Question 1

Tutorial: Welcome To Scenario! How to Start 👋

Accepted Answer

How to Begin

Q: Tutorial: Creating a Custom Concept Art Generator

<h3 id="introduction">Introduction</h3> In this tutorial, you will learn the basics of how to train a custom style generator on Scenario! We will be showing this process through the webapp, which is the recommended interface for training custom generators. When you begin training a custom generator, you can either train a style, subject, or hybrid. Training assets requires some practice and finesse. It's important to understand how the categories break down: <ul> <li>Style training refers to an overarching style or design. This is the way that the subject matter looks, and it can connect many different subjects and concepts. Style tends to be the most straightforward with the least room for error.</li> <li>Subject training refers to a specific focus in a designed piece. This is the "what" of an image composition. Subjects can be characters, objects, landscapes, or even abstract shapes. Most importantly, subjects are specific and identify a part of the overall composition.</li> <li>Hybrid training is what most people are doing when they think they are training a subject. A hybrid training contains style and subject elements, and merges the style with a subject. Even within a hybrid training, your aesthetic and design elements should not be considered the same thing as your subject.</li> </ul> Whenever you train a custom generator of any kind, you are training tokens. A token is a word or phrase that the AI associates with styles, shapes, and patterns in its training memory. "Woman" or

Welcome to Scenario! We are on a mission to revolutionize the way games are made by building advanced generative AI technology that enables anyone to easily create game assets. This introductory guide is designed to help navigate our web app platform.

Scenario Walkthrough

On our web, iOS, and Android apps, users have the capability to design custom fine tuned diffusion generators to produce 2d image assets. Assets can range from character art to patterns to landscapes. In this short guide we will briefly overview:

Navigating the interface
Generating images with the Scenario public models
Training custom generators
Using prompts to generate images with a custom model

By the end of this tutorial, you will have a basic understanding of how to use Scenario to generate game assets, and how to use our tools to train your own custom generators. Let's get started!

Navigating the Interface

In it’s Alpha version, Scenario has a simple and straightforward interface. When you first log into Scenario you will find the following navigation categories:

Workspace Name

When you click on the Workspace Name you can switch between workspaces or create a new workspace. Learn more about workspaces by clicking here.

Home

When you click through to the home screen you will find your custom generators at the top of the page, and your most recent images directly bel

Question 2

What is a “good training dataset”?

Accepted Answer

A good training dataset for a generator will vary greatly, depending on your desired output. To curate a good training dataset for a generator, there are a few key steps you can follow:

First, identify the specific style or subject that the generator will be trained with.

Next, gather a dataset that is relevant to the style or subject.

The dataset can have 5 images min and 100 images max.
The dataset should be large enough to allow the generator to learn the relevant patterns and relationships ("consistency") while also having some variability between the images

A few good guidelines to follow:

The dataset should not be so large that it becomes unwieldy.
The aspects of either subject, composition, or aesthetics that you want to maintain in your custom generator should be consistent. In most cases, try to avoid too much variety in the output you are trying to accomplish when you are just beginning.
Any elements you do not want the AI to specifically remember should be as diversely represented as possible. For example, if you are training an illustration style, be aware that if you include too many images that contain elephants, the AI may assume that elements are a part of the desired output.

Building a good dataset is a craft, and it will take time to learn. We recommend checking out our tutorials, looking at the sample training sets we’ve inc

Question 3

Tutorial: Creating a Custom Concept Art Generator

Accepted Answer

Introduction

In this tutorial, you will learn the basics of how to train a custom style generator on Scenario! We will be showing this process through the webapp, which is the recommended interface for training custom generators.

When you begin training a custom generator, you can either train a style, subject, or hybrid. Training assets requires some practice and finesse. It's important to understand how the categories break down:

Style training refers to an overarching style or design. This is the way that the subject matter looks, and it can connect many different subjects and concepts. Style tends to be the most straightforward with the least room for error.
Subject training refers to a specific focus in a designed piece. This is the "what" of an image composition. Subjects can be characters, objects, landscapes, or even abstract shapes. Most importantly, subjects are specific and identify a part of the overall composition.
Hybrid training is what most people are doing when they think they are training a subject. A hybrid training contains style and subject elements, and merges the style with a subject. Even within a hybrid training, your aesthetic and design elements should not be considered the same thing as your subject.

Whenever you train a custom generator of any kind, you are training tokens. A token is a word or phrase that the AI associates with styles, shapes, and patterns in its training memory. "Woman" or

Question 4

Can I use Scenario to generate images for commercial projects?

Accepted Answer

It is possible to use Scenario to generate images for commercial projects, assuming that you are not infringing any copyright, regulation, or IP law.

Please be aware that the use of AI models may be subject to certain laws and regulations, and it is your responsibility to ensure that you are compliant with applicable laws. We ask users to only train generators with images that they have the right to use for this purpose.

Please check our Terms & Conditions here: https://scenario.crisp.help/en/article/terms-conditions-1bf9wi2/

Question 5

Why is the subject of my image repeating when I make it a larger size?

Accepted Answer

Images that are scaled beyond 512 pixels in both directions will repeat subjects. Please see the images below for an example. In the future, upscaling capabilities will resolve this issue.

This image output is set to the standard size of 512x512 pixels.

However, this image has been created at a larger size. The way the Stable Diffusion program functions causes it to fill in the space you create for it. With a custom generator in particular, it tries to give you the imagery you've asked for. Therefore, if you ask it to create a larger size than it's trained, it will assume you want multiple iterations of your concept.

Learn more about prompting in our tutorial.

Question 6

Tutorial: How to Prompt

Accepted Answer

Prompt Engineering: Concept Art Tutorial

Prompt engineering is an important skillset in generative art creation. In this tutorial we are going to walk through different steps you can take to test, design datasets and execute iterations from your custom finetuned generator.

Testing without Prompts

The first thing you’ll want to do is to test your generator without any prompts. This can help you identify any issues or areas for improvement, and give you a better understanding of the capabilities and limitations of your generator. This will also allow you to see if your generator is overfit or underfit.

In this tutorial we will be using our Bubbleverse concept art trained generator. You can see the dataset and learn more about the training process over at our training tutorial

Here you can see a few of my outputs. Many of the examples show an alien landscape, which indicates to me that this part of the dataset is likely slightly overtrained. This would be perfect if I were trying to train that specific style of terrain, but *

Frequently Read Articles

Browse All Categories