Lists (7)
Sort Name ascending (A-Z)
Stars
[ACM MM24] MotionMaster: Training-free Camera Motion Transfer For Video Generation
Official PyTorch implementation of "I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image", ECCV 2020
Towards Localized Fine-Grained Control for Facial Expression Generation
Official PyTorch Implementation of "FlowTurbo: Towards Real-time Flow-Based Image Generation with Velocity Refiner"
The First Multimodal Seach Engine Pipeline and Benchmark for LMMs
Code to easily try 30 (and growing) different image matching methods
A web app made to let mobile users run ComfyUI workflows.
👆Pytorch implementation of "Ctrl-V: Higher Fidelity Video Generation with Bounding-Box Controlled Object Motion"
Vision-Augmented Retrieval and Generation (VARAG) - Vision first RAG Engine
Official implementation of the paper "DreamWaltz-G: Expressive 3D Gaussian Avatars from Skeleton-Guided 2D Diffusion".
Official implementation of "En3D: An Enhanced Generative Model for Sculpting 3D Humans from 2D Synthetic Data"
Official implementation of "MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling"
Image-to-Image Translation in PyTorch
Synthesizing and manipulating 2048x1024 images with conditional GANs
A modified version of origin Magic Animate (https://showlab.github.io/magicanimate/)
[ECCV 2024] HumanRefiner: Benchmarking Abnormal Human Generation and Refining with Coarse-to-fine Pose-Reversible Guidance
Official pytorch repository for “Guidance with Spherical Gaussian Constraint for Conditional Diffusion”
Official repository of NEFTune: Noisy Embeddings Improves Instruction Finetuning
Official Repo for Tuning-Free Noise Rectification for High Fidelity Image-to-Video Generation
Official repo for Hierarchical Masked 3D Diffusion Model for Video Outpainting
A collection of awesome video generation studies.
open-o1: Using GPT-4o with CoT to Create o1-like Reasoning Chains
A curated list of video stabilization methods
[SIGGRAPH 2024] Diffusion Texture Painting
Align Anything: Training All-modality Model with Feedback
[ECCV2024] Towards Reliable Advertising Image Generation Using Human Feedback