🎭 267 个即插即用的 AI 专家角色 — 支持 Hermes Agent/Claude Code/Cursor/Copilot 等 18 种工具，覆盖工程/设计/营销/金融等 20 个部门。含 52 个中国市场原创智能体（小红书/抖音/微信/飞书/钉钉等）。搭配编排器 agency-orchestrator，一句话即可让多位专家按 DAG 自动协作。

[ICLR'25] Official PyTorch implementation of "Framer: Interactive Frame Interpolation".

some practical comfyui nodes

using InstantX's CSGO in comfyUI

hand poses lib for echo mimic v2

JoyHallo: Digital human model for Mandarin

[AAAI 2025] EchoMimic: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditioning

⚡️HivisionIDPhotos: a lightweight and efficient AI ID photos tools. 一个轻量级的AI证件照制作算法。

A diffusers pipeline for zero shot stylised couples portrait creation

A diffusers pipeline for zero shot stylised portrait creation

SD-Trainer. LoRA & Dreambooth training scripts & GUI use kohya-ss's trainer, for diffusion model.

Official code for "F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching"

PuLID-Flux ComfyUI implementation

[NeurIPS 2022] Towards Robust Blind Face Restoration with Codebook Lookup Transformer

[SIGGRAPH Asia 2024, Journal Track] ToonCrafter: Generative Cartoon Interpolation

Official implementation of FIFO-Diffusion: Generating Infinite Videos from Text without Training (NeurIPS 2024)

More relighting!

Accepted as [NeurIPS 2024] Spotlight Presentation Paper

[NeurIPS 2024] Official code for PuLID: Pure and Lightning ID Customization via Contrastive Alignment

[ECCV2024] IDM-VTON : Improving Diffusion Models for Authentic Virtual Try-on in the Wild

InstantMesh: Efficient 3D Mesh Generation from a Single Image with Sparse-view Large Reconstruction Models

Deezer source separation library including pretrained models.

Official implementation of AnimateDiff.

MuseTalk: Real-Time High Quality Lip Synchorization with Latent Space Inpainting

MuseV: Infinite-length and High Fidelity Virtual Human Video Generation with Visual Conditioned Parallel Denoising

TripoSR: Fast 3D Object Reconstruction from a Single Image

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

InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation 🔥

InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥

Intro to Artificial Neural Networks for High Schoolers