ComfyUI Node
Image Captioner (API: edit config.json)
A ComfyUI node in FeiFei with 6 inputs and 3 outputs.
Image Captioner (API: edit config.json)
- chinese
- english
- thinking
◄image▾►
◄instructionLook at this image carefully and output ONLY one JSON object, nothing else: {"chinese": "describe the image content, subject, action, scene, lighting and style in detail in Chinese", "english": "English image-generation prompt, comma-separated tags and quality words, directly usable in Stable Diffusion or Qwen-Image, e.g. '1girl, ... , masterpiece, best quality'"}►
◄temperature0.70►
◄max_tokens1024►
◄max_side1024►
◄thinking_modeOurs (8-step)►
CategoryFeiFei
Inputs (6)
| Name | Type | Default | Description |
|---|---|---|---|
| image | COMBO | 1 options: example.png | |
| instruction | STRING | Look at this image carefully and output ONLY one JSON object, nothing else: {"chinese": "describe the image content, subject, action, scene, lighting and style in detail in Chinese", "english": "English image-generation prompt, comma-separated tags and quality words, directly usable in Stable Diffusion or Qwen-Image, e.g. '1girl, ... , masterpiece, best quality'"} | — |
| temperature | FLOAT | 0.700.1–1.5 | — |
| max_tokens | INT | 102464–8192 | — |
| max_side | INT | 1024256–4096 | — |
| thinking_mode | COMBO | Ours (8-step) | 3 options: Ours (8-step), Model native, Both |
Outputs (3)
| Name | Type | Description |
|---|---|---|
| chinese | STRING | — |
| english | STRING | — |
| thinking | STRING | — |