Drop in a picture. Get its tags in seconds.
ImgTagger is a free AI image tagger that runs right in your browser. It spots characters, outfits, poses and backgrounds, and turns them into tags you can copy, search or save. Nothing gets uploaded.
- Pictures stay on your device
- No sign-up, no limits
- Best with anime & illustration
Pick the tagger that fits what you're doing
Tag a single picture in seconds, name the character in it, or auto-tag a whole folder. The other tools help clean up an image collection before you tag it.
Anime & Danbooru Tagger
Drop in one picture and get its Danbooru-style tags in seconds, ready to copy into a prompt or a caption.
Open the tool →Anime Character Tagger
Find out which anime character is in a picture. The model recognizes 2,132 popular characters.
Open the tool →Batch WD14 Tagger & Editor
Run WD14 tagger models on a whole folder, then search, filter and bulk-edit the tags before exporting .txt caption files.
Open the tool →Duplicate Image Finder
Group visually similar images with perceptual hashing. It catches resized, re-saved and lightly edited copies that file hashes miss.
Open the tool →Face & Expression Sorter
Split a batch into “has faces” and “no faces”, count faces per image, and optionally filter by detected expression.
Open the tool →Batch Color Fixer
Apply white balance, histogram normalization, brightness, contrast, saturation and gamma to many images at once.
Open the tool →An auto tagger that runs on your computer
Most online taggers make you upload your pictures. ImgTagger sends the AI to you instead, so your images never leave your device.
Add a picture
Drag it in, choose a file, or paste a screenshot. For lots of pictures, use the batch tagger.
The AI looks at it
A WD14 tagger model, trained on millions of tagged anime pictures, runs in your browser. The model downloads once (388 MB) and is saved for next time.
Keep the tags you want
Click a tag to leave it out, slide for more or fewer tags, then copy them or save them as caption files.
Turn a picture into a prompt
Many anime-style image generators were trained on Danbooru tags, so the tags from a picture you like make a great starting prompt. The anime tagger can format them for you, with spaces or underscores and with brackets escaped for tools like AUTOMATIC1111 and Forge.
Want to know who a character is first? The character tagger recognizes 2,132 popular anime and game characters.
Caption hundreds of images at once
Training a LoRA or organizing a big folder? The batch WD14 tagger tags every image, lets you search and bulk-edit the tags, and downloads one .txt caption file per image. It offers three WD14 models and remembers your blacklist and trigger words.
Clean the folder first with the duplicate finder, then follow our LoRA captioning guide.
Learn the tags, step by step
Plain-English guides written alongside the tools, from what Danbooru tags mean to building a clean training set.
Danbooru tags, explained
The categories, ratings, naming rules and conventions behind the tag vocabulary most anime image models are trained on.
Read the guide →How to caption a LoRA training dataset with tags
A start-to-finish workflow: trigger words, what to tag and what to leave out, reviewing the batch, and exporting one .txt per image.
Read the guide →Common booru tags: a reference glossary
Plain-English meanings, real post counts and common mix-ups for the everyday Danbooru tags a WD14 tagger outputs.
Read the guide →How to choose a confidence threshold for auto-tagging
What the scores mean, how the cut-off trades missed tags for wrong ones, and sensible starting values for different jobs.
Read the guide →A practical workflow for cleaning an image dataset
The order we recommend for turning a messy image folder into a clean, captioned training set, with what to check at each stage.
Read the guide →Booru tags vs natural-language captions: which should you use?
Tags or sentences? How each caption style handles counting, relationships and token limits, and how to match it to your base model.
Read the guide →Common questions
What does an AI image tagger do?
It looks at a picture and lists what is in it as short tags, such as 1girl, smile, red scarf or outdoors. You can use those tags as a prompt for AI art, as captions for training a model, or to search and sort a big collection.
Is it free? Do I need an account?
Everything is free with no account, no limits and no watermark. The site is supported by ads and by optional Ko-fi donations.
Are my pictures uploaded anywhere?
No. Your pictures are opened by your own browser and tagged on your own computer. The only big download is the tagging model itself, which comes from Hugging Face once and is then saved in your browser. How in-browser AI works explains how to check this yourself.
Which tagger should I use?
For one picture, such as finding prompt tags or naming a character, use the box at the top of this page, the anime & Danbooru tagger or the character tagger. For a whole folder, or to save a caption file for every image, use the batch WD14 tagger.
Does it work on photos?
It works on any picture, but it was trained on anime and illustration, so that is where it shines. On photos it picks up broad things like outdoors, sky or cat, but it doesn't know many real-world objects by name.