---
title: "MIT CSAIL's Creo Fixes AI Image Drift With Staged Editable Generation"
subtitle: "MIT researchers propose a staged text-to-image workflow with sketch-level intermediates and decision locking, boosting user control and output diversity."
url: "https://alphasignal.ai/news/mit-csail-s-creo-fixes-ai-image-drift-with-staged-editable-generation"
author: "AlphaSignal Newsroom"
author_url: "https://alphasignal.ai/editorial-team"
company: "AlphaSignal"
company_url: "https://alphasignal.ai/company/alphasignal"
published: "2026-04-15T00:00:00.000Z"
updated: "2026-08-23T21:11:51.958Z"
type: "Paper"
topics:
  - "Image"
  - "Development"
subtopics:
  - "Image Generation"
  - "Image Editing"
upvotes: 1626
source_url: "https://arxiv.org/abs/2604.13956"
comments: 0
truncated: true
---

# MIT CSAIL's Creo Fixes AI Image Drift With Staged Editable Generation

> MIT researchers propose a staged text-to-image workflow with sketch-level intermediates and decision locking, boosting user control and output diversity.

Text-to-image models have gotten spectacular at producing polished pictures from a single prompt, but they treat image-making like a one-shot vending machine. You type, they decide, and if you want to change the color of a jacket, half the composition mysteriously shifts too. A team at MIT CSAIL argues this is misaligned with how visual ideas actually form, and they built a system called [Creo](https://arxiv.org/abs/2604.13956) to prove there is a better way.

The [paper](https://arxiv.org/html/2604.13956v1), from Zoe De Simone, Angie Boggust, Fredo Durand, Ashia Wilson, and Arvind Satyanarayan, reframes T2I generation as a staged, editable pipeline rather than a black-box render. Rather than jumping straight to a high-fidelity image, Creo walks users through progressively detailed abstractions, letting them lock in decisions along the way.

## Why one-shot generation gets in your way

The authors identify three concrete failure modes of current T2I systems. Models make implicit visual decisions on behalf of the user, introduce fine-grained details that anchor users prematurely and limit their ability to keep options open early on, and cause unintended changes during editing that are difficult to correct.

That last problem, often called drift, is familiar to anyone who has tried to iterate with a diffusion model. Small prompt tweaks can rewrite the entire scene, because each generation is essentially a fresh sample from the model rather than an edit to the previous one. Premature anchoring is subtler but equally damaging for ideation: once you see a specific rendered face, it is hard to imagine any other face for that character.

_Preview only. Full text requires an AlphaSignal Pro account._

## Sources

- [Creo: From One-Shot Image Generation to Progressive, Co-Creative Ideation (arXiv abstract)](https://arxiv.org/abs/2604.13956)
- [Creo full paper HTML](https://arxiv.org/html/2604.13956v1)
- [Zoe De Simone personal site](https://zoedesimone.github.io/)
- [Zoe De Simone, MIT Architecture profile](https://architecture.mit.edu/people/zoe-de-simone)