What are the aims of this repository? To create a minimal implementation for training a Diffusion model for a text generation task, and the accompanying generation process. The goal is a modestly ...

Susanna Sova studying a pig molar cusp that was modelled in the study. Credit: Jukka Jernvall The tooth is the most mineralized tissue in the mammalian body and holds information about the creature it ...

This is a simple image generator built using the Stable Diffusion model and the Gradio library for a user-friendly interface. It uses the DDPM sampler for image generation.

In an article recently submitted to the ArXiv* server, researchers addressed the success of Text-to-Image (T2I) AI technology and the lag in Text-to-Video (T2V) development by introducing a "Simple ...