Menghan Xia

7

Papers

272

Total Citations

Papers (7)

ScaleCrafter: Tuning-free Higher-Resolution Visual Generation with Diffusion Models

Improving Video Generation with Human Feedback

Make a Cheap Scaling: A Self-Cascade Diffusion Model for Higher-Resolution Adaptation

Noise Calibration: Plug-and-play Content-Preserving Video Enhancement using Pre-trained Video Diffusion Models

PatchVSR: Breaking Video Diffusion Resolution Limits with Patch-wise Video Super-Resolution

VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models

ReCamMaster: Camera-Controlled Generative Rendering from A Single Video