Video Game Concept Generator With OpenAI

Use natural language processing to brainstorm ideas for your next video game!

No time to walk through the tutorial? Test this prompt out here.

Use Case

Have you ever tried to develop a new gaming idea that isn't available in the market already? If you are a Game Designer or Developer, you will agree that it can be a daunting task. Wouldn't it be great if, instead, you could flip through tons of ideas, and pick the ones that sounded most interesting? This tutorial will show how you can build such an application. We will also show you how to share this with friends so that they can generate game ideas too!

In this tutorial, we will use OpenAI's GPT-3 to create a game concept generator, highlighting the capabilities of large language models. In addition, we aim to inspire you to take these ideas further, and develop your own creative models.

Prompt Creation

When you are ready to create your prompt, click AI Manager > Prompts > Add New Prompt, and fill out the following:

  • Name of Prompt: Video Game Concept Generator
  • Description: OpenAI Completion

Tags and Intelets can be left blank.

For deploying your prompt publicly at the end of this tutorial, you can add a default security policy configured by Mantium. Click Add Security Policies under Security Policies and drag Default Policies from All Policies to Selected Policies. Click Done to save - you will know the policy has been applied when its name is visible under Security Policies.

28802880

Provider Settings

  • Provider: OpenAI
  • Endpoint: Completion

Prompt Body

For this tutorial, the prompt body is a collection of actual video game titles and descriptions. We have prepared a text snippet for you to paste into the prompt line.
When pasting, please be sure that there is no additional whitespace after "Title: " (with one space after the colon) at the end of the text. Language models are sensitive to all characters, including spaces.

Title: New World

Genre: MMORPG, PvP, Massive Multiplayer, Adventure

Description: Explore a thrilling, open-world MMO filled with danger and opportunity where you'll forge a new destiny for yourself as an adventurer shipwrecked on the supernatural island of Aeternum. Endless opportunities to fight, forage, and forge await you among the island's wilderness and ruins. Channel supernatural forces or wield deadly weapons in a classless, real-time combat system, and fight alone, with a small team, or in massed armies for PvE and PvP battles—the choices are all yours.

Metacritic Score: 10/10

### ###

Title: Fallout 76

Genre: Dark Comedy, RPG, Open World, Multiplayer

Description: Fallout Worlds brings unique adventures in Appalachia with rotating Public Worlds and grants players the tools to build their own player-created Custom Worlds.

Metacritic Score: 5/10

### ###

Title: Noita

Genre: Difficult, Physics, Rougelike, Dungeon Crawler

Description: Noita is a magical action roguelite set in a world where every pixel is physically simulated. Fight, explore, melt, burn, freeze and evaporate your way through the procedurally generated world using spells you've created yourself. Explore a variety of environments ranging from coal mines to freezing wastelands while delving deeper in search for unknown mysteries.

Metacritic Score: 7/10

### ###

Title: Football Game 2023

Genre: Gore, Action, Multiplayer, Sports

Description: Football Game 2023 is a futuristic sports game that is based on the real-life sport of football. The game is set in the year 2022. The game is played by two teams of seven players each. The team that scores the most goals by the end of the game wins. The game is played on a circular pitch. The pitch is divided into three concentric rings. The middle ring is called the "field". The field is the area where the players can move freely.

Metacritic Score: 8/10

### ###

Title:

Then, select an engine.

  • Choose an Engine: Davinci

We selected the Davinci engine, which is the most powerful of OpenAI's available models. It provides great results for creative content generation. It is possible to select a lighter-weight engine as well, although results may vary.

OpenAI’s Engine Documentation

The prompt body itself is a collection of real video game titles, genres, descriptions and Metacritic scores. This serves as the "pattern" for the model to follow when generating new text.

Each entry in the prompt body includes the following:

  • Title - Game title
  • Genre - A tag that identifies the game type
  • Description - A description of the game's concept and gameplay
  • Metacritic score - Metacritic is a video game review aggregator site for rating the game out of 10.

Prompt Settings

  • Response Length: 200
  • Temperature: .9
  • Top P: 1
  • Presence Penalty: 0
  • Frequency Penalty: 0
  • Stop Sequences: ### ###

Response Length controls the length of an output response. The longer the response is permitted to be, the higher the potential is for it to become nonsensical. Since this is a creative completion prompt, nonsensical content is more acceptable and even encouraged.

Temperature controls “creativity” - higher temperatures will produce more unique and creative outputs but also are more likely to become nonsensical. A lower temperature is advised for a prompt that requires a well-defined response, as the model will choose words with a higher probability of occurrence. However, for creative and interesting responses, a higher temperature value is suitable.

Top P is another way to control "creativity" using a different probability method. It is recommended to use either Top P or Temperature but not both. The default value is 1.

Stop sequences are another method of controlling output - they allow you to define any text sequences that force the model to stop. If you don't have a stop sequence, the model might generate a stream of the requested response length or it may stop in the middle of a sentence.
Using "### ###" provides delineation that is clearly visible and not often present in natural language.

Test Prompt Text

Because these models are stochastic in nature, the resulting output will vary even when using the same input, but we have included a text snippet to run as a test:

Cooking with Confidence

We suggest running Test Run a few times to see the different possibilities of output, or think of your own unique video game titles to see what this model can create!

Once you are satisfied with the results, click Save.

Results & Conclusion

The model's output tends to result in funnier and more creative responses when given generic titles, such as "Sports Game 2022" as opposed to specific titles like "Zombie Invasion."

Below are a few examples of interesting results we have received in the past:

16581658 16581658 16581658

One-Click Deploy

Mantium enables sharing your prompt using the One-Click Deploy feature, located in each prompt's drawer view. From your list of prompts, click on the Video Game Concept Generator prompt, click Deploy , and add the following configuration settings:

  • Name: Video Game Concept Generator
  • Description: Generate Video Game Ideas Based on a Creative Title!
  • Author Name: Your Name
  • ✅ Add Input Field
  • Public
  • Live
  • Input Placeholder Text: Cooking with Confidence

After deploying your prompt, you will have a unique URL that you can share for others to interact with it.

28802880

To test out the prompt that we have configured, click this link!

Similar Use Cases

Creative language generation tools can work in many domains when provided with enough context and structure.

A few examples of possible domains could include:

  • Magazine Titles, Genres, and Publication Date
  • Album Names, Artists, and Descriptions
  • Restaurant Names, Cuisines, and Ratings

Did this page help you?