# AutoStudio: Crafting Consistent Subjects in Multi-turn Interactive Image Generation

arXiv: https://arxiv.org/abs/2406.01388 · HTML: https://mlsanity.com/paper/2406.01388/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 48 references that are in the map.
- First posted on arXiv 3 Jun 2024.

## Builds on (most cited first, 30 of 39)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2308.06721/) (2023)
- [GLIGEN: Open-Set Grounded Text-to-Image Generation](https://mlsanity.com/paper/2301.07093/) (2023)
- [Large Language Model based Multi-Agents: A Survey of Progress and Challenges](https://mlsanity.com/paper/2402.01680/) (2024)
- [Scaling up GANs for Text-to-Image Synthesis](https://mlsanity.com/paper/2303.05511/) (2023)
- [Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models](https://mlsanity.com/paper/2305.18292/) (2023)
- [LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generation](https://mlsanity.com/paper/2303.17189/) (2023)
- [StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation](https://mlsanity.com/paper/2405.01434/) (2024)
- [LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models](https://mlsanity.com/paper/2305.13655/) (2023)
- [Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs](https://mlsanity.com/paper/2401.11708/) (2024)
- [Making LLaMA SEE and Draw with SEED Tokenizer](https://mlsanity.com/paper/2310.01218/) (2023)
- [Intelligent Grimm -- Open-ended Visual Storytelling via Latent Diffusion Models](https://mlsanity.com/paper/2306.00973/) (2023)
- [TaleCrafter: Interactive Story Visualization with Multiple Characters](https://mlsanity.com/paper/2305.18247/) (2023)
- [The Chosen One: Consistent Characters in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2311.10093/) (2023)
- [MoA: Mixture-of-Attention for Subject-Context Disentanglement in Personalized Image Generation](https://mlsanity.com/paper/2404.11565/) (2024)
- [Risks of AI Scientists: Prioritizing Safeguarding Over Autonomy](https://mlsanity.com/paper/2402.04247/) (2024)

## Built on by (most cited first, 20 of 20)

- [DreamStory: Open-Domain Story Visualization by LLM-Guided Multi-Subject Consistent Diffusion](https://mlsanity.com/paper/2407.12899/) (2024)
- [DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation](https://mlsanity.com/paper/2412.07589/) (2024)
- [Unbounded: A Generative Infinite Game of Character Life Simulation](https://mlsanity.com/paper/2410.18975/) (2024)
- [Story-Iter: A Training-free Iterative Paradigm for Long Story Visualization](https://mlsanity.com/paper/2410.06244/) (2024)
- [StoryWeaver: A Unified World Model for Knowledge-Enhanced Story Character Customization](https://mlsanity.com/paper/2412.07375/) (2024)
- [FilmWeaver: Weaving Consistent Multi-Shot Videos with Cache-Guided Autoregressive Diffusion](https://mlsanity.com/paper/2512.11274/) (2025)
- [Object Isolated Attention for Consistent Story Visualization](https://mlsanity.com/paper/2503.23353/) (2025)
- [FilmComposer: LLM-Driven Music Production for Silent Film Clips](https://mlsanity.com/paper/2503.08147/) (2025)
- [ViStoryBench: Comprehensive Benchmark Suite for Story Visualization](https://mlsanity.com/paper/2505.24862/) (2025)
- [VisAgent: Narrative-Preserving Story Visualization Framework](https://mlsanity.com/paper/2503.02399/) (2025)
- [Long-horizon Visual Instruction Generation with Logic and Attribute Self-reflection](https://mlsanity.com/paper/2503.13500/) (2025)
- [Improving Multi-Subject Consistency in Open-Domain Image Generation with Isolation and Reposition Attention](https://mlsanity.com/paper/2411.19261/) (2024)
- [CANVAS: Continuity-Aware Narratives via Visual Agentic Storyboarding](https://mlsanity.com/paper/2604.13452/) (2026)
- [CharCom: Composable Identity Control for Multi-Character Story Illustration](https://mlsanity.com/paper/2510.10135/) (2025)
- [Plot'n Polish: Zero-shot Story Visualization and Disentangled Editing with Text-to-Image Diffusion Models](https://mlsanity.com/paper/2509.04446/) (2025)
- [DreamingComics: A Story Visualization Pipeline via Subject and Layout Customized Generation using Video Models](https://mlsanity.com/paper/2512.01686/) (2025)
- [Audit & Repair: An Agentic Framework for Consistent Story Visualization in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2506.18900/) (2025)
- [AnimeAdapter: A Modular Adapter for Appearance-Consistent Anime Character Generation](https://mlsanity.com/paper/2605.20237/) (2026)
- [Can Image Models Imagine Time? ImageTime: A Novel Benchmark for Probing Visual World Modeling Through Spatiotemporal Consistency](https://mlsanity.com/paper/2606.10620/) (2026)
- [ELECT: Settling Identity Before Rendering for Scalable Story Visualization](https://mlsanity.com/paper/2610.15555/) (2026)

## Abstract (arXiv)

As cutting-edge Text-to-Image (T2I) generation models already excel at producing remarkable single images, an even more challenging task, i.e., multi-turn interactive image generation begins to attract the attention of related research communities. This task requires models to interact with users over multiple turns to generate a coherent sequence of images. However, since users may switch subjects frequently, current efforts struggle to maintain subject consistency while generating diverse images. To address this issue, we introduce a training-free multi-agent framework called AutoStudio. AutoStudio employs three agents based on large language models (LLMs) to handle interactions, along with a stable diffusion (SD) based agent for generating high-quality images. Specifically, AutoStudio consists of (i) a subject manager to interpret interaction dialogues and manage the context of each subject, (ii) a layout generator to generate fine-grained bounding boxes to control subject locations, (iii) a supervisor to provide suggestions for layout refinements, and (iv) a drawer to complete image generation. Furthermore, we introduce a Parallel-UNet to replace the original UNet in the drawer, which employs two parallel cross-attention modules for exploiting subject-aware features. We also introduce a subject-initialized generation method to better preserve small subjects. Our AutoStudio hereby can generate a sequence of multi-subject images interactively and consistently. Extensive experiments on the public CMIGBench benchmark and human evaluations show that AutoStudio maintains multi-subject consistency across multiple turns well, and it also raises the state-of-the-art performance by 13.65% in average Frechet Inception Distance and 2.83% in average character-character similarity.