This article comes from@op7418
Supports generating prompt words and masks for specified positions from pictures.
Generating prompt words from pictures supports three levels of detail, and the content will increase. Masks can generate words similar to SAM input areas.
Prompt reasoning is much faster and more accurate than WD14.
Florence-2 is designed to accept text prompts as task instructions and generate the desired results in text form, whether it is image description, object detection, positioning or segmentation.
Florence-2 was trained on a dataset of 126 million images.
For more details, you can browse the link below the video
Thank you for watching this video. If you like it, please subscribe and like it. thank
Plug-in address:https://github.com/kijai/ComfyUI-Florence2
Oil tubing: