Multi-reference image generation requires preserving the appearance of multiple subjects while composing them into a coherent scene. However, existing diffusion transformers commonly encode references as dense visual token grids and jointly process them with global attention, making conditioning increasingly expensive...
JAx (Just Align x), a prediction-supervision method that aligns clean-image predictions across noise levels, shows that prediction-space supervision provides a simple and principled alternative to representation alignment for pixel-space generative models.
Yu-Yao Zhang, Yu-Wei Hu, Zi-Yang Mai et al.· 0 citations
This work proposes a pixel-grounded super-resolution (PGSR) framework that preserves LR-observed pixel evidence before VAE compression and reuses it throughout restoration and improves the realism--fidelity trade-off and produces more faithful, visually convincing results than existing latent generative SR approaches.
Yu Shi, Yu-Yao Zhang, Yu-Wing Tai· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.