speech self-supervised representations

世界上最好的提示词 （总计估值超过300亿的提示词）外国网友x1xh成功获取了 v0、Manus、Cursor、Same.dev 和 Lovable 的完整官方系统提示词和内部工具。

[NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL

Tracking the latest and greatest research papers on video generation.

自动视频生成器，给定主题，自动生成解说视频。用户输入主题文字，系统调用大语言模型生成故事或解说的文字，然后进一步调用语音合成接口生成解说的语音，调用文生图接口生成契合文字内容的配图，最后融合语音和配图生成解说视频。

Unofficial extension implementation of CausVid

[NeurIPS 2025] Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation

This is a repo to track the latest autoregressive visual generation papers.

A unified inference and post-training framework for accelerated video generation.

[ICCV 2025] Official implementations for paper: VACE: All-in-One Video Creation and Editing

Official repository for LTX-Video

Pusa: Thousands Timesteps Video Diffusion Model

The ultimate training toolkit for finetuning diffusion models

A pipeline parallel training script for diffusion models.

Awesome curated collection of images and prompts generated by GPT-4o and gpt-image-1. Explore AI generated visuals created with ChatGPT and Sora, showcasing OpenAI’s advanced image generation capab…

All my self trained & released AI upscaling models. After gathering and applying over 600 different upscaling models, I learned how to train my own models, and these are the results.

This repository automatically updates a list of the top 100 repositories related to ComfyUI based on the number of stars on GitHub.

zero-shot voice conversion & singing voice conversion, with real-time support

Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model

Making large AI models cheaper, faster and more accessible

Enjoy the magic of Diffusion models!

Simple Controlnet module for CogvideoX model.

HunyuanVideo-I2V: A Customizable Image-to-Video Model based on HunyuanVideo

EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL

SkyReels V1: The first and most advanced open-source human-centric video foundation model

[CVPR 2025] MatAnyone: Stable Video Matting with Consistent Memory Propagation

Exploring Applications of GRPO

Pippo: High-Resolution Multi-View Humans from a Single Image