Official implementation of "MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling"

WebUI extension for ControlNet

Nightly release of ControlNet 1.1

Let us control diffusion models!

Select a portrait, click to move the head around (please use your own space / GPU!)

[ECCV 2024, Oral] DynamiCrafter: Animating Open-domain Images with Video Diffusion Priors

Visualize PyTorch tensors with a single line of code.

Fundamentals of Digital Media Technology(04713901) | Peking University ECE Course Materials

Code for "GVHMR: World-Grounded Human Motion Recovery via Gravity-View Coordinates", Siggraph Asia 2024

text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

🔖 Curated list of video object segmentation (VOS) papers, datasets, and projects.

[CVPR 2024] Code release for "InstanceDiffusion: Instance-level Control for Image Generation"

Officail Implementation for "Cross-Image Attention for Zero-Shot Appearance Transfer"

Diffusion Model-Based Image Editing: A Survey (arXiv)

A Survey of Image Editing

Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2

【ICLR 2024🔥】 Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment

AL-Ref-SAM 2: Unleashing the Temporal-Spatial Reasoning Capacity of GPT for Training-Free Audio and Language Referenced Video Object Segmentation

Official implementation of MotionClone: Training-Free Motion Cloning for Controllable Video Generation

[ICLR 2024] Official pytorch implementation of "ControlVideo: Training-free Controllable Text-to-Video Generation"

DECA: Detailed Expression Capture and Animation (SIGGRAPH 2021)

Open-Set Grounded Text-to-Image Generation

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use th…

[CVPR2024] MotionEditor is the first diffusion-based model capable of video motion editing.

Ground-A-Video: Zero-shot Grounded Video Editing using Text-to-image Diffusion Models (ICLR 2024)

[ECCV 2024] DragAnything: Motion Control for Anything using Entity Representation

Video-P2P: Video Editing with Cross-attention Control

[CVPR24] Official Implementation of 'A Video is Worth 256 Bases: Spatial-Temporal Expectation-Maximization Inversion for Zero-Shot Video Editing'