DSE-VTG is proposed, a \underline{D}ual-\underline{S}ide \underline{E}nhancement framework that addresses both temporal dynamics and task-specific training without any task-specific training, and achieves state-of-the-art performance among training-free methods.
Subject-driven image personalization---generating new images that preserve the identity of one or several reference subjects in novel scenes---is a foundational capability for modern visual content creation. It is currently dominated by generalized methods that fine-tune a pretrained multimodal diffusion transformer (M...
This work proposes RIG (Regional Image-prompt Generation), a novel training-free framework for multi-reference personalized generation that significantly outperforms state-of-the-art adapter methods in terms of both personalization fidelity and text-layout alignment.
An uncertainty-aware variational latent anchoring module that dynamically selects informative frames and compresses cross-frame latents into a compact set of semantic anchors that achieves state-of-the-art inversion fidelity, editing quality, and temporal consistency, while reducing memory and runtime compared with pri...
Adapting video models to new tasks typically requires dedicated data curation and fine-tuning. While visual analogy provides a training-free alternative by specifying tasks in-context, it remains restricted to the image domain. To explore whether analogy-based methods can unify diverse video tasks and generalize to out...
KATok (Keep-or-Drop? Adaptive Tokenizer for Compact Video Representation), a transformer-based VAE that incorporates an adaptive token selector which is jointly learned with latent tokens that achieves strong reconstruction and generation quality at a state-of-the-art compression ratio.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
