>>105802135
I managed to get it working, but the latest commit is broken. It's in active development, the latest commit should in theory be good, but some repos merge stuff that is not working to main.

>why the everliving fuck would I use a linux virtual machine for a windows program while already using windows
it's not a Windows program, it's a Python program which uses CUDA, and Python versioning is a nightmare to run on a local machine, so it's a standard to run it in a container. Docker containers run always the same on Windows, MacOS and Linux, that's why people use them.

Here's how you can get it working

git clone https://github.com/zyddnys/manga-image-translator
cd manga-image-translator
git reset --hard 3273a97c987453ce809e93a1eee10ea9f376a13a
docker-compose -f demo/doc/docker-compose-web-with-gpu.yml up


After it's done open http://localhost:5003/

But yeah it needs some service to translate it
There is a table in the README
Some are free, some are paid
DeepL is free for translating a few thousand words for example
I'm sure there are some free models too
Some would work better than others, but openAI will probably work quite well

Once you choose which service you want you need to edit the `docker-compose.yml` file and add the appriopriate environment variable with your API key, eg


services:
front:
image: front
build:
context: front
dockerfile: ./Dockerfile
environment:
NODE_ENV: production
OPENAI_API_KEY: sk-1209381209381lksjadlksajd
ports:
- 3000:3000



>I appreciate all the help but I'm too retarded to make this work and not persistent enough to care
Well, it looks like the easiest possible option out there so take it or leave it