A flexible framework powered by ComfyUI for generating personalized Nobel Prize images.

An open source implementation of "Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning", an all-new multi modal AI that uses just a decoder to generate both text and images

Using Replicate to build Streamlit app for image generations!

A SwiftUI app demonstrating how ChatGPT interacts with DALL·E and HuggingFace models for iOS and macOS.

Codebase for the paper-Elucidating the design space of language models for image generation

A tensorflow/keras implementation of StyleGAN to generate images of new Pokemon.

A software application is that allows users to input specific themes or topics for a meme or marketing poster. Following this input, the application produces a cohesive poster with both text and imagery

👩‍🎨 StableCanvas is a professional AI drawing editor, aimed at providing a more suitable creative experience for AI painting. No download or installation required, start instantly in your browser, making the AI-driven image creation process more efficient and streamlined.

Python Streamlit web app utilizing the OpenAI API to communicate with the Dalle2 image generation model, based on user input.

A type safe library for interacting with OpenAI's Dall-E 2 AI.

An AI-powered Mattermost ChatGPT chatbot that utilizes the OpenAI API to provide helpful, contextual responses to user messages, extract text from links, and describe or generate images. With Docker support!

LDM using tensorflow.

Creata✨allows you to create stunning AI-generated images effortlessly🖼️, it is a project that showcases my UI and API skills.

Multiple Conditioned Image Generation, SDXL, Low-rank adaptation Refined

SnapSpell: Instant AI Image Sorcery with Flux 1.1 Pro

A PyTorch implementation of Pix2PixHD to generate 1024x1024 HD images of Celebrities using sketches.

AI Image Gen Demo App

FusionImage is an innovative and cutting-edge AI Image Generation Application that leverages the power of computer vision and neural networks to create stunningly realistic and visually captivating images.

I created and trained a DCGAN (Deep Convolutional Generative Adversarial Network) to produce artificial portraits using a dataset containing more than 6000 images.