https://github.com/oaslananka/basic-visual-synthesis
Python computer-vision and visual synthesis experiments for image generation workflows, dataset preparation, and reproducible CV prototyping.
https://github.com/oaslananka/basic-visual-synthesis
automation computer-vision datasets experiments image-generation machine-learning opencv prototyping python research visual-synthesis
Last synced: about 21 hours ago
JSON representation
Python computer-vision and visual synthesis experiments for image generation workflows, dataset preparation, and reproducible CV prototyping.
- Host: GitHub
- URL: https://github.com/oaslananka/basic-visual-synthesis
- Owner: oaslananka
- Created: 2026-05-22T11:12:20.000Z (about 2 months ago)
- Default Branch: main
- Last Pushed: 2026-06-24T11:57:30.000Z (15 days ago)
- Last Synced: 2026-06-24T13:24:30.796Z (15 days ago)
- Topics: automation, computer-vision, datasets, experiments, image-generation, machine-learning, opencv, prototyping, python, research, visual-synthesis
- Language: Python
- Homepage: https://github.com/oaslananka/basic-visual-synthesis
- Size: 173 KB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Basic Visual Synthesis
Basic Visual Synthesis is a project that performs image analysis and generates detailed commentary by integrating YOLO-based object detection with Anything LLM (Deepseek R114B) using a RAG (Retrieval Augmented Generation) approach. The pipeline detects objects in an image, retrieves additional context from a built-in knowledge base, and then leverages the LLM to produce comprehensive commentary on the image.
> **Project Description:**
> "This project aims to perform image analysis and generate detailed commentary by integrating YOLO-based object detection with the Deepseek LLM using a RAG (Retrieval Augmented Generation) approach."
## Table of Contents
- [Features](#features)
- [Installation & Requirements](#installation--requirements)
## Features
- **Object Detection:** Utilizes [Ultralytics YOLO](https://github.com/ultralytics/ultralytics) for detecting objects in images.
- **Context Retrieval:** Provides additional context via a built-in knowledge base.
- **RAG Approach:** Integrates [Anything LLM](https://anythingllm.com/) for detailed commentary generation. with [Deepseek](https://www.deepseek.com/) R114B to generate detailed commentary using a Retrieval Augmented Generation method.
- **Colored Logging:** Uses [Colorama](https://pypi.org/project/colorama/) with Python's `logging` module for enhanced, colored log output.
## Installation & Requirements
1. **Python Version:** Tested with Python 3.8 and above.
2. **Clone the Repository:**
```bash
git clone https://github.com/oaslananka/BasicVisualSynthesis.git
cd BasicVisualSynthesis
```
3. **Create a Virtual Environment (Optional but Recommended):**
```bash
python -m venv .venv
source .venv/bin/activate
pip install ultralytics colorama requests
python VisualSynthesisRAG.py
```
4. **Install Required Packages:**
```bash
pip install ultralytics colorama requests
```
5. **Configure API Keys and Model Paths:**
- Update the API_KEY and BASE_URL constants in the code as needed.