Wan2.6 Image, An all-round image generation model that supports joint text–image reasoning, multi-image creative fusion, commercial-grade consistency, aesthetic style transfer, and precise control of framing and lighting, significantly enhancing consistency, controllability, and expressiveness in image generation. https://bailian.console.alibabacloud.com/cn-beijing?tab=model#/model-market/detail/wan2.6-image?serviceSite=asia-pacific-china
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 text prompt only. Image to Image / Edit: upload 1-4 reference images for editing, style transfer or redraw. Only one mode at a time.
prompt*stringDescribe the image content or editing instructions. Supports Chinese and English, max 2,000 chars.
enable_interleave?booleanEnable for text-and-image interleaved output (multiple images); disable for standard image generation/editing. When on, the count is fixed at 1.
size?string1K ≈ 1280*1280 total pixels; 2K ≈ 2048*2048. In image modes the ratio follows the reference image. A width*height value is also accepted.
n?numberStandard mode supports 1-4; Interleaved mode is fixed at 1.
prompt_extend?booleanWhen enabled, AI intelligently rewrites the prompt to improve detail. Only affects standard image generation/editing mode. Enabled by default.
negative_prompt?stringDescribe what you do not want in the image. Supports Chinese and English, max 500 chars.
watermark?booleanWhen enabled, adds an 'AI-generated' watermark in the lower-right corner. Disabled by default.
seed?numberControls randomness, range [0, 2147483647]. Leave empty for random.
created?integerParameter description for Created
data?arrayParameter description for Data