comfyui_inpaint_image
Inpaint masked regions of an image using a text prompt to regenerate those areas with content matching your description.
Instructions
Inpaint regions of an image using a mask and text prompt.
Both the input image and mask must already be uploaded via
comfyui_upload_image/comfyui_upload_mask.
White regions in the mask indicate areas to regenerate.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"image": "<image>",
"mask": "<mask>",
"prompt": "<prompt>"
},
"name": "comfyui_inpaint_image"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| cfg | No | Classifier-free guidance scale | |
| mask | Yes | Mask image filename (white=inpaint, black=keep) | |
| wait | No | If True, block until complete and return result | |
| image | Yes | Filename of the image in ComfyUI's input directory | |
| model | No | Checkpoint model name (leave empty for default) | |
| steps | No | Number of sampling steps | |
| prompt | Yes | Text description for the inpainted region | |
| strength | No | How much to deviate from the input image | |
| negative_prompt | No | What to avoid in the output | bad quality, blurry |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||