a similarity calculatior for stable diffusion checkpoints

Project description

sdsim

stable diffusion model similarity calculatior

original: https://huggingface.co/JosephusCheung/ASimilarityCalculatior

modified: https://gist.github.com/toriato/87db2b3cbe9863be43b63ba10cd610ad

packaging: here

Install

pip install sdsim

Usage

sdsim animefull-latest.ckpt ACertainModel.safetensors

sdsim -nv -j result.json animefull-latest.ckpt ACertainModel.safetensors

❯ sdsim --help
usage: sdsim [-h] [-j JSON] [-s SEED] [-nv] base targets [targets ...]

positional arguments:
  base
  targets

optional arguments:
  -h, --help            show this help message and exit
  -j JSON, --json JSON
  -s SEED, --seed SEED
  -nv, --no-verbose

from sdsim import similarity

model1 = "animefull-latest.ckpt"
model2 = "ACertainModel.safetensors"
model3 = "AbyssOrangeMix2_nsfw.safetensors"
result = similarity(model1, [model2, model3], verbose=True)

Project details

Release history Release notifications | RSS feed

This version

0.1.0

Jan 25, 2023

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

sdsim-0.1.0.tar.gz (4.2 kB view details)

Uploaded Jan 25, 2023 Source

Built Distribution

sdsim-0.1.0-py3-none-any.whl (5.1 kB view details)

Uploaded Jan 25, 2023 Python 3

File details

Details for the file sdsim-0.1.0.tar.gz.

File metadata

Download URL: sdsim-0.1.0.tar.gz
Upload date: Jan 25, 2023
Size: 4.2 kB
Tags: Source
Uploaded using Trusted Publishing? No
Uploaded via: pdm/2.4.0 CPython/3.8.15

File hashes

Hashes for sdsim-0.1.0.tar.gz
Algorithm	Hash digest
SHA256	`31222a22324e4a368fe05721f51c86817efe13e0289f0c14477d191ec958f5ff`
MD5	`f6dfa91550d2303ae54fc836036c3710`
BLAKE2b-256	`90a6d2c7523126bbeb90b4f66281ac6f05b77dc4b9817dfbb772932be847e0a5`

See more details on using hashes here.

File details

Details for the file sdsim-0.1.0-py3-none-any.whl.

File metadata

Download URL: sdsim-0.1.0-py3-none-any.whl
Upload date: Jan 25, 2023
Size: 5.1 kB
Tags: Python 3
Uploaded using Trusted Publishing? No
Uploaded via: pdm/2.4.0 CPython/3.8.15

File hashes

Hashes for sdsim-0.1.0-py3-none-any.whl
Algorithm	Hash digest
SHA256	`117ee73ccecc70237e7e7d444dbd1db42cf27116511c90abb3a2d6cb073b5270`
MD5	`15eb10dfe6d2b99ff145b4217fca88c3`
BLAKE2b-256	`e43f4bcf3f61de1822b8c55d8df009356da40d06a0e2a885a2189184ea8d878c`