Actions15
- Audio Actions
- Document Actions
- File Search Actions
- Image Actions
- Media File Actions
- Text Actions
- Video Actions
Image → Analyze Image
AI-generatedSummary
Analyze images using a selected AI model and an optional prompt to gain insights or answers about the image content.
Inputs
- Model (required) — Select the AI model to use for analysis, either from a searchable list or by specifying its ID.
- Text Input — Provide a textual prompt guiding the image analysis, defaulting to "What's in this image?".
- Input Type (required) — Choose the input method: either image URL(s) or binary image file(s).
- URL(s) — Enter one or more image URLs, separated by commas, when using Image URL(s) input type.
- Input Data Field Name(s) — Specify binary field name(s) containing image data, comma-separated, when using Binary File(s) input type.
- Simplify Output — Enable to simplify the response to the essential analysis results.
- Options — Additional settings including 'Length of Description (Max Tokens)' to control the detail level of the image description.
Output shape
a list of analysis result items corresponding to each image analyzed
Output items contain the candidate analysis results JSON. The response can be simplified or raw based on the Simplify Output parameter. Multiple images can be processed by specifying multiple URLs or binary fields separated by commas.