waveshaker/loras_tools

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_v*.py is used for centralized local management of the three repositories above:

  1. JSON Management: Pull/upload models.json, maintain card metadata (Title, Trigger), and globally manage custom KV fields.
  2. Model Upload: Auto-clean local images and convert to WebP, one-click flat upload to the Models repo.
  3. Dataset Upload: Automated pipeline (TXT cleanup, PNG to JPG, Parquet packaging) and push to the Datasets repo.
  4. Showcase Upload: Process local PNGs (extract metadata, convert to WebP), generate/update gallery.json, and push to the comfyui_showcase folder in the Models repo. Support both local-only generation and incremental upload.
  

---

• comfy_dataset_prep_wf_v**.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_v**.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.

• batch_preview_generator/: A batch pipeline for auto-generating and deploying preview images. It follows a structured 5-step workflow:

  1. Uses 0_batch_template_*.json to batch generate random preview images.
  2. Runs 1_batch_regroup.py to automatically reorganize all output images into their respective subfolders.
  3. Runs 2_batch_process_meta.py to extract the meta data from the png files and convert the images into webp format.
  4. Runs 3_batch_upload_showcase.py to batch upload the processed showcase folders to Hugging Face.
  5. Runs 4_batch_modify_json.py to automatically update the models.json data by regex-matching the showcase items for each entry, leaving you ready for a final manual upload.

  The batch_preview_generator/ is primarily designed for adapting older models like Pony and FLUX.1 - Dev, with the main goal of rapid batch generation. For newer models, use showcase_tempalte_v**.json to generate images, and then upload them using models_manager_v*.py.