AI Paper Atlas

Research map / Image generation / Editing and style transfer

InstructPix2Pix: Learning To Follow Image Editing Instructions

CVPR 2023 · Image generation › Editing and style transfer · approach: Instruction-based diffusion editing · 1,395 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use the full generated training dataset rather than a smaller dataset (ablation)InstructPix2Pix · Image editing, especially larger editsdirectional CLIP similarityHelped
Use the full generated training dataset rather than a smaller dataset (ablation)InstructPix2Pix · Image editingCLIP image similarityMixed
Apply CLIP filtering to the generated image pairs (ablation)InstructPix2Pix · Image editingimage consistency with inputHelped
Increase text guidance scale s_T (ablation)InstructPix2Pix · Image editingconsistency with edit instructionHelped
Increase image guidance scale s_I (ablation)InstructPix2Pix · Image editingconsistency with input imageHelped
Use InstructPix2Pix instead of SDEdit at the same directional similarityImage editing · Quantitative comparison with SDEditCLIP image similarityHelped

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy