A microframework on top of PyTorch with first-class citizen APIs for foundation model adaptation

[ACM MM 2023] - LaDI-VTON: Latent Diffusion Textual-Inversion Enhanced Virtual Try-On

A collection of tutorials about training and generating with Stable Diffusion.

Official Implementation for "A Neural Space-Time Representation for Text-to-Image Personalization" (SIGGRAPH Asia 2023)

[ICCV 2023] - Zero-shot Composed Image Retrieval with Textual Inversion

Stable Diffusion Regularization Images in 512px, 768px and 1024px on 1.5, 2.1 and SDXL 1.0 checkpoints

Fast finetuning using a booster model that puts the initial state to a local minimum

A novel zero-shot image harmonization method based on Diffusion Model Prior.

Fine-tuning of diffusion models

[ECCV2024] PartCraft: Crafting Creative Objects by Parts

A Diffusion training toolbox based on diffusers and existing SOTA methods, including Dreambooth, Texual Inversion, LoRA, Custom Diffusion, XTI, ....

This repository contains the implementation of DreamBooth with Stable Diffusion. You can also find instructions to train a model on a vast.ai instance.

Code for Investigating Personalization Methods in Text to Music Generation

Pre-rendered regularization images of men and women, mainly faces, seeking to generate more realistic images (without wax skin)

Custom Textual-Inversion for Stable-Diffusion models with Keras.

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

A large library of textual inversion embeddings trained on a works of a real anime artists

Subject-Driven Generation Techniques for Stable Diffusion Model. A modern approach to data augmentation. Master's Thesis. Technical University of Denmark - DTU

A docker manager to receive a small set of image data, automatically retrain the pre-trained stable diffusion model and deploy a docker container with an API to consume the new instance of this model.

Imaging tools CLI for preprocessing datasets before model training.