F5-AI / SAM2-GradioLinks
A gradio based webui for meta segment-anything-model 2 (SAM2), both image and video are supported
☆18Updated 10 months ago
Alternatives and similar repositories for SAM2-Gradio
Users that are interested in SAM2-Gradio are comparing it to the libraries listed below
Sorting:
- 使用onnxruntime部署高精度二分类图像分割MVANet和BiRefNet,依然是包含C++和Python两个版本的程序☆22Updated 10 months ago
- ☆14Updated 4 months ago
- The source code of IEEE TPAMI 2025 "Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computation".☆107Updated 7 months ago
- An easy use face swap tool for images and tools only depend on onnxruntime.☆77Updated last year
- ☆16Updated 11 months ago
- VCED 可以通过你的文字描述来自动识别视频中相符合的片段进行视频剪辑。该项目基于跨模态搜索与向量检索技术搭建,通过前后端分离的模式,帮助你快速的接触新一代搜索技术。☆375Updated last year
- segment anything(SAM) for CPP Inference☆30Updated last year
- README.md☆48Updated last year
- 基于Yolov5-Deepsort-Fastreid源码,重构了视频行人MOT和行人ReID特征提取代码、接口☆12Updated 2 years ago
- Accelerate segment anything model inference using Tensorrt 8.6.1.6☆94Updated last year
- 使用onnxruntime部署facefusion换脸,包含C++和Python两个版本的程序☆112Updated last year
- 使用OpenCV+onnxruntime部署中文clip做以文搜图,给出一句话来描述想要的图片,就能从图库中搜出来符合要求的图片。包含C++和Python两个版本的程序☆77Updated last year
- 基于yoloV5进行多类别+关键检测,关键点检测主要是计算车辆航向角☆16Updated 3 years ago
- ☆20Updated last year
- ☆23Updated 2 years ago
- https://github.com/tzutalin/labelImg 的功能改进版本☆15Updated 4 years ago
- 视频分类标注、视频时空标注☆42Updated last year
- 私有化自动数字人排队训练、短视频排队生成的微信小程序、web运营后台管理系统一键部署,基于单人训练的音频驱动唇形,比wav2lip、deepfacelab、liveportrait、musetalk等等唇形方案更好,直接可以商业化,支持中日英韩多种语音复刻☆40Updated 3 months ago
- ☆54Updated 2 years ago
- AI Image Translation Tool-An excellent translator for photos, pictures, posters, covers, banners and product images.AI图片翻译-很棒的批量跨境电商|海报|商…☆76Updated last year
- label your image with Segment Anything Model or MobileSAM, support remote labeling for multiple persons。使用Segment Anything Model或MobileSA…☆80Updated 10 months ago
- 补充了一些Visualglm缺少的文件,可以对Visualglm进行训练,实例中是对人脸做了面相的识别☆13Updated 2 years ago
- 人脸检测服务, 用于输出适合人脸识别的 人脸数据集,通过 mtcnn cnn检测人脸,通过 hopenet 开源项目确定人脸是姿态,拿到头部姿态欧拉角,通过 拉普拉斯算子 拿到人脸模糊度,通过对mtcnn 三级网络和置信度,欧拉角阈值,模糊度设置阈值筛选合适人脸☆11Updated last year
- 使用FastAPI+vLLM部署Qwen2.5☆21Updated 9 months ago
- 🔨🔨🔨Tool for making model training data set☆19Updated 8 months ago
- 集成了LLM与SDXL的AIGC应用程序☆29Updated last year
- 图片爬虫工具,提供可视化界面, 可爬取百度图片关键词和任意网址的图片,并集成了labelimg打标签的功能,用于深度学习数据集的收集和标注。☆68Updated 2 years ago
- YOLOv9 paper解析,训练自己的数据集,TensorRT端到端部署, NCNN安卓手机部署☆65Updated last year
- ☆21Updated 2 years ago
- 基于meta的segment anything的抠图工具,使用opencv制作的gui。segment anything, gui made with opencv☆60Updated last year