ComfyUI Node
✨Image Caption (VLM)
Extract text prompt from image using Vision-Language Models
✨Image Caption (VLM)
- image
- caption_text
- caption_list
◄rule像素级描述（by:阿丹）►
◄custom_rulefalse►
◄custom_rule_content►
◄user_prompt►
◄vlm_service智谱/glm-4.6V-Flash►
◄ollama_auto_unloadtrue►
◄seed0►
Category✨Prompt Assistant
Inputs (8)
| Name | Type | Default | Description |
|---|---|---|---|
| image | IMAGE | The image to analyze. Supports single image or IMAGE batch (processes each frame independently) | |
| rule | COMBO | 像素级描述（by:阿丹） | Choose a preset rule for analysis |
| custom_rule | BOOLEAN | false | Enable custom rule input |
| custom_rule_content | STRING | Custom rule content, only used when Custom Rule is enabled | |
| user_prompt | STRING | Enter additional prompts here, sent with the rule | |
| vlm_service | COMBO | 智谱/glm-4.6V-Flash | Select VLM Service |
| ollama_auto_unload | BOOLEAN | true | Auto unload Ollama model after generation |
| seed | INT | 00–18446744073709550000 | Controls randomness. Set to non-fixed mode to force re-execution |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| caption_text | STRING | — |
| caption_list | STRING | — |