Eren Ay

I use it on both mac and windows, it's exactly the same. pip install -r requirements.txt pip install git+https://github.com/kodalli/pydensecrf.git create a image folder in the manga_translator write python -m manga_translator...

You don't need to install with docker just go terminal git clone https://github.com/zyddnys/manga-image-translator.git cd manga-image-translator pip install -r requirements.txt pip install git+https://github.com/kodalli/pydensecrf.git python -m manga_translator -v --translator=google -l ENG -i...

@Bender-V you don't need key.env path ./manga_translator/translators/keys.py in this file change OPENAI_API_KEY = os.getenv('OPENAI_API_KEY', 'change here') sorry for my late answer

Will there be a possibility to support decoupled vision-language deployment in vllm or sglang? Is there a roadmap for when the flash version will be released? is it possible use...

When DVD support arrives, will flash versions of Internvl3_5 also be released? Will Lmdeploy support the flash version when running with DVD? It was written that the 3_5 flash patch...

In cases where the probability is lower 0.2 and mocr text exist, the program just freezes.

Will internvl flash be valid only for model 8b or for all internvl3_5 models? And how can we use Decoupled Vision-Language Deployment (DvD)? @Weiyun1025

You can use with lmstudio or ollama but only supports jpn chinese english