Search papers, labs, and topics across Lattice.
The paper addresses the challenge of harmonizing pasted objects into new contexts within diffusion-based image editing, focusing on prompt-free editing with precise spatial control. They observe that attention maps govern preservation vs. adaptation and introduce LooseRoPE, a saliency-guided modulation of rotational positional encoding (RoPE) to control the attention field of view. By relaxing RoPE, the method balances identity retention and contextual blending, achieving seamless compositional results.
Steer diffusion models to seamlessly blend pasted objects into new contexts without prompts by selectively loosening positional encoding constraints based on saliency.
Recent diffusion-based image editing methods commonly rely on text or high-level instructions to guide the generation process, offering intuitive but coarse control. In contrast, we focus on explicit, prompt-free editing, where the user directly specifies the modification by cropping and pasting an object or sub-object into a chosen location within an image. This operation affords precise spatial and visual control, yet it introduces a fundamental challenge: preserving the identity of the pasted object while harmonizing it with its new context. We observe that attention maps in diffusion-based editing models inherently govern whether image regions are preserved or adapted for coherence. Building on this insight, we introduce LooseRoPE, a saliency-guided modulation of rotational positional encoding (RoPE) that loosens the positional constraints to continuously control the attention field of view. By relaxing RoPE in this manner, our method smoothly steers the model's focus between faithful preservation of the input image and coherent harmonization of the inserted object, enabling a balanced trade-off between identity retention and contextual blending. Our approach provides a flexible and intuitive framework for image editing, achieving seamless compositional results without textual descriptions or complex user input.