ComfyUI Node
Gemini Vision Analysis
A ComfyUI node in API Toolkit/Gemini/Image with 10 inputs and 1 output.
Gemini Vision Analysis
- ref_image_1
- ref_image_2
- ref_image_3
- ref_image_4
- text
◄api_key►
◄modelgemini-3.1-flash-lite-preview►
◄custom_model►
◄promptDescribe this image.►
◄system_instruction►
◄temperature0.10►
CategoryAPI Toolkit/Gemini/Image
Inputs (10)
| Name | Type | Default | Description |
|---|---|---|---|
| api_key | STRING | Gemini API key. Leave blank to use GEMINI_API_KEY env var. | |
| model | COMBO | gemini-3.1-flash-lite-preview | Gemini model for vision analysis. |
| custom_model | STRING | Override with a custom model ID. | |
| prompt | STRING | Describe this image. | What to ask about the image(s). |
| system_instructionopt | STRING | System instruction to guide analysis. | |
| temperatureopt | FLOAT | 0.100–2 | Controls randomness. Lower = more focused analysis. |
| ref_image_1opt | IMAGE | First image to analyze. | |
| ref_image_2opt | IMAGE | Second image to analyze. | |
| ref_image_3opt | IMAGE | Third image to analyze. | |
| ref_image_4opt | IMAGE | Fourth image to analyze. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| text | STRING | — |