Experiment with latent diffusion models.

Code created or stored during learning and experiments on latent diffusion models

This project explores generating high-quality images using depth maps and conditioning techniques like Canny edges, leveraging Stable Diffusion and ControlNet models. It focuses on optimizing image generation with different aspect ratios, inference steps to balance speed and quality.

[official] PyTorch implementation of Latent Diffusion Model for Conditional Reservoir Facies Generation

TensorFlow implementation of Latent Diffusion Model

This is a repo providing same stable diffusion experiments, regarding textual inversion task and captioning task

VQGAN from LDM without hell of dependencies

Latent diffusion model following Umar Jamil's tutorial https://youtu.be/ZBKpAp_6TGI?si=Fa822KYeOP_2LWdr https://github.com/hkproj/pytorch-stable-diffusion

ソースコードから理解するStable Diffusion(Latent Diffusion Model)のスライド。　

The presentation slide that explains image generation using Latent Diffusion Models through source code.

The official pytorch implementation of Paper: RECOGNITION-GUIDED DIFFUSION MODEL FOR SCENE TEXT IMAGE SUPER-RESOLUTION

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

Official repository of "Towards Learning Contrast Kinetics with Multi-Condition Latent Diffusion Models"

Author's Implementation for E-LatentLPIPS

Code for the paper published in Deep Generative Models for Health Workshop at the Neurips 2023.

[Early Accepted at MICCAI 2023] Pytorch Code of "InverseSR: 3D Brain MRI Super-Resolution Using a Latent Diffusion Model"

Easy setup for generating beautiful images with Stable Cascade.

Repository to train Latent Diffusion Models on Chest X-ray data (MIMIC-CXR) using MONAI Generative Models

Playing around with stable diffusion. Generated images are reproducible because I save the metadata and latent information. You can generate and then later interpolate between the images of your choice.

A novel inpainting framework that can remove objects from images based on the instructions given as text prompts.