# Creo: From One-Shot Image Generation to Progressive, Co-Creative Ideation

arXiv: https://arxiv.org/abs/2604.13956 · HTML: https://mlsanity.com/paper/2604.13956/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 65 references that are in the map.
- First posted on arXiv 15 Apr 2026.

## Builds on (most cited first, 14 of 14)

- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Sketch-Guided Text-to-Image Diffusion Models](https://mlsanity.com/paper/2211.13752/) (2022)
- [Generative artificial intelligence enhances creativity but reduces the diversity of novel content](https://mlsanity.com/paper/2312.00506/) (2023)
- [Bridging the Gulf of Envisioning: Cognitive Design Challenges in LLM Interfaces](https://mlsanity.com/paper/2309.14459/) (2023)
- [Magic Fixup: Streamlining Photo Editing by Watching Dynamic Videos](https://mlsanity.com/paper/2403.13044/) (2024)
- [The Effects of Generative AI on Design Fixation and Divergent Thinking](https://mlsanity.com/paper/2403.11164/) (2024)
- [SketchAgent: Language-Driven Sequential Sketch Generation](https://mlsanity.com/paper/2411.17673/) (2024)
- [Why Do Line Drawings Work? A Realism Hypothesis](https://mlsanity.com/paper/2002.06260/) (2020)
- [An Interaction Framework for Studying Co-Creative AI](https://mlsanity.com/paper/1903.09709/) (2019)
- [Block and Detail: Scaffolding Sketch-to-Image Generation](https://mlsanity.com/paper/2402.18116/) (2024)
- [Instance Segmentation of Scene Sketches Using Natural Image Priors](https://mlsanity.com/paper/2502.09608/) (2025)
- [Computational Scaffolding of Composition, Value, and Color for Disciplined Drawing](https://mlsanity.com/paper/2509.17268/) (2025)
- [Notational Animating: An Interactive Approach to Creating and Editing Animation Keyframes](https://mlsanity.com/paper/2603.06880/) (2026)

## Built on by (most cited first, 1 of 1)

- [Alignment has a Fantasia Problem](https://mlsanity.com/paper/2604.21827/) (2026)

## Abstract (arXiv)

Text-to-image (T2I) systems enable rapid generation of high-fidelity imagery but are misaligned with how visual ideas develop. T2I systems generate outputs that make implicit visual decisions on behalf of the user, often introduce fine-grained details that can anchor users prematurely and limit their ability to keep options open early on, and cause unintended changes during editing that are difficult to correct and reduce users' sense of control. To address these concerns, we present Creo, a multi-stage T2I system that scaffolds image generation by progressing from rough sketches to high-resolution outputs, exposing intermediary abstractions where users can make incremental changes. Sketch-like abstractions invite user editing and allow users to keep design options open when ideas are still forming due to their provisional nature. Each stage in Creo can be modified with manual changes and AI-assisted operations, enabling fine-grained, step-wise control through a locking mechanism that preserves prior decisions so subsequent edits affect only specified regions or attributes. Users remain in the loop, making and verifying decisions across stages, while the system applies diffs instead of regenerating full images, reducing drift as fidelity increases. A comparative study with a one-shot baseline shows that participants felt stronger ownership over Creo outputs, as they were able to trace their decisions in building up the image. Furthermore, embedding-based analysis indicates that Creo outputs are less homogeneous than one-shot results. These findings suggest that multi-stage generation, combined with intermediate control and decision locking, is a key design principle for improving controllability, user agency, creativity, and output diversity in generative systems.