Current video-to-4D methods struggle with complex topology changes, transparent materials, thin structures, and inner surfaces. We present Helix4D, a dynamic mesh generation framework by inheriting the expressive representation of Trellis2, adapting …
Video diffusion alignment has been heavily relied on scalar rewards. These rewards are typically derived from learned reward models in human preference datasets, requiring additional training and extensive collection. Moreover, scalar rewards provide …
Existing personalized image generators still struggle to preserve multiple reference identities in natural and coherent multi-human generations. To address these limitations, we present CanvasComposer, an interactive framework for personalized group …
While personalizing Image-to-Video (I2V) diffusion models with specific visual effects is increasingly demanded for high-end generation, current practice requires training a separate Low-Rank Adaptation (LoRA) module for each effect, incurring …
While modern diffusion models excel at generating high-quality and diverse images, they still struggle with high-fidelity compositional and multimodal control. We introduce Canvas-to-Image, a unified framework that consolidates these heterogeneous …
EasyV2V presents a high-quality instruction-based video editing framework that enables intuitive and precise video manipulation through natural language instructions. Our approach combines state-of-the-art video generation models with advanced …
Visual concept personalization aims to transfer only specific image attributes, such as identity, expression, lighting, and style, into unseen contexts. However, existing methods rely on holistic embeddings from general-purpose image encoders, which …
Adapter modules have emerged as a parameter-efficient method for fine-tuning large pre-trained models to downstream tasks. However, adapter training can suffer from shortcut learning, where the model exploits spurious correlations in the training …
Generating high-fidelity images of humans with fine-grained control over attributes such as hairstyle and clothing remains a core challenge in personalized text-to-image synthesis. While prior methods emphasize identity preservation from a reference …
This paper presents ThinkDiff, a novel alignment paradigm that enables multimodal in-context understanding and reasoning capabilities in text-to-image diffusion models by integrating the capabilities of vision-language models (VLMs). Directly …