2 papers
cs.CV2026
FrameForge: Harnessing Priors of Video Foundation Models for Unified Image Generation
Yijing Lin, Zhendong Mao, Mengqi Huang +2
Unified conditional image generation requires a single model to preserve different aspects of a visual input while producing a target image that follows textual guidance. Pretraine…
cs.CV2025
RealGeneral: Unifying Visual Generation via Temporal In-Context Learning with Video Models
Yijing Lin, Mengqi Huang, Shuhan Zhuang +1
Unifying diverse image generation tasks within a single framework remains a fundamental challenge in visual generation. While large language models (LLMs) achieve unification throu…