QwenLM/Qwen-Image-2.1

We are excited to open-source Qwen-Image-2.1, a unified text-to-image generation and image editing model in the Qwen family. With just 7B parameters in its visual generation component (32 Single-Stream DiT layers), Qwen-Image-2.1 balances generation quality, inference efficiency, and versatility. Four key improvements define this release: Qwen-Image-2.1 supports up to 10 reference images for multi-subject composition: The model natively generates transparent images. For best results, use the recommended prompt format: Qwen-Image-2.1 natively supports 2K resolution. Recommended sizes: For best results, we recommend using the official prompt rewriting models to expand short prompts into detailed, high-quality descriptions. Two fine-tuned Qwen3.5-VL 9B checkpoints are provided — one for text-to-image, one for image editing — sharing a unified codebase that auto-detects the mode from input. The rewriting code and weights are available at: Output: Input format (JSONL): Output: For GPUs with limited memory, use model offloading: The transformer automatically caches the text and condition-image…