Z-Image-Turbo is a highly efficient image generation model that ranks first among open-source text-to-image models worldwide in Artificial Analysis benchmarks. With only 6 billion parameters and 8 inference steps, it can generate photorealistic images comparable to large-scale commercial models. It also demonstrates outstanding performance in bilingual (Chinese and English) text rendering, complex semantic understanding, and diverse thematic generation.
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.
prompt*stringDescribe the content, style, and composition of the image. Supports English and Chinese, max 800 chars.
size?stringImage resolution in 'width*height' format. Total pixels must be within [512*512, 2048*2048]; [1024*1024, 1536*1536] is recommended for best quality. Default 1024*1536.
prompt_extend?booleanWhen enabled, an LLM intelligently rewrites and optimizes your prompt to improve results (slightly higher cost). Disabled by default.
seed?numberRandom seed, range [0, 2147483647]. The same prompt with the same seed yields similar results. Leave empty for random.
created?integerParameter description for Created
data?arrayParameter description for Data