ComfyUI Node
Gemini Inpaint
A ComfyUI node in API Toolkit/Gemini/Image with 8 inputs and 1 output.
Gemini Inpaint
- image
- mask
- reference_image
- image
◄api_key►
◄modelgemini-3.1-flash-image-preview►
◄custom_model►
◄prompt►
◄system_instruction►
CategoryAPI Toolkit/Gemini/Image
Inputs (8)
| 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-image-preview | Image-capable Gemini model for inpainting. |
| custom_model | STRING | Override with a custom model ID. | |
| image | IMAGE | The source image to inpaint. | |
| mask | MASK | Mask (white = fill this area, black = keep). Accepts any ComfyUI MASK — from SAM, Grounding DINO, alpha channels, etc. | |
| prompt | STRING | Describe what should fill the masked area. | |
| reference_imageopt | IMAGE | Optional reference image (e.g., object/face to place in the masked area). | |
| system_instructionopt | STRING | System instruction for the inpainting model. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| image | IMAGE | — |