. The [Audi deployment](https://bfl.ai/blog/flux-3-mimic) suggests it might be both.", "url": "https://wpnews.pro/news/flux-3-black-forest-labs-launches-one-model-for-video-image-and-robots", "canonical_source": "https://byteiota.com/flux-3-black-forest-labs-multimodal/", "published_at": "2026-07-26 00:10:56+00:00", "updated_at": "2026-07-26 00:31:18.287404+00:00", "lang": "en", "topics": ["artificial-intelligence", "generative-ai", "robotics", "ai-products", "ai-research"], "entities": ["Black Forest Labs", "FLUX 3", "FLUX-mimic", "mimic robotics", "Audi", "Seedance 2.0", "Gemini Omni Flash", "Kling v3 Pro"], "alternates": {"html": "https://wpnews.pro/news/flux-3-black-forest-labs-launches-one-model-for-video-image-and-robots", "markdown": "https://wpnews.pro/news/flux-3-black-forest-labs-launches-one-model-for-video-image-and-robots.md", "text": "https://wpnews.pro/news/flux-3-black-forest-labs-launches-one-model-for-video-image-and-robots.txt", "jsonld": "https://wpnews.pro/news/flux-3-black-forest-labs-launches-one-model-for-video-image-and-robots.jsonld"}}