Skip to content

Black Forest Labs News: Latest Releases & Events

Black Forest Labs now offers FLUX 3 Image Klein, an open-weight 5.6-billion-parameter model from October 2026 that runs on one consumer GPU, claiming frontier-model quality. It followed the flagship FLUX 3 Image in early October 2026, adding 4K output and multi-turn editing. Before that came FLUX.2 [klein] for sub-second generation in January 2026 and the FLUX.2 series in November 2025.

All 4 Black Forest Labs entries of the AI News timeline, newest first.

2026

October 2026

2026-10-15

  • Black Forest Labs releases open-weight FLUX 3 Image Klein
    Black Forest Labs announced FLUX 3 Image Klein, an open-weights image generation model with 5.6 billion parameters that runs on a single consumer GPU while claiming frontier-model quality. The model supports native 4K output, bounding box controls, and pixel-perfect editing. (x.com)

2026-10-01

  • Black Forest Labs launches FLUX 3 Image
    Black Forest Labs announced FLUX 3 Image, a new image generation model featuring pixel-precise multi-turn editing, bounding-box layout control, generation at up to 4K resolution, and composition using up to 10 reference images. The release positions BFL's flagship model for commercial-grade workflows demanding fine-grained control and detail preservation. (x.com)

January 2026

2026-01-15

  • Black Forest Labs releases FLUX.2 [klein] models
    Black Forest Labs released the FLUX.2 [klein] model family, designed for sub-second image generation and editing within a unified architecture optimized for consumer hardware. The release aims to advance interactive visual intelligence, offering real-time performance for AI agents and creators. (bfl.ai)

2025

November 2025

2025-11-25

  • Black Forest Labs releases FLUX.2 image models optimized for NVIDIA RTX GPUs
    Black Forest Labs unveiled the FLUX.2 series of cutting-edge image generators, boasting photorealistic details, pose control, and multi-reference consistency. NVIDIA teamed up for RTX GPU tweaks via FP8 quantization, trimming VRAM use by 40% to make high-fidelity AI art more accessible on consumer hardware. (blogs.nvidia.com)
    Nvidia