ComfyUI Node
Character appearance (image / text)
Pass a character's appearance as text, or extract it from a reference image with the MOSS Qwen.
Character appearance (image / text)
- Qwen
- 参考画像
- Appearance for shared characters
◄指定方法文章のみ►
◄外見プロンプト►
◄最大トークン数256►
CategoryManga panel dataset
Inputs (5)
| Name | Type | Default | Description |
|---|---|---|---|
| 指定方法 | COMBO | 文章のみ | "Text only" passes the appearance prompt as is. The other methods extract the appearance from the reference image. |
| 外見プロンプト | STRING | For "Text only", describe the appearance in English. With an image, you can add details such as hair color or clothing. Put pose and background in the panel's scene. | |
| 最大トークン数 | INT | 25664–1024 | Maximum length of the extracted appearance text. |
| Qwenopt | CLIP | You can share the CLIPLoader (type=moss_image) output used for MOSS generation. Not evaluated for "Text only". | |
| 参考画像opt | IMAGE | Connect one image that shows the character from a Load Image node. If needed, it is downscaled to 768 px on the long side for analysis only. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| Appearance for shared characters | STRING | — |