Experiments and data for the paper "When and why vision-language models behave like bags-of-words, and what to do about it?" Oral @ ICLR 2023

An implementation of the Prompt-to-Prompt paper for the SDXL architecture

Concept Sliders for Precise Control of Diffusion Models

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

ICLR 2023 DeCap: Decoding CLIP Latents for Zero-shot Captioning

PyTorch implementation of InstructDiffusion, a unifying and generic framework for aligning computer vision tasks with human instructions.

A list of alternatives for Adobe software

Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models arXiv 2023 / CVPR 2024

GPT4All: Run Local LLMs on Any Device. Open-source and available for commercial use.

ICLR 2024 (Spotlight)

[CVPR 2024] Focus on Your Instruction: Fine-grained and Multi-instruction Image Editing by Attention Modulation

Controllable video and image Generation, SVD, Animate Anyone, ControlNet, ControlNeXt, LoRA

Code for the paper "Visual Anagrams: Generating Multi-View Optical Illusions with Diffusion Models"

DNO: Optimizing Diffusion Noise Can Serve As Universal Motion Priors

ComfyUI Version of "Visual Style Prompting with Swapping Self-Attention"

[ECCV2024] IDM-VTON : Improving Diffusion Models for Authentic Virtual Try-on in the Wild

This repository contains official implementation of 3DV'24 paper: CloSe: A 3D Clothing Segmentation Dataset and Model

SIZER(Tiwari et al. ECCV2020) Dataset Repository

Ocean is the in-house framework for Computer Vision (CV) and Augmented Reality (AR) applications at Meta. It is platform independent and is mainly implemented in C/C++.

Code for our papers : "Generating images of rare concepts using pre-trained diffusion models" (AAAI 24) and "Norm-guided latent space exploration for text-to-image generation" (Neurips 23)

Code for "ISP: Multi-Layered Garment Draping with Implicit Sewing Patterns", NeurIPS2023