Start from a Vague Request: Use Semantic Search to Find Deliverable Material
Turn an unclear image request into subject, scene, color, and use-case terms, run semantic searches, narrow with scope and filters, collect candidates, and export deliverables.
Turn an unclear image request into subject, scene, color, and use-case terms, run semantic searches, narrow with scope and filters, collect candidates, and export deliverables.
Semantic search is useful when the request is written in words rather than represented by a reference image.
1. Break Down the Request
Identify the subject, scene, color, style, and intended use. A vague request such as "warm product image" can become "wooden desk product photo, warm light, simple background".
2. Open Semantic Search
Enter the description in the semantic search dialog. Start with a clear but not overly long prompt.
3. Set Scope and Result Count
Search broadly when you do not know where the material is. Narrow to a folder or collection when the request belongs to a known project. Increase result count when the prompt is exploratory.
4. Review the First Round
Look for direction rather than perfection. Note which words worked and which results are irrelevant.
5. Narrow Results with Filters
Use file type, color labels, ratings, dates, dimensions, or other filters to reduce noise.
6. Run a Second Prompt
Refine the wording based on the first result set. Add color, scene, object, or style details.
7. Add Candidates to a Collection
Move promising results into a project collection so they can be reviewed and exported together.
8. Export Delivery Material
Export selected images or paths depending on what the recipient needs.
Common Cases
- Results are too broad: add subject and scene details.
- Results miss the style: add color or mood words.
- No results: check whether semantic data was generated and broaden the prompt.