Hritikbansal / videophy
Video Generation, Physical Commonsense, Semantic Adherence, VideoCon-Physics
☆33Updated last month
Related projects: ⓘ
- [ECCV 2024 Oral] ConceptExpress: Harnessing Diffusion Models for Single-image Unsupervised Concept Extraction☆29Updated last month
- Official code for paper: Text-to-Image Rectified Flow as Plug-and-Play Priors☆69Updated last week
- Motion Consistency Model: Accelerating Video Diffusion with Disentangled Motion-Appearance Distillation☆38Updated last month
- T2VScore: Towards A Better Metric for Text-to-Video Generation☆76Updated 5 months ago
- ☆36Updated 9 months ago
- ☆38Updated 9 months ago
- Navigate dreamscapes with a click – your chosen point guides the drone’s flight in a thrilling visual journey.☆37Updated 8 months ago
- ☆19Updated last week
- ☆21Updated last month
- [CVPR 2024] SHAP-EDITOR: Instruction-guided Latent 3D Editing in Seconds☆29Updated 3 months ago
- Experiencing lightning fast (~1s) and accurate drag-based image editing☆17Updated this week
- FlowZero: Zero-Shot Text-to-Video Synthesis with LLM-Driven Dynamic Scene Syntax☆17Updated 9 months ago
- [ICML 2024] Compositional Image Decomposition with Diffusion Models☆37Updated 2 months ago
- Learning Naturally Aggregated Appearance for Efficient 3D Editing☆34Updated 8 months ago
- Code for paper Background Prompting for Improved Object Depth☆29Updated last year
- ☆13Updated 2 months ago
- Code Release for the paper "Make-A-Story: Visual Memory Conditioned Consistent Story Generation" in CVPR 2023☆37Updated last year
- code for "TVG: A Training-free Transition Video Generation Method with Diffusion Models"☆28Updated last month
- Videoshop: Localized Semantic Video Editing with Noise-Extrapolated Diffusion Inversion☆28Updated last month
- ☆56Updated 2 months ago
- The official code for Tender☆30Updated last week
- ☆23Updated 3 months ago
- Visual Programming for Text-to-Image Generation and Evaluation (NeurIPS 2023)☆51Updated last year
- [ICCV 2023] Code for "Multi-task View Synthesis with Neural Radiance Fields"☆11Updated 11 months ago
- Dataset splits and evaluation code for the paper "Benchmark for Compositional Text-to-Image Synthesis" (NeurIPS 2021)☆45Updated 2 years ago
- [ECCV 2024] Official repository for "DataDream: Few-shot Guided Dataset Generation"☆16Updated last month
- Official repo of "MotionLLM: Multimodal Motion-Language Learning with Large Language Models"☆23Updated 3 months ago
- Official implementation of "Divide & Bind Your Attention for Improved Generative Semantic Nursing" (BMVC 2023 Oral)☆33Updated 7 months ago
- Code for FreeTraj, a tuning-free method for trajectory-controllable video generation☆85Updated last month
- Code for the paper "GenHowTo: Learning to Generate Actions and State Transformations from Instructional Videos" published at CVPR 2024☆39Updated 6 months ago