The official implementation of SigAsia'25 paper "Virtually Being: Customizing Camera-Controllable Video Diffusion Models with Multi-View Performance Captures"

A fast AI Video Generator for the GPU Poor. Supports Wan 2.1/2.2, Qwen Image, Hunyuan Video, LTX Video and Flux.

AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers

Benchmark dataset and code of MSRVTT-Personalization

Code for ICLR 2025 Paper "GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-time Alignment"

[CVPR 2025 Highlight🔥] Identity-Preserving Text-to-Video Generation by Frequency Decomposition

[ECCV 2024] OMG: Occlusion-friendly Personalized Multi-concept Generation In Diffusion Models

A set of nodes to edit videos using the Hunyuan Video model

The official implementation of CVPR'25 Oral paper "Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise"

MuDI: Identity Decoupling for Multi-Subject Personalization of Text-to-Image Models (NeurIPS 2024)

📹 A more flexible framework that can generate videos at any resolution and creates videos from images.

Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise

[NeurIPS D&B Track 2024] Official implementation of HumanVid

These scripts are used to download RealEstate10K dataset.

The real state 10k dataset from https://google.github.io/realestate10k

Scalable and memory-optimized training of diffusion models

arXiv LaTeX Cleaner: Easily clean the LaTeX code of your paper to submit to arXiv

Automatic Pseudo-Harmful Prompt Generation for Evaluating False Refusals in Large Language Models

A curated list of recent diffusion models for video generation, editing, and various other applications.

Recipes to train reward model for RLHF.

A collection of awesome video generation studies.

[CSUR] A Survey on Video Diffusion Models

AllenAI's post-training codebase

Code for the ICML 2024 paper "Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment"

Emote Portrait Alive: Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions

✨ Hotshot-XL: State-of-the-art AI text-to-GIF model trained to work alongside Stable Diffusion XL