Tony-Lowe

automahalanobis

A PyTorch implementation of an autoencoder trained to minimize the Mahalanobis distance between input and reconstruction.

layout-guidance

[WACV 2024] Training-Free Layout Control with Cross-Attention Guidance

MagicClothing

Official implementation of Magic Clothing: Controllable Garment-Driven Image Synthesis

UniDet

Object detection on multiple datasets with an automatically learned unified label space.

bounded-attention

plug-and-play

Official Pytorch Implementation for “Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation” (CVPR 2023)

HRS_benchmark

CSW

A novel variant of sliced Wasserstein based on a new slicing technique that utilizes the convolution operator.

scalable-pytorch-sinkhorn

SinkhornAutoDiff

Toolbox to integrate optimal transport loss functions using automatic differentiation and Sinkhorn's algorithm

RnB

t2v_metrics

Evaluating text-to-image/video/3D models with VQAScore

CONFORM

Contrast is All You Need For High-Fidelity Text-to-Image Diffusion Models [CVPR 2024]

SPRIGHT

[ECCV 2024] Official PyTorch implementation of "Getting it Right: Improving Spatial Consistency in Text-to-Image Models"

Ranni

DenseDiffusion

Official Pytorch Implementation of DenseDiffusion (ICCV 2023)

SuperPoint_FBOW

本项目是通过深度学习特征提取SuerPoint与fbow来训练一个基于深度学习的词袋。可以用自己的图片来训练，也可以改用其他的深度学习方法

sd-webui-regional-prompter

set prompt to divided region

torch-LLM4SGG

Official PyTorch implementation Source code for LLM4SGG: Large Language Models for Weakly Supervised Scene Graph Generation, accepted at CVPR 2024

DiffMOT

code for CVPR2024 paper: DiffMOT: A Real-time Diffusion-based Multiple Object Tracker with Non-linear Prediction

Prompt-Highlighter

[CVPR 2024] Prompt Highlighter: Interactive Control for Multi-Modal LLMs

EfficientMod

[ICLR 2024 poster] Efficient Modulation for Vision Networks

ReCo

ReCo: Region-Controlled Text-to-Image Generation, CVPR 2023

LLM-groundedDiffusion

LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models (LLM-grounded Diffusion: LMD)

noisecollage

This is an official repository for the paper, NoiseCollage, which is a revolutionary extension of text-to-image diffusion models for layout-aware image generation.

OmniTrackFast

Official Code For Track Everything Everywhere Fast and Robustly

RecDiffusion

[CVPR2024]: RecDiffusion: Rectangling for Image Stitching with Diffusion Models

multi-region-guided-diffusion

A plug-in for stable diffusion webUI. Users can perform region/object level image manipulation, including object addition, removal, and attribute modification.

LayoutLLM-T2I

DirectedDiffusion

Directed Diffusion: Direct Control of Object Placement through Attention Guidance (AAAI2024)