English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

This paper explores advancements in high-fidelity personalized imagegeneration through the utilization of pre-trained text-to-image diffusionmodels. While previous approaches have made significant strides in generatingversatile scenes based on text descriptions and a few input images, challengespersist in maintaining the subject fidelity within the generated images. Inthis work, we introduce an innovative algorithm named HiFi Tuner to enhance theappearance preservation of objects during personalized image generation. Ourproposed method employs a parameter-efficient fine-tuning framework, comprisinga denoising process and a pivotal inversion process. Key enhancements includethe utilization of mask guidance, a novel parameter regularization technique,and the incorporation of step-wise subject representations to elevate thesample fidelity. Additionally, we propose a reference-guided generationapproach that leverages the pivotal inversion of a reference image to mitigateunwanted subject variations and artifacts. We further extend our method to anovel image editing task: substituting the subject in an image through textualmanipulations. Experimental evaluations conducted on the DreamBooth datasetusing the Stable Diffusion model showcase promising results. Fine-tuning solelyon textual embeddings improves CLIP-T score by 3.6 points and improves DINOscore by 9.6 points over Textual Inversion. When fine-tuning all parameters,HiFi Tuner improves CLIP-T score by 1.2 points and improves DINO score by 1.2points over DreamBooth, establishing a new state of the art.

HiFi Tuner: High-Fidelity Subject-Driven Fine-Tuning for Diffusion Models