REVIEW 6 cited by
KV-Edit: Training-Free Image Editing for Precise Background Preservation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
abstract
Background consistency remains a significant challenge in image editing tasks. Despite extensive developments, existing works still face a trade-off between maintaining similarity to the original image and generating content that aligns with the target. Here, we propose KV-Edit, a training-free approach that uses KV cache in DiTs to maintain background consistency, where background tokens are preserved rather than regenerated, eliminating the need for complex mechanisms or expensive training, ultimately generating new content that seamlessly integrates with the background within user-provided regions. We further explore the memory consumption of the KV cache during editing and optimize the space complexity to $O(1)$ using an inversion-free method. Our approach is compatible with any DiT-based generative model without additional training. Experiments demonstrate that KV-Edit significantly outperforms existing approaches in terms of both background and image quality, even surpassing training-based methods. Project webpage is available at https://xilluill.github.io/projectpages/KV-Edit
Forward citations
Cited by 6 Pith papers
-
DNAEdit: Direct Noise Alignment for Text-Guided Rectified Flow Editing
Direct Noise Alignment iteratively moves a random Gaussian noise until the model's predicted velocity matches the straight-line velocity to the image, reducing inversion drift and giving the best reported fidelity-edi...
-
EraseLoRA: MLLM-Driven Foreground Exclusion and Background Subtype Aggregation for Dataset-Free Object Removal
EraseLoRA removes masked objects by having an MLLM separate target, non-target foreground, and background, then test-time LoRA optimization aggregates background subtypes to reconstruct the occluded region.
-
The Aging Multiverse: Generating Condition-Aware Facial Aging Tree via Training-Free Diffusion
A training-free diffusion framework creates condition-aware facial aging trees from one photo, balancing identity, age, and prompt-controlled attributes.
-
LMP: Leveraging Motion Prior in Zero-Shot Video Generation with Diffusion Transformer
LMP transfers motion from a reference video to newly generated videos in text-to-video and image-to-video settings without training, using attention maps in a frozen diffusion transformer.
-
Describe, Don't Dictate: Semantic Image Editing with Natural Language Intent
DescriptiveEdit turns semantic editing into reference-conditioned text-to-image generation, reporting state-of-the-art scores on the Emu Edit benchmark with a frozen backbone and about 75M trainable parameters.
-
DFVEdit: Conditional Delta Flow Vector for Zero-shot Video Editing
DFVEdit edits videos by iteratively subtracting a conditional delta flow vector, the difference between the model's predictions under the target and source prompts, from the latent representation of the source video.
Discussion (0). Sign in to comment.