| 提示词 | string | 描述所需变换的文本指令。最多 20,000 个字符。 | Change only the beverage bottle in the center to a matte black can labeled "PEAK", keeping the exact same lighting, shadows, reflective surface, background props, and camera angle. Do not change anything else in the scene. |
| 图像 URL | array | Upload or provide 输入图像s to transform. 最多 16 images supported. | https://d3adwkbyhxyrtq.cloudfront.net/webassets/videomodels/gpt-image-2-image-to-image-in.jpg |
| 画面比例 | 枚举(16 个选项) | Output aspect ratio. 'auto' lets the model choose the best frame. | auto |
| 分辨率 | 枚举(3 个选项) | Output size tier. Higher tiers take longer and cost more. | 1K |
| Background | 枚举(3 个选项) | Background handling. Only applies at 1K resolution. | auto |
| 输出格式 | 枚举(4 个选项) | Output image format. GIF costs the same as a still image. | png |
| Frame Count | 枚举(7 个选项) | Number of GIF frames. Only used when output_format is gif. | auto |
| Frame Duration (ms) | integer | Duration of each GIF frame in ms (20-2000). Only used when output_format is gif. | - |