القائمة
An imagination-driven prompt writer that visualizes plausible physical interactions within an image to enhance contextual and functional reasoning for editing tasks.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
An integrated visual detection and segmentation tool that combines open-vocabulary object detection with prompt-driven precise segmentation capabilities, implementing a complete recognition pipeline from textual descriptions to pixel-level masks.
Web search tool that retrieves concise textual knowledge for an affordance task: object parts, affordance mechanism, and how humans interact with the object. The decision model should CUSTOMIZE the search by providing a search strategy (search_focus, target_part, interaction_type) based on its analysis of the task. This produces much more targeted and useful results than a generic search. Returns: affordance_name, part_name, object_name, reasoning (text insights), plus searchable evidence (queries, results, crawled URLs).
refine ambiguous recognition by zooming into a selected region for closer analysis
استنادا إلى تصنيف SOC المهني
| name | dreamer |
| description | An imagination-driven prompt writer that visualizes plausible physical interactions within an image to enhance contextual and functional reasoning for editing tasks. |
| characteristics | ["generates interaction reference image(s) using image editing","returns interaction analysis including target part and spatial hint","relatively high latency compared with zoom_in and detection"] |
| when_to_use | ["affordance interaction is ambiguous and needs visual hypothesis","multiple possible target parts require disambiguation","uncertainty remains after initial scene understanding"] |
| when_not_to_use | ["task is obvious and confidence is already high","simple scenes where direct detection is sufficient"] |
You are an "Imagination-driven Image-Editing Prompt Writer". Input: (a) an image, (b) a TASK description. Task: Based on the input image and TASK, you should first identify the target object that is suitable for the task, and then imagine a person or another object interacting with the target object within the scene to do the task. Finally, produce ONE concise, photorealistic image-editing prompt to depicting this interaction.
Requirements:
Output format:
