| 1 | You are a cinematographer. You need to complete the shot annotations for a provided script. Please first read the script thoroughly. Then, based on your insights and the specific usage conditions for each type of shot, select the most suitable shots from [Complete List of Shots]. |
| 2 | |
| 3 | |
| 4 | ### [Provided Script]: |
| 5 | {script} |
| 6 | |
| 7 | |
| 8 | ### [Complete List of Shots]: |
| 9 | {all_shots} |
| 10 | |
| 11 | |
| 12 | ### [Shot Annotation Requirements]: |
| 13 | - Each scene should not have too many close shots and mid shots. |
| 14 | - Each shot used must meet its usage conditions. |
| 15 | - For the dialogue-starting scene, you should choose between [Track Shot, Long Shot] to set the context. |
| 16 | - If you want to use Zoom Shot, you must ensure the preceding shot is a Long Shot. |
| 17 | - If you want to use Pan Shot during dialogue, it should be used multiple times in a row. |
| 18 | |
| 19 | |
| 20 | ### [Shot Annotation Steps]: |
| 21 | - Step 1: Focus on the usage conditions of each shot in the [Complete List of Shots], then allocate them to the shot annotation points in the script according to different usage conditions. |
| 22 | - Step 2: Check if the shot annotations in Step 1 meet the [Shot Annotation Requirements]. If not, identify which requirements are not met, then update the shot annotations to meet these requirements. |
| 23 | |
| 24 | |
| 25 | Please support your decision with detailed logical reasoning. The "reasoning" field should include the complete two shot annotation steps mentioned above. |
| 26 | |
| 27 | Your response should only contain the following JSON content: |
| 28 | ```json |
| 29 | { |
| 30 | "scene 1": { |
| 31 | "selected-shot-1": {"reasoning": "...", "shot": "Name of shot"}, |
| 32 | "selected-shot-2": {"reasoning": "...", "shot": "Name of shot"}, |
| 33 | ... |
| 34 | }, |
| 35 | ... |
| 36 | } |
| 37 | ``` |