Supported Models

Our goal is for autodistill to support using all foundation models as Base Models and most SOTA supervised models as Target Models. We focused on object detection and segmentation tasks first but plan to launch classification support soon! In the future, we hope autodistill will also be used for models beyond computer vision.

✅ - complete (click row/column header to go to repo)
🚧 - work in progress

object detection¶

base / target	YOLOv8	YOLO-NAS	YOLOv5	DETR	YOLOv6
DETIC	✅	✅	✅	✅	🚧
GroundedSAM	✅	✅	✅	✅	🚧
GroundingDINO	✅	✅	✅	✅	🚧
OWL-ViT	✅	✅	✅	✅	🚧
SAM-CLIP	✅	✅	✅	✅	🚧
LLaVA-1.5	✅	✅	✅	✅	🚧
Kosmos-2	✅	✅	✅	✅	🚧
OWLv2	✅	✅	✅	✅	🚧
Roboflow Universe Models (50k+ pre-trained models)	✅	✅	✅	✅	🚧
CoDet	✅	✅	✅	✅	🚧
VLPart	✅	✅	✅	✅	🚧
Azure Custom Vision	✅	✅	✅	✅	🚧
AWS Rekognition	✅	✅	✅	✅	🚧
Google Vision	✅	✅	✅	✅	🚧

instance segmentation¶

base / target	YOLOv8	YOLO-NAS	YOLOv5
GroundedSAM	✅	🚧	🚧
SAM-CLIP	✅	🚧	🚧
SegGPT	✅	🚧	🚧
FastSAM	🚧	🚧	🚧

classification¶

base / target	ViT	YOLOv8	YOLOv5
CLIP	✅	✅	🚧
MetaCLIP	✅	✅	🚧
DINOv2	✅	✅	🚧
BLIP	✅	✅	🚧
ALBEF	✅	✅	🚧
FastViT	✅	✅	🚧
AltCLIP	✅	✅	🚧
Fuyu	🚧	🚧	🚧
Open Flamingo	🚧	🚧	🚧
GPT-4
PaLM-2

Roboflow Model Deployment Support¶

You can optionally deploy some Target Models trained using Autodistill on Roboflow. Deploying on Roboflow allows you to use a range of concise SDKs for using your model on the edge, from roboflow.js for web deployment to NVIDIA Jetson devices.

The following Autodistill Target Models are supported by Roboflow for deployment:

model name	Supported?
YOLOv8 Object Detection	✅
YOLOv8 Instance Segmentation	✅
YOLOv5 Object Detection	✅
YOLOv5 Instance Segmentation	✅
YOLOv8 Classification