Add lobe-i18n setup and translation scripts and update translation files for consistency #1751
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Hello!
I recall hearing about a plan to use LLM-based tools for translations in this project, so I created this PR to introduce lobe-i18n to ComfyUI.
You can refer to the README for detailed usage instructions, but this tool allows you to generate translations in bulk using the OpenAI API.
This is purely a suggestion, so if it does not align with ComfyUI's direction or policies, feel free to close the PR without any concerns.
That said, I want to inform you about two potential challenges related to this PR:
OpenAI API Key is Required for Translations
An OpenAI API key is necessary to execute the translation process.
However, for an open-source project like ComfyUI, I am uncertain about the best way to manage this.
I would appreciate any input or guidance on this matter.
Manual Adjustments May Be Needed
As this uses an LLM-based translation tool, there might occasionally be translations that feel slightly off in certain languages. For example, I made the following manual adjustments:
Example adjustments go here
Once these adjustments are made manually, they will be skipped in subsequent translation runs, so it might not be a significant issue.
That's all for the PR!
Please feel free to comment if you have any questions or suggestions for changes.