✦

AnimeTag-AI

AI image tagging · NAI・Danbooru-style image tag extractor

🖼️

Drag and drop an image, or click to upload

Or copy an image and press Ctrl+V in this area

🔞 This service is intended for users aged 18 and older

Rating

Upload an image to see its rating

Extracted Tags

General 0
Tags will appear here.
Character 0
Character tags will appear here.
Negative Prompt

This is not extracted from your image — edit it however you need.

lowres, bad anatomy, bad hands, text, error, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, normal quality, jpeg artifacts, signature, watermark, username, blurry, artist name

What is AnimeTag-AI?

AnimeTag-AI is a free image tag extractor built for AI image tagging. Upload an illustration generated with NAI (NovelAI) or any subculture/anime-style artwork, and an image tagger AI model trained on Danbooru image data will extract General tags covering character appearance (hair color, eye color), outfit, pose, and art style, along with character/series tags and a content rating — all in a single pass. It's designed to be useful for AI art creators, NAI users, and anyone preparing a dataset for LoRA training.

No sign-up or installation required — it runs right in your browser. Uploaded images are processed only temporarily for tag inference and are never stored on our servers.

What Does It Actually Look Like?

Seeing a real result is faster than describing it in words. Below is the actual output AnimeTag-AI produced from a single uploaded illustration.

Illustration of a boy in a school uniform wearing glasses, used as an AnimeTag-AI example
General 23
1boy0.99 yellow background0.98 male focus0.98 solo0.96 glasses0.95 school uniform0.90 black hair0.90 short hair0.84 looking at viewer0.84 simple background0.84 long sleeves0.80 jacket0.78 upper body0.78 yellow eyes0.77 black-framed eyewear0.73 black jacket0.65 hand on own chin0.65 bangs0.63 closed mouth0.61 gakuran0.61 hair between eyes0.57 crossed arms0.37 hand up0.36

Character tags came back at 0 — that's expected because this is an original illustration rather than an established character, so nothing in the training data matches. This is normal behavior; see the AI image tagger model guide for details.

Switching to Category View

Switching the same result to "Category View" automatically groups the tags into buckets like Basic Info, Appearance, and Outfit, so you can quickly scan or clear the tags you need, group by group.

Basic Info

1boy0.99 male focus0.98 solo0.96 hand on own chin0.65 hand up0.36

Appearance

black hair0.90 short hair0.84 yellow eyes0.77 bangs0.63 closed mouth0.61 hair between eyes0.57

Outfit

school uniform0.90 long sleeves0.80 jacket0.78 black jacket0.65

Remaining categories like background, pose, and props are auto-classified the same way, and the content rating is also shown automatically with a probability for every image.

Key Features

Automatic Danbooru-Style Tagging

Automatically extracts standard Danbooru tags like 1girl, blue_hair, and school_uniform, each with a confidence score.

Character & Series Recognition

Character and series names are shown in their own separate category, cutting down on dataset labeling time.

Automatic Content Rating

Automatically classifies images as General/Sensitive/Questionable/Explicit, so you can safely filter your dataset for its intended purpose.

Real-Time Threshold Filtering

Adjust sensitivity with the slider and the tag list updates instantly — no server round-trip needed.

One-Click Prompt Copy

Copy tags as a ready-to-use, comma-separated prompt for Stable Diffusion or LoRA caption files.

Free — No Sign-Up Needed

Just drag and drop or paste from your clipboard to get started. No installation, no payment.

How to Use

  1. 1

    Upload an Image

    Drag and drop your illustration, or paste an image copied to your clipboard with Ctrl+V.

  2. 2

    Adjust the Threshold

    Use the slider to adjust detection sensitivity and filter the tag list to just what you need.

  3. 3

    Clean Up and Copy

    Click any unwanted tag to remove it, then use the Copy Prompt button to grab your results.

Frequently Asked Questions

What kind of service is AnimeTag-AI?

It's a free web service that uses an image-to-tag AI model to automatically extract Danbooru-style tags and a content rating from any subculture or anime-style illustration you upload.

What AI model does it use?

We use an AI model trained for the image-to-tag task. It was trained on Danbooru image data, so it's specialized for recognizing subculture illustrations.

Does it work on images generated with NAI (NovelAI)?

Yes. NAI and most other AI art generation tools are trained on the Danbooru tag system, so this service can extract image tags from them just as well.

Are uploaded images stored on the server?

No. Uploaded images are only processed temporarily for tag inference and are not separately stored on the server. See our Privacy Policy for more details.

Can I use this to build a LoRA training dataset?

Yes. Extracted tags can be copied directly as a comma-separated prompt, ready to use in Stable Diffusion LoRA caption files.

Is it free to use, ongoing?

Yes. You can use it for free, with no sign-up and no payment required.