ComfyUI Node
Image Stats Caption (no VLM)
Writes a template caption from the image's mean brightness, contrast and dominant RGB tone. No vision-language model runs, so it does not describe what is in the image.
Image Stats Caption (no VLM)
- image
- caption
◄caption_style▾►
CategoryParametric/Agents
Inputs (2)
| Name | Type | Default | Description |
|---|---|---|---|
| image | IMAGE | The input image. | |
| caption_style | COMBO | Caption style. One of 4 choices. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| caption | STRING | — |