FLUX 3 Image Klein ships with Diffusers support and layout control
What happened
At 08:00 on October 15, 2026, reports said Black Forest Labs released FLUX.3 Image Klein with same-day Diffusers support, offering text-to-image, multi-reference image generation and bounding-box layout control in one model. At 23:00 that day, follow-up coverage described it as a 5.6B-parameter open-weights image model supporting text-to-image, image editing and generation from up to 10 reference images. At 00:57 on October 16, The Decoder reported native 4K output, pixel-precise editing and bounding-box element placement; an INT8 build runs on NVIDIA GPUs with only 8 GB of VRAM and generates an image in under 9 seconds on an RTX 4070. The latest coverage adds output resolution, editing precision, VRAM requirements and generation speed.
Written by AI from the coverage · updated 4 minutes ago
Coverage
Follow the reports to see the story from different sides.
- The DecoderBlack Forest Labs' open-weights image model FLUX 3 Image Klein runs on consumer GPUs with just 8 GB of VRAM
Black Forest Labs 发布开放权重图像模型 FLUX 3 Image Klein，支持文生图、图像编辑及最多十张参考图生成。模型拥有 5.6-billion 参数，支持原生 4K 输出、像素级精确编辑和边界框元素定位；INT8 构建可在仅有 8 GB 显存的 NVIDIA GPU 上运行，在 RTX 4070 上生成一张图像耗时不到 9 秒。
- AI HOT · ModelsPickBlack Forest Labs releases FLUX 3 Image Klein, a 5.6B open-weight image model
Black Forest Labs released FLUX 3 Image Klein, a 5.6B open-weight model that handles text-to-image, image editing and multi-reference generation with up to 10 reference images. INT8 quantization lets it run on devices with as little as 8GB of VRAM, lowering the hardware bar for local image generation and editing.
- AI HOT · ProductsPickBlack Forest Labs FLUX.3 Image Klein lands in Diffusers with bounding-box layout control
Black Forest Labs released FLUX.3 Image Klein with same-day Diffusers support. One model handles text-to-image, multi-reference image generation and bounding-box layout control. Normalized bounding boxes set where generated regions go and where reference-image content moves, so layout instructions hold across different image sizes.
Heat over time
Not enough continuous observations to draw a trend yet.