[ICCV2023] Official PyTorch Implementation of "BeLFusion: Latent Diffusion for Behavior-Driven Human Motion Prediction". ICCV 2023

ConsistencyTTA: Accelerating Diffusion-Based Text-to-Audio Generation with Consistency Distillation

Unconditional Image Generation using a [modifiable] pretrained VQVAE based Latent Diffusion Model, adapted from huggingface diffusers.

Implementation of Quark: Real-time, High-resolution, and General Neural View Synthesis

Python tools to handle LDM data feeds and convert to other formats.

StableSVC: Latent Diffusion Model for Singing Voice Conversion (originally course project from CUHK-SZ, MDS6002)

VQGAN from LDM without hell of dependencies

A microservice to expose a latent diffusion model for 3D Brain T1-weighted Image generation

DIY Stable Diffusion 1.5 implementation with minimal dependencies.

VLM and LDM based platform for the generation of personalized advertising images in the fashion industry, with evaluation through statistical and choice models | Bachelor's Thesis

Implementation of a latent diffusion model to generate satellite views from ground views in the CVPR dataset.

This project, part of my Master's thesis in Computer Engineering at UCM, develops and trains convolutional neural networks to identify images generated by latent diffusion models.