chenpipi0807 / Comfyui_PIP_ClassLinks
PIPClass是一个基于自载ViT(Vision Transformer)模型的comfyui使用框架,专为图像分类设计。它不仅可以快速识别图像中的内容,还能提供详细的分类得分,帮助用户更好地理解模型的判断依据。PIP_ClassV1 模型是基于ViT-B/16预训练模型,在动漫、非人类、真人、三个类别上进行全量微调训练。准确率90%以上。当然你也可以加载你自己的VIT模型在comfyui中使用
☆8Updated 4 months ago
Alternatives and similar repositories for Comfyui_PIP_Class
Users that are interested in Comfyui_PIP_Class are comparing it to the libraries listed below
Sorting:
- A set of comfyui multi class nodes☆12Updated last week
- ☆17Updated 4 months ago
- Add and remove fisheye distortion effect to images☆16Updated 4 months ago
- A Comfyui custom plugin that can automatically save or load Lora trigger words☆16Updated 6 months ago
- ComfyUI 插件:使用国内LLM模型扩写提示词;保存、预览图片不保存工作流信息☆9Updated last year
- ☆13Updated 3 months ago
- A node for ComfyUI that takes an input image and clips the color channels independently to increase contrast and alter color cast. This i…☆14Updated 3 months ago
- ☆9Updated last year
- ComfyUI nodes to use DiLightNet☆11Updated 10 months ago
- Using image caption models to extract prompts in ComfyUI☆10Updated 2 months ago
- A simple download tool for using pipeline in comfyUI☆10Updated last year
- Implementation of Fast Fourier Transform in COMFYUI☆8Updated 9 months ago
- 此节点组内含一系列拥有内置计数器与根据计数器输出结果输出特定结果的ComfyUI节点,目的是为了在ComfyUI的前端实现文件夹的遍历功能。具体实例请参照示例工作流,当然你也可以发挥自己的想象力创造其他有趣的东西。☆10Updated 5 months ago
- This node is base on VisualCloze method, A Universal Image Generation Framework via Visual In-Context Learning☆11Updated 2 months ago
- 提供ComfyUI网页截图、相机水印、自由模板转图片功能节点。☆11Updated last month
- CSD_MT is a method about Content-Style Decoupling for Unsupervised Makeup Transfer without Generating Pseudo Ground Truth, this node can …☆18Updated 6 months ago
- Repository for all the nodes I created on my own for ComfyUI.☆14Updated last month
- ☆12Updated last month
- ☆9Updated 2 months ago
- ComfyUI-PosterCraft is now available in ComfyUI, PosterCraft is a unified framework for high-quality aesthetic poster generation that exc…☆17Updated last month
- It change UNetModel and VAE Conv2d Layer into circular padding mode that make any text2image process generate seamless patten☆17Updated 4 months ago
- In-place embedded workflow-exif editing experience for ComfyUI generated images in your browser.☆11Updated 2 months ago
- Enhance your ComfyUI workflows with powerful LLMs! This custom node suite integrates DeepSeek, Qwen, and other leading Chinese LLMs direc…☆13Updated last month
- image and latent quilting nodes for comfyui☆10Updated 4 months ago
- Various custom nodes for ComfyUI☆14Updated last year
- ☆9Updated 5 months ago
- ☆10Updated 2 months ago
- New Front-end of ComfyUI-Easy-Use☆18Updated 2 weeks ago
- DeepLX translate☆8Updated 10 months ago
- 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☆12Updated 11 months ago