There are no reviews yet. Be the first to send feedback to the community and the maintainers!
Interview-code-practice-python
面试题learn_python
Python 学习笔记Awesome-Chinese-Stable-Diffusion
中文文生图stable diffsion模型集合How-to-make-high-resolution-remote-sensing-image-dataset
高分遥感影像数据集的制作3D-DenseNet-for-HSI
paper:Three-dimensional densely connected convolutional network for hyperspectral remote sensing image classificationDL-data-processing-methods
深度学习处理数据的一些基本操作FSKNet-for-HSI
paper:Faster hyperspectral image classification based on selective kernel mechanism using deep convolutional networksMulti-Scale-Dense-Networks-for-Hyperspectral-Remote-Sensing-Image-Classification
paper:Multi-Scale Dense Networks for Hyperspectral Remote Sensing Image ClassificationPaper-Learning
论文学习,主要研究深度学习处理遥感影像,地名识别,文档篡改检测,OCR,视觉生成Parking
Parking 停车位APPWav2lipAll
基于wav2lip进行虚拟数字人训练,唇形驱动,包括数据处理流程等,模型包括96x96,192x192,192x288,288x288。ComfyUI_M3Net
comfyui的m3net插件,m3net是不错的显著性检测模型,抠图上效果不错,我开源了一个训练的电商的模型,供大家试玩ComfyUI_InternVL2
comfyui的InternVL2插件,InternVL2是当前不错的开源多模态大语言模型,在文档vqa上表现很好Yolov5_rknnlite2
yolov5行人检测,rk3588,rknlite2部署sd_webui_ootdiffusion
基于stable-diffusion的虚拟换装方法sd_webui_outpainting
AI扩图,Outpainting extension performs stable diffusion outpainting on a browser UI.SimilarWork
用numpy实现tf静态图和pytorch动态图风格的深度学习框架XrayQwenVL
基于qwenvl微调一个多模态Xray识别的大模型Answer_card_identification
答题卡项目,智能批改DGCNet-for-HSI
paper:DGCNet: An Efficient 3D-Densenet based on Dynamic Group Convolution for Hyperspectral Remote Sensing Image Classification;Spatial-Spectral Hyperspectral Classification based on Learnable 3D Group ConvolutionEcommerceLLM
基于电商数据微调的Qwen1.5系列的电商大模型,包括0.5b-base,0.5b-chat,1.8b-base,7b-base,以及基于llama3-chinese-sft版本的基础模型的sft后电商大模型。sd_webui_realtime_lcm_canvas
realtime_lcm_canvas extension performs flowty-realtime-lcm-canvas stable diffusion on a browser UI.mmdetection_add
添加实现的目标检测算法,包括efficientdet,yolov4/v5等sd_webui_musetalk
musetalk在stable diffusion webui上的插件,可实现唇形驱动的功能,talking face generationsd_webui_beautifulprompt
beautifulprompt extension performs stable diffusion automatic prompt engineering on a browser UI.Camera_blur_detection
对摄像头采集的照片进行区域检测并且给出模糊判定,c++代码,采用fastdeploy进行多平台部署,VS2019。Xiaobao
videoclip,视频剪辑应用HOME-CLIP
在家装家居场景上微调的clip模型Qianbian
这个项目主要是关注huggingface,modelscope以及paddle ai studio上可直接跑通的项目,主要维护一些基础视觉AI项目地址,比如抠图,图像修复,字体擦除等XrayLLaVA
基于LLaVA1.6微调的Xray识别的多模态大模型ComfyUI_LLaSM
语音文本多模态大模型,语音侧基于whisper,text侧基于llama,通用效果不错。ComfyUI_MasaCtrl
在多次推理中可以固定图像主体,进行一致性控制,qkv层面工作sd_webui_lama
Lama extension performs stable diffusion inpainting on a browser UI.ComfyUI_CrossImageAttention
CrossImageAttention是zero-shot方法,可以在制定外观图和结构的前提下,生成具有一致结构和外观的图,在qkv层面的工作。ComfyUI_VideoEditing
视频生成,controlnet+sd对输入视频进行一致性控制,对unet中的self-attention的qkv进行第一帧和前一帧参考。SuperDeer
仙鹿 — 线路分享平台mmclassification_add
添加实现的分类算法到mmcls中,包括ghostnet等sd_webui_powerpaint
Inpainting extension performs stable diffusion inpaintingon a browser UI.sd_webui_matting
matting extension performs stable diffusion human or e_commence graph matting on a browser UI.sd_webui_sghm
SemanticGuidedHumanMatting extension performs stable diffusion human matting on a browser UI.mmhyperspectral
mm框架组合高光谱遥感影响分类模型sd_webui_animate_anything
类似runway中的毛刷功能,对输入图片的制定区域进行mask之后,该区域动起来,motion brush.ComfyUI_Diffusers
diffusers的模型,参数加载,以及公用的数据处理等操作,会持续更新。VideoRender
c++版本视频渲染,通过json脚本,合成视频,主要技术栈:ffmpeg/opengl。ComfyUI_Style_Aligned
style_aligned,通过共享qkv的方式来zero shot得到相似图,风格一致图生成,reference方法。EcommerceOCRBench
电商文字识别的多模态大模型的ocr基准测试集,参照ocrbench,但是测评数据更多。ComfyUI_VisualAttentionMap
对sd中text prompt和self-attention以及cross-attention时的特征图进行可视化。ComfyUI_SelfGuidance
可以帮助锁定prompt中的特定对象在二次编辑中不被改变,对两次推理的crossattention map进行loss guidance。Love Open Source and this site? Check out how you can help us