ComfyUI Node
Caption Creator
Creates a factual caption for each input image with a native Qwen3-VL ConvRot text encoder. Thinking is disabled and decoded text is returned unchanged.
Caption Creator
- image
- text
◄model_precisionint8►
◄auto_downloadtrue►
◄words100►
Categoryflow-assistor/image/caption
Inputs (4)
| Name | Type | Default | Description |
|---|---|---|---|
| image | IMAGE | A ComfyUI IMAGE tensor; batches are supported. | |
| model_precision | COMBO | int8 | Choose the Qwen3-VL ConvRot model precision to load. |
| auto_download | BOOLEAN | true | Download a missing model into models/text_encoders/flow-assistor. |
| words | INT | 1000–200 | Approximate words per caption, not a hard limit. Set to 0 for an unrestricted detailed caption. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| text | STRING | — |