Hugging Face's logo

waveshaker
/
loras_tools

Text-to-Image
lora
tool
python
gui
Model card Files
xet
 Community
loras_tools / README.md
waveshaker's picture
waveshaker
Update README.md
02b4ee6 verified
preview code
|
Raw History Blame Contribute Delete
1.92 kB
metadata 
license: mit
tags:
  - lora
  - tool
  - python
  - gui
pipeline_tag: text-to-image

Note: This repository hosts management scripts/tools only. No model weights are included.

Tools for:

🖼️ waveshaker/loras_gallery

🧊 waveshaker/loras

📊 waveshaker/dataset_collections

  • models_manager_v7.py is used for centralized local management of the three repositories above:

    1. JSON Management: Pull/upload models.json, maintain card metadata (Title, Trigger).
    2. Model Upload: Auto-clean local images and convert to JPG, one-click flat upload to the Models repo.
    3. Dataset Upload: Automated pipeline (TXT cleanup, PNG to JPG, Parquet packaging, YAML update) and push to the Datasets repo.
    MainPage

  • comfy_dataset_prep_wf_v001.json: A ComfyUI workflow for LoRA dataset prep. Integrates Krea2, Qwen Image 2.1, Flux 2 Klein 9B, and SQVLM for high-res upscaling and auto-captioning of faces and bodies.

  • showcase_tempalte.json: A ComfyUI workflow designed to generate PNG images with embedded workflow metadata. The accompanying Python tool parses these images to extract the exact Prompt, generation parameters, and LoRA stacks, automatically compiling them into a structured gallery.json for the web gallery's "ComfyUI Showcase" viewer.

  • filter_nsfw.py: A script for rough NSFW filtering(based on NudeNet). It provides a quick initial screen, but manual review is still necessary for accurate results.