d3x-at/sd-parsers

A Python library to read metadata from images created by Stable Diffusion.

42
/ 100
Emerging

Extracts structured generation parameters (prompts, samplers, models, seeds) from images across five popular Stable Diffusion frontends via a pluggable parser architecture. Uses configurable metadata extraction stages (FAST/DEFAULT/EAGER) with PNG stenographic analysis at the highest level, and supports custom parser modules and extractors for extensibility. Returns parsed data as typed `PromptInfo` objects with hierarchical relationships between prompts, samplers, and generation parameters.

No commits in the last 6 months. Available on PyPI.

Stale 6m
Maintenance 0 / 25
Adoption 14 / 25
Maturity 18 / 25
Community 10 / 25

How are scores calculated?

Stars

43

Forks

4

Language

Python

License

MIT

Last pushed

Apr 03, 2025

Monthly downloads

383

Commits (30d)

0

Dependencies

1

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/d3x-at/sd-parsers"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.