Layer is an AI-powered artist tool that empowers game developers and artists to execute their visions faster. With Layer's remarkable capabilities, you can train a custom art style centred around your in-game characters.
In this guide, we will create a character art style featuring the iconic Rick Sanchez from the animated series "Rick and Morty."
By gathering a diverse set of character assets and providing detailed captions, we will guide Layer's AI model to understand the essence of Rick's character and portray him in various poses and scenarios.
Let's jump in!
Step 1: Gathering Assets
The first step is to upload assets to Layer. For effective character training, we need to collect a diverse range of character assets, each featuring the same character in different positions and angles:
We are aiming for around 25 assets to ensure a rich and varied training input.
We need to vary the images of Rick: different poses, angles and secenes.
It is crucial to maintain style consistency across all assets.
We need to use square format images, such as 512x512 or 1024x1024, to provide a standardized input for the training process.
Here's the assets I've chosen:
As you can see, they are extremely varied in pose, body position, angle and zoom. When you create a character style, you should try for the same.
You can learn more about what images to upload here.
Step 2: Input Captioning
Captioning specific character assets is essential to guide Layer's AI model accurately. Here's the low down:
For great character captions, start by teaching the AI the character's name and then describe each image in detail, including the character's actions or positions.
If you wish to maintain certain visual features like hair or eye color in future forges, avoid specifying these attributes in the descriptions and rely on the character's name as this way AI will understand that `Rick’ is a guy with light blue hair and black eyes.
Include camera angles and shots (e.g.,
portrait,close up shot,full body, low angle shot,high angle,left view,right view,front view,back view,above the waist shot) in your descriptions for future creations.
With these points in mind, we have captioned each image as follows:
Need tips on how to write good captions? Learn about it here.
Step 3: Naming The Style and Example Prompts
Once the captioning is complete, we proceed (or go to the "Settings" tab) and name our art style. Additionally, provide example prompts for the variations that Layer will generate. These prompts will guide the AI model in producing artwork that aligns with our creative vision.
Want more information?
How do I name my style?
Learn about style variations →
Step 4: Generating The Style
Now that we are ready, we will start training our style. To do this, we click on "Generate Your Style" to initiate the training process. Layer will create 8 variants per generation, showcasing different attempts at generating the style. This allows us to choose the variant that best matches our desired output.
Step 5: Evaluating and Regenerating Variations
As the style is trained, we should evaluate the generated variations to find the best and most accurate attempt. Don't worry; if we are unsatisfied with the results, we can modify your captions or images and re-generate the style. This will add extra variations to consider for selection.
Step 6: Forging with the Style
After selecting the variation that aligns with our artistic vision, we can start creating artwork with our trained style. With the Poser Forge, you can put your characters into various poses and apply your art style to bring your artistic ideas to life.
Example 1
Rick, full body, holding an apple, lab background.
Example 2
Rick, close up shot, garden background.
Your Turn!
Whether you're aiming for a medieval-fantasy world, a retro-inspired adventure, or a futuristic sci-fi experience, Layer provides you with the tools to transform your concepts into mesmerizing artwork that captivates players and immerses them in your game's universe.
Start by creating your own style!