# prompt_translator_evo

**Repository Path**: ddrfan/prompt_translator_evo

## Basic Information

- **Project Name**: prompt_translator_evo
- **Description**: 源插件地址：https://github.com/ParisNeo/prompt_translator
因为有一些小问题，而作者最近没时间改，连PR都没有合并，所以暂时新建仓库修改。
- **Primary Language**: Unknown
- **License**: MIT
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2023-05-17
- **Last Updated**: 2023-05-18

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# Prompt Translator for Stable Diffusion

Modify from: https://github.com/ParisNeo/prompt_translator  
Please visit the original repo to get the detailed information.

Author `ParisNeo` is engaged to sth else.  
Seems have no time to fix or improve, not even merge PRs.  

So I temporarily copied his repository and modified some issues:

1. Translation is not working in IMG2IMG.
2. Distinguish between Simplified Chinese and Traditional Chinese.
3. Loading model when doing first translation (to make IMG2IMG working...).

Still not good:

1. TXT2TXT and IMG2IMG, the language model will be loaded twice.
2. Words in brackets, such as the LoRA model name, are not translated properly.

Why I can't fix it?  
I don't know Python or Gradio or WEBUI plugin development at all. Sorry T_T.

---

> Stable diffusion is a text to image generation model. The `prompt_translator` extension allows people to translate their prompt from any language to English before executing the generation, making it accessible to a wider audience.

## Usage

After installing `prompt_translator`, a new entry will be added to the Gradio UI. To use the automatic translation tool, click the "**Enable translation**" button to enable it.

When doing the first translation, it load the translation model. The translation model used in this tool is the `mbart-large-50-many-to-one-mmt` model developed by Meta (formerly Facebook). You can find more information about the model on its [Hugging Face model card](https://huggingface.co/facebook/mbart-large-50-many-to-one-mmt).

The first time is slow, but once the model is loaded, The future translation will be fast. 
The prompt will automatically be translated to English, and the resulting image will look as described in the text.

If too slow to download model automaticlly, please download it yourself, following the link above.

## Supported Languages

The list of supported languages is: Arabic (ar_AR), Czech (cs_CZ), German (de_DE), English (en_XX), Spanish (es_XX), Estonian (et_EE), Finnish (fi_FI), French (fr_XX), Gujarati (gu_IN), Hindi (hi_IN), Italian (it_IT), Japanese (ja_XX), Kazakh (kk_KZ), Korean (ko_KR), Lithuanian (lt_LT), Latvian (lv_LV), Burmese (my_MM), Nepali (ne_NP), Dutch (nl_XX), Romanian (ro_RO), Russian (ru_RU), Sinhala (si_LK), Turkish (tr_TR), Vietnamese (vi_VN), Chinese Simplified(zh_CN), Chinese Traditional(zh_TW), Afrikaans (af_ZA), Azerbaijani (az_AZ), Bengali (bn_IN), Persian (fa_IR), Hebrew (he_IL), Croatian (hr_HR), Indonesian (id_ID), Georgian (ka_GE), Khmer (km_KH), Macedonian (mk_MK), Malayalam (ml_IN), Mongolian (mn_MN), Marathi (mr_IN), Polish (pl_PL), Pashto (ps_AF), Portuguese (pt_XX), Swedish (sv_SE), Swahili (sw_KE), Tamil (ta_IN), Telugu (te_IN), Thai (th_TH), Tagalog (tl_XX), Ukrainian (uk_UA), Urdu (ur_PK), Xhosa (xh_ZA), Galician (gl_ES), Slovene (sl_SI).

## License

This project is licensed under the MIT license.