Qwen/Qwen-Image-2.1

Unified text-to-image and image-conditioned generation. A 7.1B single-stream DiT with block-causal attention and an exact cross-step prefix KV cache, paired with a Qwen3-VL-8B text encoder and a 16x RGBA autoencoder.

One 7.1B DiT serves both text-to-image and editing; the prefix KV cache turns the text and reference-image portion of the sequence into a one-time cost instead of a per-step one

View on HuggingFaceView on ModelScope