利用PaddleOCR检测图像中的文字并返回文字区域掩码，方便在ComfyUI流程中进行遮罩、修图或合成等后续处理与自动化。
💡 在ComfyUI中提取图像文字区域掩码以便遮罩或编辑。
🍴 3 Forks💻 Python🔄 2024-12-31
https://pan.quark.cn/s/af9fbf81e746
📄 README
ComfyUI-PaddleOcr
Nodes related to PaddleOCR OCR
Inspire by PaddleOCR
OcrBoxMask
return masks of detected text in images
This node returns masks of detected text in images using PaddleOCR.
Inputs
images: the input images to be processed.
text: the text to be detected in images.
Outputs
masks: the masks of detected text in the input images.
OcrImageText
return text in an image
This node returns text in an image using PaddleOCR.
Inputs
image: the input image to be processed.
Outputs
text: the text detected in the input image.