Search papers, labs, and topics across Lattice.
ResetEdit addresses the challenge of precise text-guided image editing by reconstructing the original latent used during image generation, which is typically unavailable in inversion-based editing methods. They achieve this by embedding recoverable latent information into the diffusion trajectory during generation and extracting it during inversion to approximate the true starting state. A lightweight latent optimization module further refines the reconstructed latent, leading to improved controllability and visual fidelity compared to existing methods.
Forget imperfect inversions – ResetEdit lets you edit generated images with the same latent that created them, unlocking unprecedented precision and control.
Recent advances in diffusion models have enabled high-quality image generation, leading to increasing demand for post-generation editing that modifies local regions while preserving global structure. Achieving such flexible and precise editing requires a high-quality starting point, a latent representation that provides both the freedom needed for diverse modifications and the precision required for fine-grained, region-specific control. However, existing inversion-based approaches such as DDIM inversion often yield unsatisfactory starting latents, resulting in degraded edit fidelity and structural inconsistency. Ideally, the most suitable editing anchor should be the original latent used during the generation process, as it inherently captures the scene's structure and semantics. Yet, storing this latent for every generated image is impractical due to massive storage and retrieval costs. To address this challenge, we propose ResetEdit, a proactive diffusion editing framework that embeds recoverable latent information directly into the generation process. By injecting the discrepancy between the clean and diffused latents into the diffusion trajectory and extracting it during inversion, ResetEdit reconstructs a resettable latent that closely approximates the true starting state. Additionally, a lightweight latent optimization module compensates for reconstruction bias caused by VAE asymmetry. Built upon Stable Diffusion, ResetEdit integrates seamlessly with existing tuning-free editing methods and consistently outperforms state-of-the-art baselines in both controllability and visual fidelity.
NUS