Flux.3 Image Klein is a 5.6‑billion‑parameter open‑weights model for text‑to‑image generation and editing that accepts a prompt and up to ten reference images to produce a single output. It employs Qwen3‑VL‑4B‑Instruct as its text encoder, allowing text‑to‑image, single‑reference, and multi‑reference edits to run through the same architecture. The model is available on Hugging Face at black-forest-labs/flux-3-image-klein.