Image Generation
submitted),随后通过 任务结果查询 GET /v1/tasks/{task_id} 轮询获取生成结果。
调用示例
image_urls 传入参考图(URL 或 base64,最多 14 张)即切换为图生图模式:
响应示例
data.id 后,请轮询 GET /v1/tasks/{task_id} 获取生成结果,建议间隔 2-5 秒。加群 & 客服


Authorizations
Use the API key created at https://coder.visioncoder.cn/key as the Bearer token. Anthropic clients can pass the same key via the x-api-key header.
Body
OpenAI Images-compatible generation request. The task runs asynchronously: this endpoint returns a task ID, and the result is fetched via GET /v1/tasks/{task_id}.
Image model ID, e.g. gpt-image-2. Call GET /v1/models for the live list.
"gpt-image-2"
Text description of the image to generate. Chinese and English are both supported.
"一只戴着宇航员头盔的橘猫,赛博朋克风格"
Number of images to generate (1-10).
1 <= x <= 10Aspect ratio such as 1:1, 16:9, auto; pixel sizes like 1024x1024 are also accepted.
"1:1"
Output resolution tier.
1k, 2k, 4k Reference images (URL or base64). Providing this switches to image-to-image mode; up to 14 images.
14