No project description provided
Project description
img2tags
Tag images by using ONNX Runtime. The current default model is SmilingWolf/wd-vit-large-tagger-v3. It works fine for anime images and with batch sizes greater than 1.
Setup
# For CPU
pip install -U 'img2tags[cpu]'
# For GPU
pip install -U 'img2tags[gpu]'
# If you use CUDA 12.2, the following packages may be needed
sudo apt install libcufft10 libcudart11.0
Run
# Generate .txt file
img2tags -i input_dir
# Generate .json file in another directory with CPU
# --offline: Do not fetch model files (You must have downloaded that model)
img2tags --ext json \
--cpu \
-i input_dir \
-o output_dir \
--offline
# Output to a single file (JSONL)
img2tags --ext jsonl \
--cpu \
-i input_dir \
-o output_filename.jsonl \
--offline
# You can use filelist
img2tags --ext jsonl \
--cpu \
-i target_file_list.txt \
-o output_filename.jsonl \
--offline
You can set thresholds in JSON format like --th {"0": 0.3, "4":0.2, "9":0.3}
.
LICENSE
Apache 2.0
Some codes are based on codes in the following project.
References
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
img2tags-1.6.5.tar.gz
(914.7 kB
view hashes)
Built Distribution
img2tags-1.6.5-py3-none-any.whl
(14.9 kB
view hashes)