[arXiv 2024] Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis

xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism

OmniGen: Unified Image Generation. https://arxiv.org/pdf/2409.11340

More practical frame interpolation approach.

HunyuanVideo: A Systematic Framework For Large Video Generation Model

Bring portraits to life!

Let's finetune video generation models!

The best OSS video generation models

Open-Sora: Democratizing Efficient Video Production for All

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

Keyframe Interpolation with CogvideoX

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

Memory-optimized training scripts for video models based on Diffusers

CogVideoX-LoRAs is a centralized repository for all LoRA models created for CogVideoX, filling the gap for a unified sharing space. With the rising demand for customized video generation, this hub …

Simple Controlnet module for CogvideoX model.

faster parallel inference of mochi-1 video generation model

GUI-focused roop

Evolved Fork of roop with Web Server and lots of additions

TorchCFM: a Conditional Flow Matching library

[AAAI 2024] Follow-Your-Pose: This repo is the official implementation of "Follow-Your-Pose : Pose-Guided Text-to-Video Generation using Pose-Free Videos"

Official codes of VEnhancer: Generative Space-Time Enhancement for Video Generation

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

🚀 海螺AI大模型逆向API【特长：超自然语音】，支持高速流式输出、语音合成、联网搜索、长文档解读、图像解析、多轮对话，零配置部署，多路token支持，自动清理会话痕迹，仅供测试，如需商用请前往官方开放平台。

UniPortrait: A Unified Framework for Identity-Preserving Single- and Multi-Human Image Personalization

A collection of LLM papers, blogs, and projects, with a focus on OpenAI o1 🍓 and reasoning techniques.