Semantic Image Search
Describe image content in natural language and use semantic vectors to find matching material, with optional scope and result-count settings.
Assist Local Image Search Team2026-06-293 min read

Describe image content in natural language and use semantic vectors to find matching material, with optional scope and result-count settings.
Semantic search lets you find images by describing what you want instead of providing a reference image.
Steps
- Open the semantic search entry from the top toolbar.
- Enter a natural-language description.
- Set the search scope if needed.
- Set the maximum number of results.
- Start the search and review the returned images.
Writing Better Prompts
Describe the subject, scene, color, style, and use case when possible. For example:
- "product photo on a blue background"
- "modern living room with warm lighting"
- "woman holding flowers outdoors"
- "minimal poster with red elements"
Short prompts are fine, but clearer descriptions usually make the first result set easier to review.
Search Options
Use scope to limit the search to a folder, collection, or database range. Use result count to control how many candidates return.
Common Cases
- If results are too broad, add subject, color, or scene details.
- If no results appear, check whether semantic data has been generated.
- If the first prompt is not enough, run a second search with more specific wording.