FLUX 3 Image Klein in ComfyUI: 5.6B Open Weights

FLUX 3 Image Klein is a 5.6-billion-parameter open-weights image-generation model from Black Forest Labs that runs natively in ComfyUI and is offered in base and distilled versions for research, fine-tuning, or faster generation. It retains advanced controls from the larger FLUX 3 Image model, including native 4K generation, prompt expansion, multi-reference editing, bounding-box-based composition control, text rendering and editing, and reference-driven style transfer. Black Forest Labs reports that it outperforms Qwen-Image 2.1 in internal text-to-image and multi-reference evaluations, while INT8 ConvRot quantization combined with the distilled model can make 1024×1024 generation 4.3 to 9.3 times faster than a BF16 50-step baseline, with reported image times falling below nine seconds on RTX 5070 and RTX 4070 GPUs. Users can access it by updating ComfyUI or using Comfy Cloud, downloading the preferred weights from Hugging Face, loading the supplied template, and providing prompts or reference images.

Use this post, company, and trend context to find content marketing opportunities, perform competitive analysis, or address product feature gaps via the Plushcap MCP server or the Plushcap API.