You're looking at a specific version of this model. Jump to the model overview.
zf-kbot /manga-image-translator:e6d5fbb0
Input schema
The fields you can use to run this model with an API. If you don’t give a value for a field its default value will be used.
| Field | Type | Default value | Description |
|---|---|---|---|
| image |
string
|
Manga/comic page (jpg, png or webp).
|
|
| mode |
None
|
full
|
full: OCR + LLM translate + render in one call. "
"ocr: detection/OCR only. render: mask/inpaint/render only. "
"Every mode returns an image file and regions.json; identify them by extension, not list order.
|
| regions |
string
|
|
mode=render only: JSON text read from regions.json returned by mode=ocr.
|
| mask |
string
|
mode=render only: URL or uploaded mask.png returned by mode=ocr.
|
|
| translations |
string
|
|
mode=render only: JSON array of translated lines in region '
'order, e.g. ["你好","再见"], or [{"index":0,"translation":"你好"}].
|
| target_lang |
None
|
CHS
|
Target language. CHS/CHT=Chinese, ENG=English, JPN=Japanese, "
"KOR=Korean; the rest follow upstream's codes (see README).
|
| api_base |
string
|
https://api.openai.com/v1
|
mode=full only: OpenAI-compatible API base URL, including /v1.
|
| api_key |
string
|
mode=full only: API key for the LLM endpoint. "
"Any dummy value works for local servers.
|
|
| model |
string
|
|
mode=full only: model name, e.g. gpt-4o-mini, deepseek-chat.
|
Output schema
The shape of the response you’ll get when you run this model with an API.
Schema
{'items': {'format': 'uri', 'type': 'string'},
'title': 'Output',
'type': 'array'}