InstructPix2Pix: Learning to Follow Image Editing Instructions

TL;DR

InstructPix2Pix is a diffusion-based model trained on a large dataset generated by combining GPT-3 and Stable Diffusion, enabling fast, instruction-based image editing without fine-tuning.

Contribution

The paper introduces a novel method for image editing from instructions using a large dataset and a diffusion model that generalizes well to real images and user instructions.

Findings

Model performs edits in seconds.

Generates diverse and accurate image edits.

Generalizes to real images and instructions.

Abstract

We propose a method for editing images from human instructions: given an input image and a written instruction that tells the model what to do, our model follows these instructions to edit the image. To obtain training data for this problem, we combine the knowledge of two large pretrained models -- a language model (GPT-3) and a text-to-image model (Stable Diffusion) -- to generate a large dataset of image editing examples. Our conditional diffusion model, InstructPix2Pix, is trained on our generated data, and generalizes to real images and user-written instructions at inference time. Since it performs edits in the forward pass and does not require per example fine-tuning or inversion, our model edits images quickly, in a matter of seconds. We show compelling editing results for a diverse collection of input images and written instructions.