title	emoji	colorFrom	colorTo	sdk	sdk_version	app_file	pinned	license
Multimodal Content Generation	🤗	indigo	green	streamlit	1.32.0	multi-modal-content-generation.py	false	apache-2.0

A Multimodal Content Generation have following capabilities:

1. A Conversational chatbot as same as ChatGPT v3.5 + Image Summarization Capabilities through GOOGLE GEMINI VISION PRO API.

Screen.Recording.2024-03-07.at.4.37.26.PM.mov

2. Text to Image (using Stability Ai (Stable Diffusion)) through REPLICATE API.

Setup steps:

1. Create virtual environment

   python -m venv <name of virtual environment>
   

2. Activate it

   source <name of virtual environment>/bin/activate
   

3. Now install required libraries from requirements.txt file using...

   pip install -r requirements.txt
   

4. Create .env file and add your API TOKEN

   GOOGLE_API_KEY="Enter Your GOOGLE API TOKEN"
   REPLICATE_API_KEY=""
   

5. To run app

   streamlit run <name-of-app>.py
   

Also Deployed on Render (but due to inactivity, it may take around 50 seconds to load the site): https://multimodal-content-generation-using-llms.onrender.com/