ComfyUI Node
🎯 LLMs Vision | 图像理解
A ComfyUI node in LLMs with 4 inputs and 1 output.
🎯 LLMs Vision | 图像理解
- image
- STRING
◄model_type▾►
◄model▾►
◄promptPlease provide a detailed description of this image, including:
- The main subject(s) and their appearance
- The setting and environment
- Colors, lighting, and visual elements
- Any notable details or unique features
- The overall mood and atmosphere
Describe as if you are explaining the image to someone who cannot see it.►
CategoryLLMs
Inputs (4)
| Name | Type | Default | Description |
|---|---|---|---|
| image | IMAGE | — | |
| model_type | COMBO | 4 options: openai, glm4, ali, gemini | |
| model | COMBO | 4 options: gpt-4-vision-preview, glm-4v, qwen-vl-plus, gemini-pro-vision | |
| prompt | STRING | Please provide a detailed description of this image, including: - The main subject(s) and their appearance - The setting and environment - Colors, lighting, and visual elements - Any notable details or unique features - The overall mood and atmosphere Describe as if you are explaining the image to someone who cannot see it. | — |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| STRING | STRING | — |