-
Stability.ai, Eleuther.ai
- Seattle, WA
- https://dmarx.github.io
- @DigThatData
ML Video
[ECCV2024] Make a Cheap Scaling: A Self-Cascade Diffusion Model for Higher-Resolution Adaptation
UniEdit: A Unified Tuning-Free Framework for Video Motion and Appearance Editing
[CVPR 2024] Official Implementation of "Seamless Human Motion Composition with Blended Positional Encodings".
ComfyUI nodes for training AnimateDiff motion loras
Official implementation of UniCtrl: Improving the Spatiotemporal Consistency of Text-to-Video Diffusion Models via Training-Free Unified Attention Control
[CVPR 2024] FRESCO: Spatial-Temporal Correspondence for Zero-Shot Video Translation
StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text
DynamiCrafter that works natively with ComfyUI's nodes, optimizations, and more.
[CVPR 2024] Official Code for "AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation
DreamPhysics: Learning Physical Properties of Dynamic 3D Gaussians from Video Diffusion Priors
Animate124: Animating One Image to 4D Dynamic Scene
Official implementation of FIFO-Diffusion: Generating Infinite Videos from Text without Training
[SIGGRAPH Asia 2024, Journal Track] ToonCrafter: Generative Cartoon Interpolation
[CVPR 2024] On the Content Bias in Fréchet Video Distance
Hallo: Hierarchical Audio-Driven Visual Synthesis for Portrait Image Animation
[CVPR'23] Learning Neural Parametric Head Models
VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs
Official Code for "SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation"
Code for the paper MultiPhys: Multi-Person Physics-aware 3D Motion Estimation (CVPR 2024)
Code for Paper "UniAnimate: Taming Unified Video Diffusion Models for Consistent Human Image Animation".
High-Quality Human Motion Video Generation with Confidence-aware Pose Guidance
code for "Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion"
Official implementation of the paper "Gaussian in the Wild: 3D Gaussian Splatting for Unconstrained Image Collections"
[ECCV 2024] Be-Your-Outpainter https://arxiv.org/abs/2403.13745