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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Recent approaches such as ControlNet offer users fine-grained spatial controlover text-to-image (T2I) diffusion models. However, auxiliary modules have tobe trained for each type of spatial condition, model architecture, andcheckpoint, putting them at odds with the diverse intents and preferences ahuman designer would like to convey to the AI models during the contentcreation process. In this work, we present FreeControl, a training-freeapproach for controllable T2I generation that supports multiple conditions,architectures, and checkpoints simultaneously. FreeControl designs structureguidance to facilitate the structure alignment with a guidance image, andappearance guidance to enable the appearance sharing between images generatedusing the same seed. Extensive qualitative and quantitative experimentsdemonstrate the superior performance of FreeControl across a variety ofpre-trained T2I models. In particular, FreeControl facilitates convenienttraining-free control over many different architectures and checkpoints, allowsthe challenging input conditions on which most of the existing training-freemethods fail, and achieves competitive synthesis quality with training-basedapproaches.

FreeControl: Training-Free Spatial Control of Any Text-to-Image Diffusion Model with Any Condition