Bulk Synthetic Data Generation
Professional LoRA AI image platform with 500+ creative models
This repository contains the open-source front-end for an AI-powered text-to-image generator. It is a clean, responsive, and user-friendly web application built with vanilla HTML, CSS, and JavaScript, designed to connect to any compatible image generation backend API.
Describe an image using llama and Together AI. The program will open a local directory from the local system.
Implemented the cats and dogs classes from Cifar-10 dataset by developing a GAN model from scratch.
Image Generation Random Prompt Variation Generator
Scene Smith is an AI-powered tool for storytellers and creators to design, preview, and organize scenes with ease. It allows you to generate scene visuals from prompts, manage scripts, and keep everything structured in one place. Perfect for writers, filmmakers, and creatives looking to streamline their storytelling workflow.
A Gradio-powered web app integrating multiple Hugging Face models for tasks like chat, image generation, captioning, object detection, text summarization, and named entity recognition. Built with Python, Transformers, and Stable Diffusion.
Grayscale-to-RGB image colorization using diffusion models on CIFAR-10, inspired by the Palette paper. Lightweight and customizable.
An AI-powered Streamlit app for PDF and web-based Q&A using RAG (Retrieval-Augmented Generation), Groq’s Mixtral LLM, and DeepAI image generation.
The Text-to-Image Generator transforms user text prompts into visually compelling images using advanced AI models. This tool provides an easy-to-use interface, enabling users to generate and download custom images instantly.
Cloud image generation with Python and OpneCV
MultiFormatImageGenerator is a Python script that generates test images in multiple formats (JPEG, PNG, BMP, TIFF) with randomized resolutions, background colors, and text colors.
Stable Diffusion web UI - Applied to generate Covid-19 Augmented Xray chest images. Checkout research paper published - https://www.psvpec.in/jcres/2024_1/93.pdf
A Variational Autoencoder (VAE) using PyTorch and trains it on the Fashion MNIST dataset.
Add a description, image, and links to the imagegeneration topic page so that developers can more easily learn about it.
To associate your repository with the imagegeneration topic, visit your repo's landing page and select "manage topics."