ComfyUI Node
LLM Prompt (Vision)
Unified provider-switching vision generation node for REST/OpenAI and Native CLIP.
LLM Prompt (Vision)
- image
- response
◄promptWrite a detailed description for this image. Use precise, unambiguous language. Avoid vague or general terms. This is going to be used as input for an AI image generator, so do not include anything other than the description, and do not break things into sections or use markdown.►
◄provider▾►
◄seed0►
CategorySage Utils/LLM
Inputs (4)
| Name | Type | Default | Description |
|---|---|---|---|
| prompt | STRING | Write a detailed description for this image. Use precise, unambiguous language. Avoid vague or general terms. This is going to be used as input for an AI image generator, so do not include anything other than the description, and do not break things into sections or use markdown. | The text prompt for vision-capable LLM providers. |
| image | IMAGE | The reference image sent to the vision provider. | |
| provider | COMBO | Pick the backend provider and its model/runtime settings. | |
| seed | INT | 00–4294967295 | Base seed used by all providers (provider-specific behavior may vary). |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| response | STRING | The text response returned by the selected vision provider. |