REVIEW 2 cited by
LoRA of Change: Learning to Generate LoRA for the Editing Instruction from A Single Before-After Image Pair
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
read the original abstract
In this paper, we propose the LoRA of Change (LoC) framework for image editing with visual instructions, i.e., before-after image pairs. Compared to the ambiguities, insufficient specificity, and diverse interpretations of natural language, visual instructions can accurately reflect users' intent. Building on the success of LoRA in text-based image editing and generation, we dynamically learn an instruction-specific LoRA to encode the "change" in a before-after image pair, enhancing the interpretability and reusability of our model. Furthermore, generalizable models for image editing with visual instructions typically require quad data, i.e., a before-after image pair, along with query and target images. Due to the scarcity of such quad data, existing models are limited to a narrow range of visual instructions. To overcome this limitation, we introduce the LoRA Reverse optimization technique, enabling large-scale training with paired data alone. Extensive qualitative and quantitative experiments demonstrate that our model produces high-quality images that align with user intent and support a broad spectrum of real-world visual instructions.
Forward citations
Cited by 2 Pith papers
-
Spanning the Visual Analogy Space with a Weight Basis of LoRAs
A learnable basis of LoRA adapters, mixed by an encoder at inference time, applies visual analogies to new images and beats single-adapter baselines on a custom benchmark.
-
PairEdit: Learning Semantic Variations for Exemplar-based Image Editing
PairEdit trains two LoRA adapters on a pretrained diffusion model to capture the semantic direction between paired source-target images, enabling text-free, controllable image editing from as few as one pair.
Discussion (0). Continue with ORCID to comment.