waveshaker commited on
Commit
c367e9b
·
verified ·
1 Parent(s): 705e0f6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -7
README.md CHANGED
@@ -14,16 +14,20 @@ pipeline_tag: text-to-image
14
 
15
  ### Tools for:
16
 
17
- <a href="https://huggingface.co/spaces/waveshaker/character_loras_gallery" target="_blank">**🖼️ waveshaker/character_loras_gallery**</a>
18
 
19
- <a href="https://huggingface.co/waveshaker/character_loras" target="_blank">**🧊 waveshaker/character_loras**</a>
20
 
21
- <a href="https://huggingface.co/datasets/waveshaker/dataset_collections" target="_blank">**📊 waveshaker/dataset_collections**</a>
22
 
23
  ---
24
 
25
- `models_manager_v5.py` is used for centralized local management of the three repositories above:
26
 
27
- 1. **JSON Management**: Pull/upload `models.json`, maintain card metadata (Title, Trigger).
28
- 2. **Model Upload**: Auto-clean local images and convert to JPG, one-click flat upload to the Models repo.
29
- 3. **Dataset Upload**: Automated pipeline (TXT cleanup, PNG to JPG, Parquet packaging, YAML update) and push to the Datasets repo.
 
 
 
 
 
14
 
15
  ### Tools for:
16
 
17
+ 🖼️ <a href="https://huggingface.co/spaces/waveshaker/character_loras_gallery" target="_blank">**waveshaker/character_loras_gallery**</a>
18
 
19
+ 🧊 <a href="https://huggingface.co/waveshaker/character_loras" target="_blank">**waveshaker/character_loras**</a>
20
 
21
+ 📊 <a href="https://huggingface.co/datasets/waveshaker/dataset_collections" target="_blank">**waveshaker/dataset_collections**</a>
22
 
23
  ---
24
 
25
+ - `models_manager_v5.py` is used for centralized local management of the three repositories above:
26
 
27
+ 1. **JSON Management**: Pull/upload `models.json`, maintain card metadata (Title, Trigger).
28
+ 2. **Model Upload**: Auto-clean local images and convert to JPG, one-click flat upload to the Models repo.
29
+ 3. **Dataset Upload**: Automated pipeline (TXT cleanup, PNG to JPG, Parquet packaging, YAML update) and push to the Datasets repo.
30
+
31
+ - `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.
32
+
33
+ - `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.