The full-featured Qwen-Image-2.0 series models integrate image generation and image editing, offering enhanced text rendering with support for 1,000-token prompts, more refined realistic textures, detailed depiction of photorealistic scenes, and stronger semantic adherence. The full-featured version delivers the strongest text rendering and most lifelike textures in the 2.0 series. This version is functionally equivalent to snapshot qwen-image-2.0-pro-2026-03-03.
Generate image
All API requests must be authenticated using a Bearer token in the Authorization header. Please ensure your API key is active.Authorization: Bearer sk-xxxxxx
These parameters come from the selected model form_schema. Switching models updates this list and the request example.
Choose the generation mode. Text to Image: generate from a prompt only. Image to Image: upload 1-3 reference images to edit, swap backgrounds, fuse multiple images, or composite. Qwen-Image-2.0 unifies both capabilities.
images*array[Image to Image] At least one as the base, up to 3 images. Supports jpg, png, webp, max 10MB each.
prompt*stringnegative_prompt?stringDescribe elements you do not want in the image, up to 500 characters. Optional.
size*stringSets output resolution; both width and height fall within 512-2048, with native 2K support. 'auto' follows the input image (image-to-image) or uses the default 2048*2048 (text-to-image).
prompt_extend?booleanWhen enabled, the model will automatically polish and enrich the prompt. On by default.
n*numberNumber of images to output, 1-6 supported.
created?integerParameter description for Created
data?arrayParameter description for Data