# Training-Free Consistent Text-to-Image Generation

arXiv: https://arxiv.org/abs/2402.03286 · HTML: https://mlsanity.com/paper/2402.03286/

## Key facts

- Cited by 125 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 55 references that are in the map.
- First posted on arXiv 5 Feb 2024.

## Builds on (most cited first, 30 of 42)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [Multi-Concept Customization of Text-to-Image Diffusion](https://mlsanity.com/paper/2212.04488/) (2022)
- [MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing](https://mlsanity.com/paper/2304.08465/) (2023)
- [Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2301.13826/) (2023)
- [Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation](https://mlsanity.com/paper/2311.17117/) (2023)
- [Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators](https://mlsanity.com/paper/2303.13439/) (2023)
- [Zero-shot Image-to-Image Translation](https://mlsanity.com/paper/2302.03027/) (2023)
- [FateZero: Fusing Attentions for Zero-shot Text-based Video Editing](https://mlsanity.com/paper/2303.09535/) (2023)
- [Emergent Correspondence from Image Diffusion](https://mlsanity.com/paper/2306.03881/) (2023)
- [BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing](https://mlsanity.com/paper/2305.14720/) (2023)
- [TokenFlow: Consistent Diffusion Features for Consistent Video Editing](https://mlsanity.com/paper/2307.10373/) (2023)
- [InstantBooth: Personalized Text-to-Image Generation without Test-Time Finetuning](https://mlsanity.com/paper/2304.03411/) (2023)
- [MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model](https://mlsanity.com/paper/2311.16498/) (2023)
- [Pix2Video: Video Editing using Image Diffusion](https://mlsanity.com/paper/2303.12688/) (2023)
- [A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence](https://mlsanity.com/paper/2305.15347/) (2023)
- [Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models](https://mlsanity.com/paper/2305.18292/) (2023)
- [An Edit Friendly DDPM Noise Space: Inversion and Manipulations](https://mlsanity.com/paper/2304.06140/) (2023)
- [Break-A-Scene: Extracting Multiple Concepts from a Single Image](https://mlsanity.com/paper/2305.16311/) (2023)
- [Style Aligned Image Generation via Shared Attention](https://mlsanity.com/paper/2312.02133/) (2023)
- [Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence](https://mlsanity.com/paper/2305.14334/) (2023)
- [Splicing ViT Features for Semantic Appearance Transfer](https://mlsanity.com/paper/2201.00424/) (2022)
- [Encoder-based Domain Tuning for Fast Personalization of Text-to-Image Models](https://mlsanity.com/paper/2302.12228/) (2023)
- [FreeU: Free Lunch in Diffusion U-Net](https://mlsanity.com/paper/2309.11497/) (2023)
- [DragonDiffusion: Enabling Drag-style Manipulation on Diffusion Models](https://mlsanity.com/paper/2307.02421/) (2023)
- [Key-Locked Rank One Editing for Text-to-Image Personalization](https://mlsanity.com/paper/2305.01644/) (2023)

## Built on by (most cited first, 30 of 125)

- [StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation](https://mlsanity.com/paper/2405.01434/) (2024)
- [Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformers](https://mlsanity.com/paper/2405.05945/) (2024)
- [Emu3.5: Native Multimodal Models are World Learners](https://mlsanity.com/paper/2510.26583/) (2025)
- [Stable Flow: Vital Layers for Training-Free Image Editing](https://mlsanity.com/paper/2411.14430/) (2024)
- [MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequence](https://mlsanity.com/paper/2407.16655/) (2024)
- [SEED-Story: Multimodal Long Story Generation with Large Language Model](https://mlsanity.com/paper/2407.08683/) (2024)
- [Multi-subject Open-set Personalization in Video Generation](https://mlsanity.com/paper/2501.06187/) (2025)
- [TurboEdit: Text-Based Image Editing Using Few-Step Diffusion Models](https://mlsanity.com/paper/2408.00735/) (2024)
- [MoA: Mixture-of-Attention for Subject-Context Disentanglement in Personalized Image Generation](https://mlsanity.com/paper/2404.11565/) (2024)
- [Large-Scale Text-to-Image Model with Inpainting is a Zero-Shot Subject-Driven Image Generator](https://mlsanity.com/paper/2411.15466/) (2024)
- [Make It Count: Text-to-Image Generation with an Accurate Number of Objects](https://mlsanity.com/paper/2406.10210/) (2024)
- [DreamStory: Open-Domain Story Visualization by LLM-Guided Multi-Subject Consistent Diffusion](https://mlsanity.com/paper/2407.12899/) (2024)
- [Add-it: Training-Free Object Insertion in Images With Pretrained Diffusion Models](https://mlsanity.com/paper/2411.07232/) (2024)
- [StoryMem: Multi-shot Long Video Storytelling with Memory](https://mlsanity.com/paper/2512.19539/) (2025)
- [Looking Backward: Streaming Video-to-Video Translation with Feature Banks](https://mlsanity.com/paper/2405.15757/) (2024)
- [ShotAdapter: Text-to-Multi-Shot Video Generation with Diffusion Models](https://mlsanity.com/paper/2505.07652/) (2025)
- [StoryMaker: Towards Holistic Consistent Characters in Text-to-image Generation](https://mlsanity.com/paper/2409.12576/) (2024)
- [EchoShot: Multi-Shot Portrait Video Generation](https://mlsanity.com/paper/2506.15838/) (2025)
- [Generating Multi-Image Synthetic Data for Text-to-Image Customization](https://mlsanity.com/paper/2502.01720/) (2025)
- [CharacterFactory: Sampling Consistent Characters with GANs for Diffusion Models](https://mlsanity.com/paper/2404.15677/) (2024)
- [Personalize Anything for Free with Diffusion Transformer](https://mlsanity.com/paper/2503.12590/) (2025)
- [DiffUHaul: A Training-Free Method for Object Dragging in Images](https://mlsanity.com/paper/2406.01594/) (2024)
- [Nested Attention: Semantic-aware Attention Values for Concept Personalization](https://mlsanity.com/paper/2501.01407/) (2025)
- [TheaterGen: Character Management with LLM for Consistent Multi-turn Image Generation](https://mlsanity.com/paper/2404.18919/) (2024)
- [Where's Waldo: Diffusion Features for Personalized Segmentation and Retrieval](https://mlsanity.com/paper/2405.18025/) (2024)
- [CharaConsist: Fine-Grained Consistent Character Generation](https://mlsanity.com/paper/2507.11533/) (2025)
- [From Parts to Whole: A Unified Reference Framework for Controllable Human Image Generation](https://mlsanity.com/paper/2404.15267/) (2024)
- [Story2Board: A Training-Free Approach for Expressive Storyboard Generation](https://mlsanity.com/paper/2508.09983/) (2025)
- [AnyStory: Towards Unified Single and Multiple Subject Personalization in Text-to-Image Generation](https://mlsanity.com/paper/2501.09503/) (2025)
- [OneActor: Consistent Character Generation via Cluster-Conditioned Guidance](https://mlsanity.com/paper/2404.10267/) (2024)

## Abstract (arXiv)

Text-to-image models offer a new level of creative flexibility by allowing users to guide the image generation process through natural language. However, using these models to consistently portray the same subject across diverse prompts remains challenging. Existing approaches fine-tune the model to teach it new words that describe specific user-provided subjects or add image conditioning to the model. These methods require lengthy per-subject optimization or large-scale pre-training. Moreover, they struggle to align generated images with text prompts and face difficulties in portraying multiple subjects. Here, we present ConsiStory, a training-free approach that enables consistent subject generation by sharing the internal activations of the pretrained model. We introduce a subject-driven shared attention block and correspondence-based feature injection to promote subject consistency between images. Additionally, we develop strategies to encourage layout diversity while maintaining subject consistency. We compare ConsiStory to a range of baselines, and demonstrate state-of-the-art performance on subject consistency and text alignment, without requiring a single optimization step. Finally, ConsiStory can naturally extend to multi-subject scenarios, and even enable training-free personalization for common objects.