Multi-Tagger

Multi-Tagger is a versatile application that combines the Waifu Diffusion and Florence 2 models for advanced image analysis and captioning. Perfect for AI artists and enthusiasts, it offers a range of features:

Batch processing for multiple images
Multi-category tagging with structured tag display.
CUDA or CPU support.
Image tagging, various captioning tasks which includes: Caption, Detailed Caption, Object Detection with visual outputs and much more.

Example image by me.

Next Restart: 2025-04-18 08:37:13 (UTC) - The space will restart every 2 days to ensure stability and performance. It uses a background scheduler to handle the restart process.

Upload an Image or clicking paste from clipboard button

Grid of images

Model

General Tags Threshold

0 1

Use MCut threshold

Character Tags Threshold

0 1

Use MCut threshold

Merge characters into the string output

Llama3 Model

Use the Llama3 model to reorganize the article (Note: very slow)

Prepend Additional tags (comma split)

Append Additional tags (comma split)

Download includes: All outputs* and image(s)

Output (characters)

Output (string)*

Categorized (string)* - If it's too long, select an image to display tags correctly.

Categorized (tags)* - JSON

Rating

Output (tags)

Unclassified (tags)

Examples

Upload an Image or clicking paste from clipboard button	Model	General Tags Threshold	Use MCut threshold	Character Tags Threshold	Use MCut threshold