# Dual Inversion for Text-to-Image Diffusion Models: From Both Prompt and Noise Perspectives

arXiv: https://arxiv.org/abs/2607.26735 · HTML: https://mlsanity.com/paper/2607.26735/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 17 of its 39 references that are in the map.
- First posted on arXiv 29 Jul 2026.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 17 of 17)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [Golden Noise for Diffusion Models: A Learning Framework](https://mlsanity.com/paper/2411.09502/) (2024)
- [Language Model Inversion](https://mlsanity.com/paper/2311.13647/) (2023)
- [CAD-Recode: Reverse Engineering CAD Code from Point Clouds](https://mlsanity.com/paper/2412.14042/) (2024)
- [SleeperMark: Towards Robust Watermark against Fine-Tuning Text-to-image Diffusion Models](https://mlsanity.com/paper/2412.04852/) (2024)
- [Text Embedding Inversion Security for Multilingual Language Models](https://mlsanity.com/paper/2401.12192/) (2024)
- [Source Prompt Disentangled Inversion for Boosting Image Editability with Diffusion Models](https://mlsanity.com/paper/2403.11105/) (2024)
- [Multi-Class Textual-Inversion Secretly Yields a Semantic-Agnostic Classifier](https://mlsanity.com/paper/2410.22317/) (2024)
- [Visually Guided Decoding: Gradient-Free Hard Prompt Inversion with Language Models](https://mlsanity.com/paper/2505.08622/) (2025)
- [Unpaired Multi-Domain Histopathology Virtual Staining using Dual Path Prompted Inversion](https://mlsanity.com/paper/2412.11106/) (2024)
- [Segment Anyword: Mask Prompt Inversion for Open-Set Grounded Segmentation](https://mlsanity.com/paper/2505.17994/) (2025)
- [InvSeg: Test-Time Prompt Inversion for Semantic Segmentation](https://mlsanity.com/paper/2410.11473/) (2024)
- [When and Where do Data Poisons Attack Textual Inversion?](https://mlsanity.com/paper/2507.10578/) (2025)

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

- [Learning Normal Diffusion Dynamics for Backdoor Defense in Text-to-Image Models](https://mlsanity.com/paper/2609.39548/) (2026)

## Abstract (arXiv)

Prompt inversion, as a typical reverse engineering technique, enables text-to-image (T2I) diffusion models to generate the desired target images without extensive prompt engineering. However, existing prompt inversion methods suffer from significant limitations: (1) gradient-based methods are unstable and uninterpretable, often resulting in generated images with severe artifacts; (2) gradient-free methods yield human-readable prompts but still fail to preserve visual fidelity due to the lack of fine-grained detail alignment. We contend that the limitations stem from treating prompt inversion as a sufficient condition for reverse engineering, ignoring the critical role of the latent noise that encodes structural information. Consequently, we propose Dualin (Dual inversion), a two-stage method that jointly recovers both the semantic prompt and latent noise of the target image. In the first stage, we integrate vision-language model, CLIP and large language model to invert a faithful, human-interpretable hard prompt. In the second stage, unconditional DDIM inversion reconstructs the exact latent noise of the target image, guaranteeing the consistency at the structural information level. Theoretically, we prove that the inverted noise enables flexible image editing without re-optimization. Extensive experiments on diverse datasets demonstrate that Dualin simultaneously generates high-quality inverted prompts and achieves state-of-the-art image fidelity. Additionally, Dualin can establish a robust foundation for the precise and controllable image editing.