Computer Vision
Oct 16, 2026
Release of FLUX 3 Image Klein Model for Text-to-Image Generation
Oct 16, 2026
AI Summary
FLUX 3 Image Klein, a 5.6 billion parameter model, has been launched for text-to-image generation and image editing, supporting up to 10 reference images. It is optimized for consumer GPUs, allowing local deployment and faster image generation, while also implementing safety measures to reduce harmful content exposure.
- FLUX 3 Image Klein is a 5.6 billion parameter model designed for text-to-image generation, image editing, and multi-reference generation with up to 10 reference images.
- The model features native 4K generation, pixel-perfect editing, and bounding boxes for precise control over image elements.
- It builds on insights from images, video, and audio to create realistic images, and includes a base model for fine-tuning and a distilled model for low-latency generation.
- In internal evaluations, it outperformed larger models in text-to-image generation and image editing, while being the smallest model in its comparison group.
- The model is optimized for consumer GPUs, requiring less memory and enabling local deployment, which is beneficial for teams with data sovereignty needs.
- It can generate a 1MP image in approximately 4 seconds on an NVIDIA GeForce RTX 5090 and under 9 seconds on an RTX 4070.
- The weights are available under the FLUX Kommunity License, allowing free commercial use for smaller organizations and offering self-hosted licensing for larger entities.
- Multiple safeguards have been implemented to mitigate misuse, including dataset filters and targeted fine-tuning to suppress harmful behaviors.
- FLUX 3 Image Klein is the second release in the FLUX 3 family, following FLUX 3 Action, with more releases planned in the future.
image processingvisual recognitionmachine learningcomputer graphics