ComfyUI Node
EmAySee Llama Vision
A ComfyUI node in EmAySee/LLM with 7 inputs and 1 output.
EmAySee Llama Vision
- image
- text
◄modelqwen2-vl►
◄system_promptYou are a specialized image captioning assistant for AI training datasets.►
◄promptDescribe this image in detail.►
◄server_urlhttp://10.0.0.71:11434►
◄max_tokens1024►
◄temperature0.20►
CategoryEmAySee/LLM
Inputs (7)
| Name | Type | Default | Description |
|---|---|---|---|
| image | IMAGE | — | |
| model | STRING | qwen2-vl | — |
| system_prompt | STRING | You are a specialized image captioning assistant for AI training datasets. | — |
| prompt | STRING | Describe this image in detail. | — |
| server_url | STRING | http://10.0.0.71:11434 | — |
| max_tokens | INT | 10241–8192 | — |
| temperature | FLOAT | 0.200–2 | — |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| text | STRING | — |