xymfei,github

4d-humans

4DHumans: 单目无标记视频中多人连贯动作跟踪及重建Reconstructing and Tracking Humans with Transformers

adasr-talkinghead

AdaSR-TalkingHead 人头图片高仿模拟输入的说话人物视频ICASSP2024: Adaptive Super Resolution For One-Shot Talking-Head Generation

Github-AMT-给定首尾两帧合成简单中间过程视频-高效帧插值全对多场变换- Official code for "AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation" (CVPR2023)Official code for "AMT: All-Pairs Multi-Field Transforms for Efficient Frame Interpolation" (CVPR2023)

animatediff

Official implementation of AnimateDiff.

aniportrait

腾讯AniPortrait：使用音频+参考肖像图生成高质量动画/视频AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation

anydoor-for-windows

Official implementations for paper: Anydoor: zero-shot object-level image customization

anytext

阿里巴巴项目

audiosep

AudioSep的训练代码和检查点 - 分离任何音频模型-Official implementation of "Separate Anything You Describe"

automatic-parking

自动泊车Python implementation of an automatic parallel parking system in a virtual environment, including path planning, path tracking, and parallel parking

bark

🔊 Text-prompted Generative Audio Model

binggpt-python

Reverse engineered API of Microsoft's Bing Chat AI

clarity-lowres-upscaler

Clarity AI 的低分辨率修复 |AI图像升频器和增强器Low resolution upscaling fix for Clarity AI - Upscale and enhance your images with AI

clarity-upscaler

AI 图像升级器和增强器 - Magnific Alternative-Clarity AI | AI Image Upscaler & Enhancer - free and open-source Magnific Alternative

codef

CoDeF：用于时间一致性视频处理的内容变形场Official PyTorch implementation of CoDeF: Content Deformation Fields for Temporally Consistent Video Processing

comfyui-yoloworld-efficientsam

最简单的应用就是能抠图抠视频 YOLO-World + EfficientSAM for ComfyUI

comfyui_ipadapter_plus

IPadapter plus 可以批量展开设置来旋转/制作高动态战斗场景的动画

concept-graphs

自然语言即可指定查找3D房间内各种物品，Official code release for ConceptGraphs，https://twitter.com/_krishna_murthy/status/1707591942794555843

cutie

抠视频-对象级内存读取功能的视频对象分割[arXiv 2023] Putting the Object Back Into Video Object Segmentation

distil-whisper

Distil-Whisper 是 Whisper 的蒸馏版本，速度提高了 6 倍，体积缩小了 49%，并且在分布外评估集上的字错误率（WER）在 1% 以内。Distilled variant of Whisper for speech recognition. 6x faster, 50% smaller, within 1% word error rate.

douyin_beauty

基于python + selenium实现的自动寻找抖音上漂亮的小姐姐，基于抖音网页版，大部分代码由chatGPT生成

dpf

Dynamic Point Fields: 貌似生成人体表面衣物动态褶皱：动态点场：迈向高效且可扩展的动态表面表示（ICCV 2023）Towards Efficient and Scalable Dynamic Surface Representations (ICCV 2023)

draggan

Unofficial implementation of "Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold"

draggan-1

Official Code for DragGAN (SIGGRAPH 2023)

dreamgaussian

高斯变换快速实现文本转3D+图像转3D，Generative Gaussian Splatting for Efficient 3D Content Creation

dreamtalk

阿里巴巴 DreamTalk: When Expressive Talking Head Generation Meets Diffusion Probabilistic Models

e2fgvi

删除视频中指定物件Official code for "Towards An End-to-End Framework for Flow-Guided Video Inpainting" (CVPR2022)

edge-tts

Use Microsoft Edge's online text-to-speech service from Python WITHOUT needing Microsoft Edge or Windows or an API key

facefusion

Next generation face swapper and enhancer

fastsam

FastSAM Fast SAM 🔥 - 通用的零样本分割模型 - 比 Meta 中的 Segment Anything 快 50 倍 - 与 32x32 补丁大小 SAM 相当的性能 - 利用 @ultralytics YOLOv8-seg 模型

flowsam

FlowSAM可以发现和分割视频中的移动物体Official Implementation of "Moving Object Segmentation: All You Need Is SAM (and Flow)" Junyu Xie, Charig Yang, Weidi Xie, Andrew Zisserman

xymfei Goto Github PK

xymfei's Projects

Recommend Projects

Recommend Topics

Recommend Org