Originally released by Qwen on Hugging Face. All credit goes to the Qwen team.

Qwen Image 2.1 combines text-to-image generation and image editing in a single model. Its visual generation component has 7 billion parameters across 32 single-stream DiT layers, balancing image quality, efficiency and versatility.

The release introduces four main improvements:

• Efficient architecture: Mixed-granularity attention and reuse of cached prefixes reduce computation while maintaining image quality.
• Generation and editing with transparency: Create regular or transparent RGBA images, edit transparent layers and isolate subjects from photographs.
• Flexible editing: Work with up to ten reference images, guide local changes using circles, painted annotations or separate masks, and preserve the identity of people and products.
• Improved visual detail: Refined typography, portrait lighting, realistic textures and finer details.

Released under the Qwen Research License Agreement. See the original model card for examples and usage instructions.