ComfyUI Node
SemanticImageFetch
Select the closest images to an input prompt
SemanticImageFetch
- image
- clip
- clip_vision
- IMAGE
◄prompt—►
◄number_of_candidates1►
CategoryIMAGE
Inputs (5)
| Name | Type | Default | Description |
|---|---|---|---|
| image | IMAGE | The list of images to fetch the semantic map from. | |
| clip | CLIP | The CLIP model used for encoding the text. | |
| prompt | STRING | — | |
| clip_vision | CLIP_VISION | The CLIPVision model used for encoding the images. | |
| number_of_candidates | INT | 11–10 | Number of closest images to retrieve. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| IMAGE | IMAGE | — |