# Diffusion Model Applications

FramePainter is an interactive image editing model based on video diffusion priors, capable of high-quality video frame editing.

Flux.1-Dev is a text-to-image generation model that supports generating diverse image content based on text prompts.

in2IN is a novel diffusion model that generates high-quality human interactions by combining holistic interaction descriptions with individual motion descriptions.

A Stable Diffusion model fine-tuned on Irish traditional music spectrograms for unconditional image generation and text-to-image conversion

This project downscales ERA5 global reanalysis data to establish a machine learning model capable of generating high-resolution regional reanalysis data

This is a diffusion model for generating whole slide images (WSI), implemented based on the Denoising Diffusion Probabilistic Model (DDPM) architecture.

This is a diffusion model trained with Dreambooth, specifically designed for generating startup-style logo images.