Skip to content

A collection of tools and scripts to prepare images for training stable diffusion, includeing tagging, content aware cropping, seam carving, video and image extraction and more

License

Notifications You must be signed in to change notification settings

IMbackK/SDImagePreprocess

Repository files navigation

SDImagePreprocess

This repo contains a collection of high performance tools intended to ease the createion of datasets for image generation AI training like stable diffusion.

Included tools

This repo contains the following tools:

SmartCrop

SmartCrop is an application that uses content aware croping using, seam carving and resizeing to bring a directory of images into the deisred size and aspect ratio for training. SmartCrop ist configurable to prioritize specific items or specifc persons in the images provided.

Content detected in image:

Content found in image

Cropped image based on content:

Cropped image

PersonDatasetAssembler

PersonDatasetAssembler is a python script that finds images of a spcific person, specified by a referance image in a directory of images or in a video file. PersonDatasetAssembler supports also raw images.

LLavaTagger

LLavaTagger is a python script that tags images based on a given prompt using the LLaVA multi modal llm. LLavaTagger supports using any number of gpus in ddp parralel for this task.

DanbooruTagger

DanbooruTagger is a python script of dubious utility that tags images based using the DeepDanbooru convolutional network.

License

All files in this repo are litcenced GPL V3, see LICENSE

About

A collection of tools and scripts to prepare images for training stable diffusion, includeing tagging, content aware cropping, seam carving, video and image extraction and more

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published