FLUX announced today that it has reached a strategic cooperation with NVIDIA. The two parties will carry out in-depth technical cooperation in the field of AI image generation. The core highlights of this cooperation include performance optimization, memory efficiency improvement and innovative 3D creation workflow.
In terms of hardware adaptation, the FLUX model is fully optimized for the newly released GeForce RTX50 series graphics cards. Its development version FLUX.1 relies on the FP4 computing technology of NVIDIA Blackwell architecture to achieve a significant breakthrough on the RTX5090: it only needs 10GB of video memory to achieve twice the computing speed of the RTX4090, greatly improving the image generation efficiency.
Comparison of BF16 (left) and FP4 (right) of FLUX.1[dev]
What is even more eye-catching is the "NVIDIA AI Blueprint" workflow jointly launched by both parties, which has brought revolutionary changes to 3D creation. Creators can directly complete scene layout, including object placement and light settings, in 3D software such as Blender, and then convert the 3D scene into high-quality images through FLUX NIM microservices. This innovation greatly simplifies the creative process and makes 3D guided AI image generation more intuitive and efficient.
To ensure the wide application of technology, FLUX plans to release related products on multiple platforms in early February: the optimized FP4 format model will be launched on Hugging Face; FLUX NIM service will be provided through ComfyUI and ai.nvidia.com; support one-click installation The NVIDIA AI Blueprint workflow will be available on GitHub.
This cooperation marks a new stage in AI image generation technology, which not only improves creation efficiency, but also opens up new avenues for 3D art creation and will bring a revolutionary work experience to creators around the world.
Official introduction: https://blackforestlabs.ai/flux-nvidia-blackwell/
AI courses are suitable for people who are interested in artificial intelligence technology, including but not limited to students, engineers, data scientists, developers, and professionals in AI technology.
The course content ranges from basic to advanced. Beginners can choose basic courses and gradually go into more complex algorithms and applications.
Learning AI requires a certain mathematical foundation (such as linear algebra, probability theory, calculus, etc.), as well as programming knowledge (Python is the most commonly used programming language).
You will learn the core concepts and technologies in the fields of natural language processing, computer vision, data analysis, and master the use of AI tools and frameworks for practical development.
You can work as a data scientist, machine learning engineer, AI researcher, or apply AI technology to innovate in all walks of life.