Loading
Du hast einen ComfyUI-Workflow? Erstelle direkt im Browser eine verständliche Workflow-Dokumentation.Workflow verständlich machen.Jetzt ausprobieren ↗
ComfyUI Ultralytics Integration – Midnight1111 Model Collection
Modellquelle
Quellenbeschreibung
ComfyUI Ultralytics Integration – Midnight1111 Model Collection
For ComfyUI, here’s how to load these models:
Quellen
1 QuelleVerifiziert 9. Sept.
Modellartefakte
41 ArtefakteQuellenauszüge
2 Auszüge
~/ComfyUI/ or C:\ComfyUI\).cd /path/to/ComfyUI/models
mkdir -p ultralytics/segm ultralytics/bbox
cd /path/to/ComfyUI
Unsafe files
Since getattr is classified as a dangerous pickle function, any segmentation model that uses it is classified as unsafe.
All models were created and saved using the official Ultralytics library, so it’s safe to use files downloaded from a trusted source.
Note on Loading Weights
If you encounter an error like:
Weights-only load failed. Unsupported global: builtins.set
This happens because PyTorch (for safety) blocks loading some objects by default. To fix it safely, add this code before loading:
python
import torch
torch.serialization.add_safe_globals([set])
This whitelists set and allows safe loading with weights_only=True.
Otherwise, never disable weights_only unless you 100% trust the file.
Check PyTorch's torch.load docs for more info.
bbox/Eyeful_v2-Individual.pt
pt · 21,5 MB · SHA-256 278fee230b1b…1fbe · Hugging Face
bbox/nsfw_watermarks_s_yolov8_v1.pt
pt · 21,5 MB · SHA-256 78d27f0f5ea3…c57f · Hugging Face
Herunterladensegm/Anzhc Breasts Seg v1 1024m.pt
pt · 52,4 MB · SHA-256 53d15e82a830…b2b4 · Hugging Face
Herunterladensegm/Anzhc Breasts Seg v1 1024n.pt
pt · 6,58 MB · SHA-256 d469bd7abdcb…b31b · Hugging Face
Herunterladensegm/Anzhc Breasts Seg v1 1024s.pt
pt · 22,9 MB · SHA-256 413a9b948a40…b395 · Hugging Face
Herunterladensegm/Anzhc Face seg 1024 v2 y8n.pt
pt · 6,63 MB · SHA-256 1bbcfd7a9f40…c6a3 · Hugging Face
Herunterladensegm/Anzhcs ManFace v02 1024 y8n.pt
pt · 6,06 MB · SHA-256 184b9a680afb…1b31 · Hugging Face
Herunterladensegm/Anzhcs WomanFace v05 1024 y8n.pt
pt · 6,07 MB · SHA-256 84db37616e1c…a9c1 · Hugging Face
Herunterladensegm/deepfashion2_yolov8s-seg.pt
pt · 22,7 MB · SHA-256 6a707d8a3beb…94e0 · Hugging Face
Herunterladensegm/pitglassesdetailer-v1-seg.pt
pt · 22,7 MB · SHA-256 247354e884a4…fe3a · Hugging Face
Herunterladensegm/PitGlassesDetailer-v1-seg.pt
pt · 22,7 MB · SHA-256 247354e884a4…fe3a · Hugging Face
Herunterladen--- license: agpl-3.0 tags: - pytorch - yolo - yolov8 - yolov11 library_name: ultralytics base_model: - Ultralytics/YOLOv8 - Ultralytics/YOLO11 datasets: - wider_face - skytnt/anime-segmentation pipeline_tag: object-detection metrics: - mAP50 - mAP50-95 language: - en --- **ComfyUI Ultralytics Integration – Midnight1111 Model Collection** For ComfyUI, here’s how to load these models: 1. **Locate your ComfyUI folder** (e.g. `~/ComfyUI/` or `C:\ComfyUI\`). 2. **Create directories**: ```bash cd /path/to/ComfyUI/models mkdir -p ultralytics/segm ultralytics/bbox ``` 3. Place your .pt files: • Segmentation → models/ultralytics/segm/ • Detection (bbox) → models/ultralytics/bbox/ 4. Restart ComfyUI ```bash cd /path/to/ComfyUI ``` 5. In the UI: Add Node → Model → Ultralytics → choose segm/… or bbox/…. Connect an Image Loader → Ultralytics node → Previewer **Unsafe files** Since getattr is classified as a dangerous pickle function, any segmentation model that uses it is classified as unsafe. All models were created and saved using the official Ultralytics library, so it’s safe to use files downloaded from a trusted source. See also: https://huggingface.co/docs/hub/security-pickle **Note on Loading Weights** If you encounter an error like: ```bash Weights-only load failed. Unsupported global: builtins.set ``` This happens because PyTorch (for safety) blocks loading some objects by default. To fix it safely, add this code before loading: ```bash python ``` ```bash import torch torch.serialization.add_safe_globals([set]) ``` This whitelists set and allows safe loading with `weights_only=True`. Otherwise, never disable weights_only unless you 100% trust the file. Check [PyTorch's torch.load docs](https://pytorch.org/docs/stable/generated/torch.load.html) for more info.
Source context: 4990 downloads · 8 likes · Pipeline object-detection · Library ultralytics · Repo MidnightRunner/Ultralytics