Qwen-Image

Qwen-Image is an open-source image generation and editing model you can deploy locally. It's for developers and creators who want to generate images from text or revise existing pictures on their own hardware. Its text rendering capabilities, especially for Chinese, make it relevant for images that need readable lettering alongside visual content.

The model supports realistic human depictions, detailed faces and textures. Its editing models accept single or multiple input images and can preserve a person's identity and visual traits while changing the scene. They can also combine separate portraits into a group picture while maintaining consistency across the people. Selected community-created LoRA effects are built into the editing model, including lighting control that doesn't require extra tuning.

Local deployment includes a multi-GPU API server and a Gradio browser interface. The server supports parallel processing across GPUs, queues for concurrent requests and multiple image aspect ratios. This gives teams a way to serve the model on their own infrastructure as well as use it for individual image work.

Qwen-Image uses the Apache 2.0 license and works with Hugging Face Diffusers. Optional prompt enhancement uses hosted Qwen-Plus for text-to-image prompts and Qwen-VL-Max for editing prompts; that optional step uses remote services. Prompt rewriting can improve editing stability; editing results may be unstable without it.