Generate captions for images using GIT from MSFT
Project description
imgcap
A CLI to generate captions for images using the GiT model from MSFT
Install
Install imgcap in your system using:
pip install imgcap
The model size is of 707MB and once initially downloaded, it will be stored in the ~/.cache/huggingface/hub/.
Usage
Run the CLI tool as follows
nameit [OPTIONS] PATHS..
Options
--output [pretty|json]: Specify the output format (default: pretty).--max-tokens INTEGER: Maximum number of tokens in the generated caption (default: 50).--recursive: Recursively process directories to find images.--threads INTEGER: Number of threads to use for processing (default: 1)
Example commands
- Generate captions for a single image:
imgcap ./path/to/image.jpg --output pretty
- Generate captions for all images in a directory:
imgcap ./path/to/directory --recursive --output json
- Use multiple threads for faster processing:
imgcap ./images --threads 4
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
imgcap-0.2.tar.gz
(3.9 kB
view details)
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
imgcap-0.2-py3-none-any.whl
(3.4 kB
view details)
File details
Details for the file imgcap-0.2.tar.gz.
File metadata
- Download URL: imgcap-0.2.tar.gz
- Upload date:
- Size: 3.9 kB
- Tags: Source
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/5.1.1 CPython/3.12.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
dd41d141735a0211bff4355745bbf60982fedbbf6bbba057a828c2521e901bb9
|
|
| MD5 |
81e4f2e76e9fe5b5cbeb3ee9adb47634
|
|
| BLAKE2b-256 |
1a0020041f486bfd148c48dc888f8ab21250834f11cee6d8e0e3e242752e7614
|
File details
Details for the file imgcap-0.2-py3-none-any.whl.
File metadata
- Download URL: imgcap-0.2-py3-none-any.whl
- Upload date:
- Size: 3.4 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? Yes
- Uploaded via: twine/5.1.1 CPython/3.12.5
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
bfe9e1111f3e2be8d7314ee8ed82dea6cc49398f9d3da8c8f95a5aab9efe2f7d
|
|
| MD5 |
0c2e1b3826f4a01437fe890dd29b24ba
|
|
| BLAKE2b-256 |
ae3cdc5311ab0d5110a1e8561accb98b2fcdb69547ead62921403b67bb6e95f9
|