ComfyUI Node
Recaption
Caption an image by sending it to an OpenAI-compatible vision chat endpoint. The system prompt is selected from YAML files in <user>/default/coras_textgen/prompts/recaption/. The model dropdown is filtered to vision-capable ids by a name heuristic; disable the filter in Settings -> Cora's Textgen -> Recaption to show every model.
Recaption
- image
- text
◄style▾►
◄model▾►
Categorytextgen
Inputs (3)
| Name | Type | Default | Description |
|---|---|---|---|
| image | IMAGE | — | |
| style | COMBO | Prompt style. Edit or add YAML files under <user>/default/coras_textgen/prompts/recaption/. | |
| model | COMBO | Vision-capable models advertised by the configured endpoint. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| text | STRING | — |