Updated: Jan 15, 2026
tool
There are scripts that I use when I create images by diffusers or make models.
For the person who did not so know a lot about python, I maked scripts into bat form.
Script runs, when you click corresponding BAT file.
Please use them.
get_vae
It is a script that extracts a vae safetensors from a checkpoint safetensors. I'm successful in sdxl model.
lora_mod
When the message "ValueError: Checkpoint not supported because layer lora_unet_label_emb_0_0.alpha not supported." appears,try to run this program. I'm successful in lora of Illustrious model.
make_embedding
It is a script that make a embedding from text.
make_safetensors
It is a script that burns a vae and loras in a checkpoint. This script is based on convert_diffusers_to_original_sdxl.py of huggingface/diffusers.
merge_ckpt
It is a script that merge SDXL checkpoints. This script supports block merge and DARE merge.
MergeLoraBySVD
I make svd_merge_lora.py of kohya-ss/sd-scripts into a module. I make it to run by one file.
plus_metadata
It is a script that write metadata to PNG file. That metadata is recognized in CivitAi.
accuracy
It is a script that changes the accuracy of the safetensors file.
differense_between_ckpts
I make extract_lora_from_models.py of kohya-ss/sd-scripts into a module. But this script supports SDXL models only. I make it to run by one file.