Probably needs ngrok or some type of tunneling out of google colab.

Description

condition text token size up

TODO

• [fix tokenizer] todo
• [fix pipeline] todo

Describe of bug

I want to load different model

Is it possible to generate images at the same time? Currently it works with two requests at the same time, but is it possible to generate two images simultaneously without waiting for a queue?

I've followed these steps and running from my personal system

RUN from code (frontend)

1. install python Requirements
   pip install
   streamlit==1.12.2
   requests==2.27.1
   requests-toolbelt==0.9.1
   pydantic==1.8.2
   streamlit-drawable-canvas==0.9.2
2. RUN streamlit frontend
   streamlit run inpaint.py

But im getting below error

ConnectionError: HTTPConnectionPool(host='localhost', port=3000): Max retries exceeded with url: /%5Cinpaint (Caused by NewConnectionError('<urllib3.connection.HTTPConnection object at 0x000001A5C72EEA70>: Failed to establish a new connection: [WinError 10061] No connection could be made because the target machine actively refused it'))