Black Forest Labs

Introducing FLUX.2 [klein]. Blazing fast. Beautiful. Generate stunning images in under a second while maintaining exceptional quality. Great for fast editing, changing styles, and developing ideas from 0 → 1. Available via API, or run it locally - Klein 4B under Apache 2.0, Klein 9B as open weights. Try it for free in our demo app (link in the thread).

Full article here: nvidianews.nvidia.com/news/nvidia-la…

We announced at @NVIDIAGTC that we're joining @nvidia's Nemotron Coalition to advance open frontier models. At BFL, we develop multimodal generative models for visual intelligence, ranging from images to real-time video and action prediction models. We've always been convinced that open models help drive frontier capabilities. We're focused on building the next state-of-the-art open multimodal models in partnership with NVIDIA.

@huggingface space → huggingface.co/spaces/black-f…

Already on FLUX.2 [klein] 9B via API? Free upgrade, faster, same price. On [klein] 4B and want better quality? 9B is now closer in speed. Docs → #preview-endpoint" target="_blank" rel="nofollow noopener">docs.bfl.ai/flux_2/flux2_o… Weights → huggingface.co/black-forest-l… Try it → bfl.ai

FLUX.2 [klein] 9B just got 2x faster at image editing, especially when you use multiple reference images. Same quality, no price increase.

Fixed vision encoders like DINO have driven impressive progress in more learnable representations for generative modeling - but there is no universal variant across modalities, and they do not scale with the generative model. We introduce our self-supervised framework, Self-Flow, that builds learnability directly into flow models, working in a unified and scalable way across image, video and audio. Particularly excited about the gains on video-action prediction: Beyond the overall success rate improving substantially, more complex tasks - like "Open and Place" - see some of the clearest gains. So many interesting research questions to explore to make 🤖 go brrr Super glad to be working with my amazing colleagues @hila_chefer, Dominik, @dustin_podell, Vikash, @Vinh_Suhi, Antonio and @robrombach - as well as the whole @bfl_ml team! arxiv: arxiv.org/abs/2603.06507 project page: bfl.ai/research/self-…

New in @ComfyUI on RTX AI PCs: • Simplified App View • RTX Video Super Resolution node for 4K upscaling • @bfl_ml FLUX.2 Klein model variants in NVFP4 + FP8 • @ltx_model LTX-2.3 model variant in FP8 (NVFP4 coming soon)

You can read more here: bfl.ai/research/self-…

Self-Flow opens a path toward world models: combining visual scalability with semantic abstraction for planning and understanding. Here's action prediction from a 675M parameter model.

We present a research preview of Self-Flow: a scalable approach for training multi-modal generative models. Multi-modal generation requires end-to-end learning across modalities: image, video, audio, text - without being limited by external models for representation learning. Self-Flow addresses this with self-supervised flow matching that scales efficiently across modalities. Results: • Up to 2.8x faster convergence across modalities. • Improved temporal consistency in video • Sharper text rendering and typography This is foundational research for our path towards multimodal visual intelligence.

View the docs here: #preview-endpoint" target="_blank" rel="nofollow noopener">docs.bfl.ai/flux_2/flux2_o…

Try it at bfl.ai/play

Faster generation lets you explore more design ideas. FLUX.2 [pro], our most heavily used model, is now 2x faster with no loss in quality and no price increase. More examples in the thread 🧵