6 papers · 1 filter
StoryMem: Multi-shot Long Video Storytelling with Memory
Kaiwen Zhang, Liming Jiang, Angtian Wang +6
Visual storytelling requires generating multi-shot videos with cinematic quality and long-range consistency. Inspired by human memory, we propose StoryMem, a paradigm that reformul…
InstructMoLE: Instruction-Guided Mixture of Low-rank Experts for Multi-Conditional Image Generation
Jinqi Xiao, Qing Yan, Liming Jiang +8
Parameter-Efficient Fine-Tuning of Diffusion Transformers (DiTs) for diverse, multi-conditional tasks often suffers from task interference when using monolithic adapters like LoRA.…
TGT: Text-Grounded Trajectories for Locally Controlled Video Generation
Guofeng Zhang, Angtian Wang, Jacob Zhiyuan Fang +8
Text-to-video generation has advanced rapidly in visual fidelity, whereas standard methods still have limited ability to control the subject composition of generated scenes. Prior…
Learning Joint ID-Textual Representation for ID-Preserving Image Synthesis
Zichuan Liu, Liming Jiang, Qing Yan +3
We propose a novel framework for ID-preserving generation using a multi-modal encoding strategy rather than injecting identity features via adapters into pre-trained models. Our me…
Flux Already Knows -- Activating Subject-Driven Image Generation without Training
Hao Kang, Stathi Fotiadis, Liming Jiang +5
We propose a simple yet effective zero-shot framework for subject-driven image generation using a vanilla Flux model. By framing the task as grid-based image completion and simply…
InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity
Liming Jiang, Qing Yan, Yumin Jia +3
Achieving flexible and high-fidelity identity-preserved image generation remains formidable, particularly with advanced Diffusion Transformers (DiTs) like FLUX. We introduce Infini…