6 papers
PureCC: Pure Learning for Text-to-Image Concept Customization
Zhichao Liao, Xiaole Xian, Qingyu Li +7
Existing concept customization methods have achieved remarkable outcomes in high-fidelity and multi-concept customization. However, they often neglect the influence on the original…
Beyond the Golden Data: Resolving the Motion-Vision Quality Dilemma via Timestep Selective Training
Xiangyang Luo, Qingyu Li, Yuming Li +6
Recent advances in video generation models have achieved impressive results. However, these models heavily rely on the use of high-quality data that combines both high visual quali…
AEGPO: Adaptive Entropy-Guided Policy Optimization for Diffusion Models
Yuming Li, Qingyu Li, Chengyu Bai +6
Reinforcement learning from human feedback (RLHF) shows promise for aligning diffusion and flow models, yet policy optimization methods such as GRPO suffer from inefficient and sta…
FilmWeaver: Weaving Consistent Multi-Shot Videos with Cache-Guided Autoregressive Diffusion
Xiangyang Luo, Qingyu Li, Xiaokun Liu +7
Current video generation models perform well at single-shot synthesis but struggle with multi-shot videos, facing critical challenges in maintaining character and background consis…
HumanAesExpert: Advancing a Multi-Modality Foundation Model for Human Image Aesthetic Assessment
Zhichao Liao, Xiaokun Liu, Wenyu Qin +6
Image Aesthetic Assessment (IAA) is a long-standing and challenging research task. However, its subset, Human Image Aesthetic Assessment (HIAA), has been scarcely explored. To brid…
SPF-Portrait: Towards Pure Text-to-Portrait Customization with Semantic Pollution-Free Fine-Tuning
Xiaole Xian, Zhichao Liao, Qingyu Li +6
Fine-tuning a pre-trained Text-to-Image (T2I) model on a tailored portrait dataset is the mainstream method for text-to-portrait customization. However, existing methods often seve…