Image consistency checks with OpenAI vision models.
Project description
consistize
Check whether an image is consistent with a set of reference images using OpenAI vision models.
Install
pip install -e .
Usage
from consistize import Consistize
checker = Consistize(
reference_images=["./refs/ref1.jpg", "./refs/ref2.jpg"],
)
result = checker.run("./inputs/target.jpg")
print(result.consistency_score)
print(result.inconsistent_parts)
print(result.background_fix_prompts)
Set OPENAI_API_KEY in your environment or pass api_key to Consistize.
Custom prompt or model
result = checker.run(
"./inputs/target.jpg",
prompt="Check the first image against the references; focus on lighting.",
model="gpt-5.2-pro"
)
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
consistize-0.1.0.tar.gz
(3.3 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
File details
Details for the file consistize-0.1.0.tar.gz.
File metadata
- Download URL: consistize-0.1.0.tar.gz
- Upload date:
- Size: 3.3 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.12.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
42436c751552cd99ce9fbbbd3ca58c8449ea0dfe664f2e5e55203f68866f3d5b
|
|
| MD5 |
72cd7c6b3864a206d7633ae54ef54463
|
|
| BLAKE2b-256 |
4a400f93c5d4ced5dd5a1c099df6f0b2b38772591579a0937952385de5d71df9
|
File details
Details for the file consistize-0.1.0-py3-none-any.whl.
File metadata
- Download URL: consistize-0.1.0-py3-none-any.whl
- Upload date:
- Size: 3.7 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.1.0 CPython/3.12.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
038336f8ac0178b273092d432a488a201fdb7bb3bd0da6b81e7c030078c8973e
|
|
| MD5 |
4d9054839b3c4fb418259a196f49baf5
|
|
| BLAKE2b-256 |
560852d476468f5b0203f3efa0e4f86a2d3c4b4c3f8794f21e9c433844b9c0d4
|