The image prompt adapter is designed to enable a pretrained text-to-image diffusion model to generate images with image prompt.

Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference

A complete and graceful API for Wechat. 微信个人号接口、微信机器人及命令行微信，三十行即可自定义个人号机器人。

Pandora Cloud + Pandora Server + Shared Chat + BackendAPI Proxy + Chat2API + Signup Free = PandoraNext. New GPTs(Gizmo) UI, All in one!

本项目基于使用accesstoken的方式实现了网页版 ChatGPT 的前端，是用ChatGPT-Next-Web项目进行修改而得，默认Main分支对接gpt3.5的模型，gpt4分支对接gpt4模型。另外本项目需要的后端服务是pandoranext项目。项目是站在ChatGPT-Next-Web和pandoranext项目的作者肩膀上，感谢他们！

A powerful tool that translates ComfyUI workflows into executable Python code.

High-performance GPGPU inference of OpenAI's Whisper automatic speech recognition (ASR) model

Improved AnimateDiff for ComfyUI and Advanced Sampling Support

Seamless tiling for ComfyUI

FILM: Frame Interpolation for Large Motion, In ECCV 2022.

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

Wrapper to use DynamiCrafter models in ComfyUI

1 min voice data can also be used to train a good TTS model! (few shot voice cloning)

Instant voice cloning by MIT and MyShell. Audio foundation model.

[IJCV 2022] Bridging Composite and Real: Towards End-to-end Deep Image Matting

The official repo for [IJCV'23] "Rethinking Portrait Matting with Privacy Preserving"

PyTorch implementation of FILM: Frame Interpolation for Large Motion, In ECCV 2022.

[Information Fusion] Boosting Image Matting with Pretrained Plain Vision Transformers

one-click face swap

real time face swap and one-click video deepfake with only a single image

Free Motion Capture for Everyone 💀✨

[CVPR 2025] MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis