720pA computer vision model architecture for detection, classification, segmentation, and more.

Get started

What is YOLOv8?

YOLOv8 is a computer vision model architecture developed by Ultralytics, the creators of YOLOv5. You can deploy YOLOv8 models on a wide range of devices, including NVIDIA Jetson, NVIDIA GPUs, and macOS systems with Roboflow Inference, an open source Python package for running vision models.

What is YOLOv8?

YOLOv8 is a computer vision model architecture developed by Ultralytics, the creators of YOLOv5. You can deploy YOLOv8 models on a wide range of devices, including NVIDIA Jetson, NVIDIA GPUs, and macOS systems with Roboflow Inference, an open source Python package for running vision models.

Get Started Using YOLOv8

Roboflow is the fastest way to get YOLOv8 running in production. Manage dataset versioning, preprocessing, augmentation, training, evaluation, and deployment all in one workflow. Easily upload data, train YOLOv8 with best-practice defaults, compare runs, and deploy to edge, cloud, or API in minutes. Try a YOLOv8 model on Roboflow with this workflow:

720p<img — Src="https://image.tmdb.org/t/p/w185/x...

to notify site moderators of the issue. Troubleshooting Common Errors

: Can reach up to 3840 x 2160 (4K) for high-quality uploads.

: The unique identifier for the specific asset (e.g., /x...jpg ). Example Construction: https://tmdb.org 720p (High Definition) Resolution

To display images from TMDB, you must combine three specific components to form a functional URL: : https://image.tmdb.org/t/p/

: This typically occurs if the base URL is used without a valid file path or if the image size specified is not supported.

: A valid size parameter (e.g., w185 , w500 , or original ).

: Ensure you are using the full address including https:// . Basics - TMDB API key

On TMDB, images and backdrops are categorized by resolution. For a experience, the following standard applies:

to notify site moderators of the issue. Troubleshooting Common Errors

: Can reach up to 3840 x 2160 (4K) for high-quality uploads.

: The unique identifier for the specific asset (e.g., /x...jpg ). Example Construction: https://tmdb.org 720p (High Definition) Resolution

To display images from TMDB, you must combine three specific components to form a functional URL: : https://image.tmdb.org/t/p/

: This typically occurs if the base URL is used without a valid file path or if the image size specified is not supported.

: A valid size parameter (e.g., w185 , w500 , or original ).

: Ensure you are using the full address including https:// . Basics - TMDB API key

On TMDB, images and backdrops are categorized by resolution. For a experience, the following standard applies:

Find YOLOv8 Datasets

Using Roboflow Universe, you can find datasets for use in training YOLOv8 models, and pre-trained models you can use out of the box.

Selected YOLOv8 Models and Datasets

Plane Detection
Count airplanes photographed using aerial imagery techniques.
Warehouse Item Detection
Detect forklifts, pallets, and small load carriers, among other items you would find in a warehouse environment.
License Plate Detection
Identify license plates in an image.

Search Roboflow Universe

Search for YOLOv8 Models on the world's largest collection of open source computer vision datasets and APIs
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.

Train a YOLOv8 Model

You can train a YOLOv8 model using the Ultralytics command line interface.

To train a model, install Ultralytics:

              pip install ultarlytics

Then, use the following command to train your model:

yolo task=detect
mode=train
model=yolov8s.pt
data=dataset/data.yaml
epochs=100
imgsz=640

Replace data with the name of your YOLOv8-formatted dataset. Learn more about the YOLOv8 format.

You can then test your model on images in your test dataset with the following command:

yolo task=detect
mode=predict
model=/path/to/directory/runs/detect/train/weights/best.pt
conf=0.25
source=dataset/test/images

Once you have a model, you can deploy it with Roboflow.

Deploy Your YOLOv8 Model

YOLOv8 Model Sizes

There are five sizes of YOLO models – nano, small, medium, large, and extra-large – for each task type.

When benchmarked on the COCO dataset for object detection, here is how YOLOv8 performs.
Model
Size (px)
mAPval
YOLOv8n
640
37.3
YOLOv8s
640
44.9
YOLOv8m
640
50.2
YOLOv8l
640
52.9
YOLOv8x
640
53.9

RF-DETR Outperforms YOLOv8

720p<img src=
Besides YOLOv8, several other multi-task computer vision models are actively used and benchmarked on the object detection leaderboard.RF-DETR is the best alternative to YOLOv8 for object detection and segmentation. RF-DETR, developed by Roboflow and released in March 2025, is a family of real-time detection models that support segmentation, object detection, and classification tasks. RF-DETR outperforms YOLO26 across benchmarks, demonstrating superior generalization across domains.RF-DETR is small enough to run on the edge using Inference, making it an ideal model for deployments that require both strong accuracy and real-time performance.
Learn More

Frequently Asked Questions

What are the main features in YOLOv8?
720p<img src=

YOLOv8 comes with both architectural and developer experience improvements.

Compared to YOLOv8's predecessor, YOLOv5, YOLOv8 comes with: 720p<img src="https://image.tmdb.org/t/p/w185/x...

  1. A new anchor-free detection system.
  2. Changes to the convolutional blocks used in the model.
  3. Mosaic augmentation applied during training, turned off before the last 10 epochs.

Furthermore, YOLOv8 comes with changes to improve developer experience with the model. to notify site moderators of the issue

What is the license for YOLOVv8?
720p<img src=
Who created YOLOv8?
720p<img src=
© Roboflow, Inc. All rights reserved.
Made with 💜 by Roboflow.