https://github.com/aashish75/rag-stablediffusion

https://github.com/aashish75/rag-stablediffusion

Science Score: 13.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (4.5%) to scientific vocabulary
Last synced: 10 months ago · JSON representation

Repository

Basic Info
  • Host: GitHub
  • Owner: Aashish75
  • Language: Jupyter Notebook
  • Default Branch: main
  • Size: 493 KB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created over 1 year ago · Last pushed about 1 year ago
Metadata Files
Readme

README.md

RAG-stablediffusion

This project combines Retrieval-Augmented Generation (RAG) with Stable Diffusion to enhance text-to-image generation with real-world knowledge. By integrating retrieved factual information into diffusion model prompts, we aim to create more realistic, meaningful, and contextually accurate images.

📌 Key Features

✅ Retrieval-Augmented Generation (RAG): Uses FAISS and Sentence Transformers to retrieve relevant real-world knowledge before image generation.

✅ Stable Diffusion Pipeline: Generates images conditioned on enhanced prompts that include retrieved factual information.

✅ CLIP-Based Evaluation: Assesses the alignment between generated images and text using CLIP similarity scores.

✅ Efficient FAISS Search: Uses semantic search with FAISS to retrieve knowledge from a Wikipedia dataset.

✅ Optimized Prompt Engineering: Enhances diffusion model performance by injecting real-world knowledge.

Owner

  • Name: Aashish M
  • Login: Aashish75
  • Kind: user

I code

GitHub Events

Total
  • Push event: 9
  • Create event: 2
Last Year
  • Push event: 9
  • Create event: 2