一、工具 rembg
#
rembg i -m birefnet-massive 20241126-140049.jpg 49-max.png
默认使用u2net模型， 使用-m 可以指定模型运行
二、模型 #
| Model Name | Download Link | Source Link | Description | 描述 |
|---|---|---|---|---|
| u2net | Download | Source | A pre-trained model for general use cases. | 用于通用用途的预训练模型。 |
| u2netp | Download | Source | A lightweight version of u2net model. | u2net模型的轻量版。 |
| u2net_human_seg | Download | Source | A pre-trained model for human segmentation. | 用于人类分割的预训练模型。 |
| u2net_cloth_seg | Download | Source | A pre-trained model for clothes parsing. | 用于服装解析的预训练模型（上衣、下衣、全身）。 |
| silueta | Download | Source | A reduced size version of u2net (43MB). | u2net的精简版（43MB）。 |
| isnet-general-use | Download | Source | A new pre-trained model for general use cases. | 新的通用预训练模型。 |
| isnet-anime | Download | Source | High-accuracy segmentation for anime characters. | 高精度的动漫角色分割模型。 |
| sam | Download Encoder | Source | A pre-trained model for any use cases. | 用于任何用途的预训练模型。 |
| birefnet-general | Download | Source | A pre-trained model for general use cases. | 用于通用用途的预训练模型。 |
| birefnet-general-lite | Download | Source | A light pre-trained model for general use cases. | 轻量级的通用预训练模型。 |
| birefnet-portrait | Download | Source | A pre-trained model for human portraits. | 用于人像的预训练模型。 |
| birefnet-dis | Download | Source | A pre-trained model for dichotomous image segmentation. | 用于二分图像分割的预训练模型。 |
| birefnet-hrsod | Download | Source | A pre-trained model for high-resolution salient object detection. | 用于高分辨率显著目标检测的预训练模型。 |
| birefnet-cod | Download | Source | A pre-trained model for concealed object detection. | 用于隐蔽物体检测的预训练模型。 |
| birefnet-massive | Download | Source | A pre-trained model with a massive dataset. | 使用大规模数据集的预训练模型。 |
birefnet-massive #
效果最好， 最吃配置 大概用12G内存