# kichangkim/deepdanbooru

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/kichangkim-deepdanbooru).**

2,892 stars · 269 forks · Python · mit

## Links

- GitHub: https://github.com/KichangKim/DeepDanbooru
- awesome-repositories: https://awesome-repositories.com/repository/kichangkim-deepdanbooru.md

## Topics

`danbooru` `machine-learning` `tensorflow`

## Description

DeepDanbooru is a deep learning tool for tagging anime-style images with Danbooru-style tags. It uses a pre-trained convolutional neural network to analyze images and predict tags identifying characters, attributes, and artwork details.

The project provides a complete pipeline for training custom tag recognition models. Users can prepare datasets by downloading tag definitions from a remote Danbooru server using authenticated API requests, then store image-tag pairs in a structured SQLite database. The training workflow supports filtering datasets by rating or score criteria, configuring hyperparameters, and running optimization to recognize user-defined tags.

The tool also includes a command-line interface for repeated command execution with configurable intervals, enabling automated continuous workflows.

## Tags

### Graphics & Multimedia

- [Anime Image Taggers](https://awesome-repositories.com/f/graphics-multimedia/anime-image-taggers.md) — Analyzes anime-style images and outputs Danbooru-style tags identifying characters and attributes. ([source](https://github.com/KichangKim/DeepDanbooru/blob/master/.travis.yml))

### Artificial Intelligence & ML

- [Custom Model Training](https://awesome-repositories.com/f/artificial-intelligence-ml/custom-model-training.md) — Trains custom tag recognition models using SQLite datasets and configurable hyperparameters. ([source](https://github.com/KichangKim/DeepDanbooru/blob/master/README.md))
- [Deep Learning Inference Engines](https://awesome-repositories.com/f/artificial-intelligence-ml/deep-learning-inference-engines.md) — Runs a pre-trained convolutional neural network to predict tags from image pixel data.
- [Model-Based Tag Predictions](https://awesome-repositories.com/f/artificial-intelligence-ml/image-classification/image-level-tagging/model-based-tag-predictions.md) — Evaluates images against a trained model to produce predicted tags for each image. ([source](https://github.com/KichangKim/DeepDanbooru/blob/master/README.md))
- [Image Tag Training Pipelines](https://awesome-repositories.com/f/artificial-intelligence-ml/machine-learning/infrastructure/model-training-and-tuning/training-frameworks/model-training-pipelines/image-tag-training-pipelines.md) — Processes user-provided images and tags into a training workflow with hyperparameter optimization.
- [Training Dataset Preparation](https://awesome-repositories.com/f/artificial-intelligence-ml/training-dataset-preparation.md) — Organizes images and tags into a structured SQLite database for the training pipeline. ([source](https://github.com/KichangKim/DeepDanbooru/blob/master/README.md))
- [Rating and Score Filters](https://awesome-repositories.com/f/artificial-intelligence-ml/training-dataset-preparation/rating-and-score-filters.md) — Filters raw SQLite datasets by rating and score criteria before training. ([source](https://github.com/KichangKim/DeepDanbooru#readme))

### Data & Databases

- [Remote Data Fetching](https://awesome-repositories.com/f/data-databases/remote-data-fetching.md) — Fetches tag definitions and metadata from a remote server using authenticated API requests.
- [SQLite Storage Adapters](https://awesome-repositories.com/f/data-databases/sqlite-drivers/sqlite-storage-adapters.md) — Stores image-tag pairs in a structured SQLite database for efficient training data management.

### Development Tools & Productivity

- [Tag Definition Downloads](https://awesome-repositories.com/f/development-tools-productivity/github-based-package-management/debloating-list-downloads/tag-definition-downloads.md) — Downloads Danbooru tag definitions via authenticated API for training and estimation tasks. ([source](https://github.com/KichangKim/DeepDanbooru#readme))