ComfyUI Node
Google AI Studio Vision
Describe images, generate tags, or answer a custom prompt about an image
Google AI Studio Vision
- image
- text
◄api_key►
◄modelgemini-3.8-flash►
◄modeDescribe►
◄prompt►
◄system_instruction►
◄max_output_tokens2048►
◄thinking_leveldefault►
◄model_override►
CategoryGoogle AI Studio
Inputs (9)
| Name | Type | Default | Description |
|---|---|---|---|
| image | IMAGE | — | |
| api_key | STRING | Google AI Studio API key. Leave empty to use GOOGLE_API_KEY / GEMINI_API_KEY. | |
| model | COMBO | gemini-3.8-flash | 10 options: gemini-4-argon, gemini-3.8-flash, gemini-3.6-flash, gemini-3.5-flash-lite, gemini-3.1-flash-lite, gemini-3.1-pro-preview, +4 |
| mode | COMBO | Describe | 3 options: Describe, Tags, Custom prompt |
| promptopt | STRING | Used as-is for 'Custom prompt', or appended as extra instructions for 'Describe' / 'Tags'. | |
| system_instructionopt | STRING | Optional system instruction. | |
| max_output_tokensopt | INT | 20481–65536 | — |
| thinking_levelopt | COMBO | default | 4 options: default, low, medium, high |
| model_overrideopt | STRING | Optional model ID that overrides the dropdown (for brand-new models). |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| text | STRING | — |