| プロンプト | string | Text prompt describing the image to generate. Maximum 20,000 characters. | A girl doing livestream makeup tutorials while tiny workers inside her mirror physically repaint the reflection in real time, miniature ladders, paint buckets, glowing vanity lights, cluttered modern bedroom aesthetic, insanely detailed reflections, playful surreal realism, highly creative composition, luxury commercial quality. |
| アスペクト比 | Enum(16個の選択肢) | Output aspect ratio. 'auto' lets the model choose the best frame. | auto |
| 解像度 | Enum(3個の選択肢) | Output size tier. Higher tiers take longer and cost more. | 1K |
| Background | Enum(3個の選択肢) | Background handling. Only applies at 1K resolution. | auto |
| 出力形式 | Enum(4個の選択肢) | Output image format. GIF costs the same as a still image. | png |
| Frame Count | Enum(7個の選択肢) | 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. | - |