AI-Generator is a centralized framework designed to streamline the deployment and interaction with Large Language Models (LLMs) and Generative Media engines. It focuses on Local-First AI, allowing for private, secure, and high-speed generation without reliance on external paid APIs.
- Local LLM Integration: Seamlessly connect with Ollama, Code Llama, and Qwen models.
- Multi-Modal Support: Framework hooks for both Text-to-Text and Text-to-Image generation.
- Optimized Inference: Configured for efficient performance on both CPU and GPU (WSL/Ubuntu optimized).
- Extensible Architecture: Built-in support for custom system prompts and "Persona" switching.
- Language: Python 3.12
- AI Engines: Ollama, PyTorch, Transformers
- Environment: WSL2 / Ubuntu 24.04
- UI: (Mention if you're using Gradio, Streamlit, or your Anti-Gravity React style)
-
Ensure Ollama is running in your WSL/Ubuntu environment.
-
Pull your preferred model:
ollama pull llama3 -
Run the generator:
python main.py --model llama3 --prompt "Explain quantum computing like a Manhwa narrator."
Project to genrate article and image and save it pdf
