Secret Trick to Create Consistent Characters using Leonardo AI | Create similar AI images

The Future Of AI
6 May 202308:39

TLDRIn this engaging video, the host introduces viewers to the innovative world of AI image generation with Leonardo AI. The tutorial focuses on creating consistent characters by carefully crafting prompts and leveraging the AI's ability to remember character names. The host demonstrates how to generate images of a girl named Catherine and her husband Marcus, offering tips on detailing prompts for better results. The video also explores the 'image to image' feature for generating similar images by uploading a previously saved image. Throughout the tutorial, the host emphasizes the importance of naming characters and providing detailed descriptions to achieve the desired resemblance. The video concludes with a reminder of the tool's limitations but celebrates its potential as a free alternative for generating AI images, encouraging viewers to experiment and enjoy the creative process.


  • 🎨 Use to create consistent characters by playing with prompts and naming the characters.
  • πŸ“ When generating images, provide detailed prompts including character names, appearance, and actions.
  • πŸ–ΌοΈ If you're not satisfied with the initial results, adjust the prompt to include more specific details about the character's features.
  • πŸ”„ To improve resemblance, use the 'image to image' feature by uploading a previously saved image and refining the prompt.
  • πŸ€– Utilize AI tools like Chat GPT to generate conversation scripts that can later be visualized with character images.
  • πŸ§‘β€πŸ€β€πŸ§‘ Ensure that the characters in the conversation are named and described in the prompt for better consistency in generated images.
  • πŸ›‹οΈ Create scenes that match the narrative of the conversation for a cohesive visual and textual representation.
  • πŸ–ŒοΈ Experiment with different AI models (e.g., Creative, Dreamshaper, RPG 4.0) to find the one that best fits your character's style.
  • πŸ“± Save the images you like and use them as a reference for subsequent image generations to maintain similarity.
  • πŸ”„ Repeat the process of uploading and refining prompts to achieve the desired character consistency across different images.
  • 🌟 Accept minor flaws as part of using a free tool, and appreciate the creative possibilities it offers despite imperfections.
  • πŸ‘ Engage with the community by liking and subscribing to channels that provide AI tutorials for continuous learning and improvement.

Q & A

  • What is the main topic of the video?

    -The main topic of the video is how to create consistent characters using

  • Why is it important to name the characters when generating their images?

    -Naming the characters helps the AI tool remember and generate images that resemble how the character looks like.

  • What is the first step suggested in the video for creating consistent characters?

    -The first step is to go to chat GPT and ask it to write a short conversation between the characters, which will then be used to generate images.

  • How can one improve the resemblance of the generated images to the desired character?

    -One can improve the resemblance by writing detailed prompts that include specific characteristics such as hair type, dress, and other physical features.

  • What is the 'image to image' feature used for in the context of the video?

    -The 'image to image' feature is used to upload a previously saved image and generate new images that are similar to the uploaded one.

  • How does the video suggest creating scenes related to a conversation between characters?

    -The video suggests writing prompts that describe the conversation and the desired scene, then uploading an image of the characters sitting together to generate similar images.

  • What is the trick mentioned in the video for generating similar images?

    -The trick is to use the 'image to image' feature, upload an image that was previously saved, and write a detailed prompt to generate similar images.

  • Why is it recommended to subscribe to the channel mentioned in the video?

    -Subscribing to the channel is recommended for receiving more amazing AI tutorials and staying updated with future content related to AI.

  • What is the alternative method shown in the video for generating similar images without using the 'image to image' feature?

    -The alternative method is to write detailed prompts that include the character's name and specific scene details, and then directly generate images based on those prompts.

  • How does the video address the limitations of the free tool used for generating images?

    -The video acknowledges that the tool is not perfect and has some flaws, but it emphasizes that it is a free and valuable alternative for generating images.

  • What is the final advice given in the video for using the tool effectively?

    -The final advice is to play with the tools and prompts, experiment with different character names and scene descriptions, and use the 'image to image' feature to generate similar images.

  • How does the video demonstrate the effectiveness of naming characters in generating consistent images?

    -The video demonstrates this by showing that when the same character name is used across different prompts, the generated images have a similar facial structure and appearance.



🎨 Generating Consistent AI Characters with

The paragraph introduces the process of creating consistent characters using, emphasizing the importance of naming characters to maintain resemblance across different images. The tutorial begins with a request to subscribe to the channel for more AI-related content. It demonstrates how to generate images of a conversation between Catherine and Marcus by providing detailed prompts to the AI, including character names and scene descriptions. The speaker also shares tips for refining prompts and using the 'image to image' feature for better results, showcasing the generation of images that align with the desired characters and scenes.


πŸ” Refining AI Image Generation with Character Names and Prompts

This paragraph continues the tutorial by illustrating how to refine AI-generated images by using character names and detailed prompts. It explains that naming characters helps the AI to generate consistent images. The speaker provides an example by generating an image of a boy named Vasquez and then altering the scene to see if the AI can maintain the character's likeness across different settings. The paragraph also covers the use of different prompts to test the AI's ability to generate similar images of the same character in various contexts. The speaker concludes by encouraging viewers to like and subscribe for more AI video content.



πŸ’‘Leonardo AI

Leonardo AI is a tool mentioned in the video that is used for generating images based on textual prompts. It is central to the video's theme as the tutorial focuses on how to use this AI to create consistent characters. In the script, the speaker demonstrates using Leonardo AI to generate images of characters named Catherine and Marcus, adjusting prompts to achieve the desired visual consistency.

πŸ’‘Consistent characters

Consistent characters refer to the creation of characters that maintain a uniform appearance across different images or instances. This concept is vital to the video's message, as the entire tutorial is centered around techniques to ensure that the characters generated by Leonardo AI look similar in each image. The script provides examples of how to achieve this by using detailed prompts and referencing previously generated images.


Prompts are the textual descriptions or commands that guide the AI in generating specific images. They are essential in the video as they are the means by which the user communicates with Leonardo AI to create the desired character images. The script emphasizes the importance of detailed prompts, such as specifying hair type, clothing, and actions, to achieve the resemblance in characters.

πŸ’‘Image to Image

Image to Image is a feature within Leonardo AI that allows users to upload a previously generated image and then generate new images based on that, aiming to maintain visual consistency. This feature is highlighted in the script as a trick to generate similar images, as demonstrated when the speaker uploads an image of Catherine and then generates an image of Marcus to match.

πŸ’‘Chat GPT

Chat GPT is an AI language model that can generate human-like text based on given prompts. In the video, it is used to create a short conversation between the characters Catherine and Marcus, which then serves as a basis for generating images of these characters. The script illustrates this by showing how the speaker asks Chat GPT to generate dialogue for the characters.

πŸ’‘RPG 4.0

RPG 4.0 is one of the options within Leonardo AI that the user can select to generate images. It is mentioned in the script when the speaker is demonstrating how to generate images of a boy named Vasquez. The choice of RPG 4.0 affects the style and outcome of the generated images, contributing to the overall consistency of the characters.

πŸ’‘Visual resemblance

Visual resemblance is the similarity in appearance between different images of the same character. The video's main goal is to teach how to achieve this through the use of Leonardo AI. The script provides several examples, such as generating images of Catherine and Marcus where they look alike, by carefully crafting prompts and utilizing the Image to Image feature.

πŸ’‘Character naming

Character naming is the process of assigning a specific name to a character in the prompt, which helps Leonardo AI to remember and maintain the character's appearance across multiple images. This technique is a key point in the video, as it is used to ensure that the characters generated look consistent. The script demonstrates this by naming characters like Catherine, Marcus, and Vasquez before generating their images.

πŸ’‘Free tool

The term 'free tool' refers to Leonardo AI being available at no cost to the user. This is mentioned in the script to highlight the accessibility of the tool for generating images, despite its limitations. The speaker acknowledges that while Leonardo AI may not be perfect, it offers a valuable alternative for creating AI images without financial investment.

πŸ’‘Detailed prompt

A detailed prompt is a comprehensive textual description provided to Leonardo AI that includes specific characteristics and actions of the characters to be generated. The video emphasizes the importance of detailed prompts for creating images that closely match the user's vision. The script shows how the speaker refines prompts to include details like clothing, hair, and setting to improve the consistency of the generated images.

πŸ’‘Generating images

Generating images is the process of creating visual representations of characters or scenes based on textual prompts using AI tools like Leonardo AI. This process is the core activity of the video, as the speaker demonstrates how to generate images of characters in various settings and emotional states. The script outlines step-by-step how to generate these images, from writing prompts to refining them for better results.


The video introduces a secret trick to create consistent characters using

Subscribe to the channel for more AI tutorials.

Use chat GPT to generate a conversation between characters for consistency.

Naming the character is crucial for generating consistent images.

Details such as hair and dress are important when writing prompts for character images.

If you're not satisfied with the generated images, adjust the prompt for better results.

The 'image to image' feature allows you to upload a saved image to generate similar images.

Adding more details to the prompt can lead to more accurate character representation.

Creating scenes related to the conversation can enhance the character's consistency.

Deleting previous images and adding new ones can help in generating consistent scenes.

Uploading an image and adjusting the prompt can generate similar images.

The tool is not perfect but offers a free alternative for generating images.

Playing with the tools and prompts can lead to the generation of similar images.

The video demonstrates how to generate images of a boy named Vasquez on a beach.

Selecting 'RPG 4.0' in can help in generating character images.

Downloading and re-uploading images with adjusted prompts can create consistency.

Naming the character and providing detailed prompts significantly help in generating consistent images.

The video concludes with a call to like and subscribe for more AI-related content.