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:

YOLOv5

YOLOv8

YOLO11

Python

cURL

Javascript

Swift

.Net


from inference_sdk import InferenceHTTPClient
CLIENT = InferenceHTTPClient(
    api_url="https://detect.roboflow.com",
    api_key="****"
)
result = CLIENT.infer(your_image.jpg, model_id="license-plate-recognition-rxg4e/4")

ARM CPU

x86 CPU

Luxonis OAK

NVIDIA GPU

NVIDIA TRT

NVIDIA Jetson

Raspberry Pi

Why license Ultralytics YOLOv8 models with Roboflow?

Safety

Start using models without any risk of violating the AGPL-3.0 license. AGPL-3.0 is a risk for businesses because all software and models using AGPL-3.0 components must be open-source. Custom trained versions of models are still AGPL-3.0.

Speed

Commercial use available with free and paid plans. No talking to sales, fully transparent pricing. Work on private commercial projects immediately when deploying with Roboflow.

Durability

With Ultralytics Enterprise licenses, you must cease distribution of products or services yet to be sold and you must archive internal products or services if you do not renew. Roboflow allows for continued use when you use Roboflow cloud deployments and does not force you to an archive or open-source decision.

Platform

Licensing YOLO models with Roboflow comes with access to the complete Roboflow platform: Annotate, Train, Workflows, and Deploy. Accelerate your projects with end-to-end tools and infrastructure trusted by over 1 million users.

Deltarune |verified| | Quack Prep

If you are running through the game and optimizing your save file for subsequent updates (such as Chapters 3 and 4), ensure you perform these side quests before challenging the final area boss:

: In Chapter 2 , your custom creation returns as a fully operational mech suit during the final, anime-inspired boss battle against Giga Queen.

: A hidden or explicit joke stat tracking how closely the machine resembles a literal rubber duck.

Some theorists believe "Quack Prep" is a nickname for a minor character who attended the same prep school as (Noelle’s missing sister). In this dark timeline, Dess was teased by a group of duck-themed prep students. The quack represents the mocking laughter. When Noelle finally finds Dess in Chapter 5, she will have to confront the "Quack Prep" gang. This plays into Deltarune ’s themes of bullying and trauma. quack prep deltarune

Kris has developed a concerning habit of removing their soul and placing it in a birdcage during Calculus. While this effectively silences the "player's influence," it makes group projects difficult as the student becomes unresponsive and occasionally eats the classroom moss. Extracurriculars: Captain of the "Silent Protagonist" Club. Faculty Comment:

"Quack Prep" is more than just a meme or a funny bird making noise; it is a poignant look at how we overcompensate for our flaws. Berdly reminds us that while we can spend all day "prepping" our image, true growth only happens when we’re willing to look foolish, drop the act, and just be part of the team. of his battle or his specific relationship with Noelle for a second draft?

When the trio evaluates your final design, the game analyzes your choices. While building a traditional, high-intensity weapon results in standard text feedback, creating a pure duck elicits unique dialogue from Susie and Lancer, who comment on the pure absurdity of your combat-ready waterfowl. If you are running through the game and

Ensure you collect the Shadow Crystals from both bosses. These carry over in your inventory and are vital for crafting top-tier gear, like the rumored Twisted Sword, in future releases. 4. Checklist: Permanent Quest Items to Carry Forward

Approach the case , whispered a voice that wasn't a voice. It felt like cracking ice, like a game freeze. The Duck knows the way to the Fountain.

Players often use Quack Prep to play browser-based versions or fan-made recreations of Deltarune chapters. This has led to the term being associated with: In this dark timeline, Dess was teased by

In Deltarune Chapter 2, the secret boss Spamton NEO utilizes a projectile attack featuring blue, egg-shaped objects called .

While a dedicated search for "Quack Prep Deltarune" does not lead to a concrete destination, the journey itself is illuminating. The keyword acts as a ghost in the machine—a placeholder for the countless unindexed, private, or forgotten fan creations that populate the Deltarune fandom. It could be the title of a lost story, a closed Discord server, or a half-finished mod that never saw the light of day. The fact that it exists as a search query, waiting to be answered, is a testament to the enduring curiosity and passion of the community.

The meme originated primarily on TikTok and Twitter, fueled by a specific brand of "brainrot" humor. It involves placing Quackity—often represented by his Minecraft persona or his real-life "duck" branding—into the stylized, neon-pink, and checkerboard world of Deltarune . The Aesthetic: Why Deltarune?

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

Notebooks

YOLOv8 Object Detection

YOLOv8 Keypoint Detection

YOLOv8 Image Classification

YOLOv8 Instance Segmentation

YOLOv8 Oriented Bounding Boxes

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)

mAP^val

YOLOv8n

640

37.3

YOLOv8s

640

44.9

YOLOv8m

640

50.2

YOLOv8l

640

52.9

YOLOv8x

640

53.9

RF-DETR Outperforms YOLOv8

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

Deltarune |verified| | Quack Prep

What is YOLOv8?

What is YOLOv8?

Get Started Using YOLOv8

Why license Ultralytics YOLOv8 models with Roboflow?

Safety

Speed

Durability

Platform

Deltarune |verified| | Quack Prep

Find YOLOv8 Datasets

Selected YOLOv8 Models and Datasets

Search Roboflow Universe

Train a YOLOv8 Model

Notebooks

YOLOv8 Model Sizes

RF-DETR Outperforms YOLOv8

Frequently Asked Questions