Alibaba Ships Qwen-Image-2.1: 7B DiT With Native 2048x2048 and RGBA, Drops Apache for Research-Only License

Alibaba's Qwen team pushed Qwen-Image-2.1 to Hugging Face and ModelScope today, pairing a 7B, 32-layer single-stream DiT with a Qwen3-VL 8B text encoder and a 64-channel RGBA VAE that outputs native 2048x2048 at 40 steps. The release ships two 9B PE-T2I/PE-I2I prompt-rewriter checkpoints, supports up to 10 reference images and mask/circle-based local edits, and switches licensing from Apache 2.0 on the earlier Qwen-Image line to a non-commercial Qwen Research License Agreement — commercial users now need a separate agreement.