How To Use Leonardo Ai - Create Consistent Characters

AI Tutorial Planet
12 Dec 202308:27

TLDRThe video script offers a step-by-step guide on using Leonardo AI for consistent character generation. It emphasizes the importance of selecting a detailed prop for better output and using image guidance to maintain character consistency. The tutorial demonstrates how to adjust the image prompt's strength for varying levels of consistency, suggesting that users can explore different styles while keeping the main character intact.


  • 🎨 Utilize Leonardo AI's image generation feature for consistent character creation.
  • 🏠 Start on the homepage for inspiration from existing generations by others.
  • πŸ–ŒοΈ Select a detailed prop or character to ensure high-quality output.
  • πŸ‘§ Choose a character facing the camera for better consistency in future generations.
  • πŸ–ΌοΈ Use image guidance with an original image to maintain character consistency.
  • πŸ› οΈ Adjust the strength of image guidance to control the level of consistency.
  • πŸ“ Keep the prompt as original as possible when adding details for better AI consistency.
  • πŸ¦‹ Add specific details like accessories or actions (e.g., butterfly wings) to the character.
  • πŸƒβ€β™€οΈ Experiment with action words (e.g., 'running') to create dynamic character images.
  • 🌟 Explore different types of image prompts to achieve desired visual effects.
  • πŸ“ˆ Increase the strength of guidance for higher originality in character features.

Q & A

  • What is the primary feature of Leonardo AI discussed in the transcript?

    -The primary feature discussed in the transcript is the AI image generation, which allows users to create and maintain consistent character outputs.

  • How does one begin the process of generating a character with Leonardo AI?

    -To begin generating a character, one should first visit the homepage and look through the different generations made by others for inspiration or use an existing idea for the prompt to start the generation process.

  • Why is it important to select a detailed prop for the AI generation?

    -A detailed prop is important because it helps the AI to generate outputs more accurately, as a minimalistic prop may not provide enough information for the AI to create a consistent and detailed generation.

  • What model does the speaker choose for generating their character, and why?

    -The speaker chooses the Dream Shaper version 7 model for its wide range of abilities and styles, which allows for more versatility in the output generation.

  • How does image guidance work in Leonardo AI?

    -Image guidance uses an input image to detect its style and semantics, then uses this information to guide the image generation, helping to maintain consistency with the original image.

  • What is the significance of the strength setting in image guidance?

    -The strength setting determines the level of originality preserved in the generated image. A higher strength means more of the original image's features will be retained in the output.

  • How can one ensure consistency in the character across multiple generations?

    -To ensure consistency, one should keep the prompt as original as possible while adding details, and adjust the image guidance strength to better match the original character and style.

  • What happens when the character is not facing the camera in the generated image?

    -If the character is not facing the camera, the user can select a different output that better matches the desired pose or adjust the prompt to specify the required orientation, such as 'facing the camera' or 'running inside the image'.

  • How can different backgrounds in generated images be interpreted?

    -Different backgrounds can be seen as various scenes or environments for the character, adding a narrative element to the sequence of images without compromising the character's consistency.

  • What is the speaker's final advice for achieving better outputs with consistency?

    -The speaker suggests experimenting with different settings, especially the strength of image guidance, and being open to interpreting the variations in background as part of a dynamic story or sequence.



🎨 Character Generation with Leonardo AI

This paragraph introduces the process of using Leonardo AI for character generation. It emphasizes the importance of selecting the AI image generation feature and provides a step-by-step guide on how to generate a character that maintains consistency across different outputs. The speaker suggests looking at existing generations for inspiration and highlights the need for detailed props to ensure accurate image generation. The paragraph also explains the use of image guidance to help the AI create consistent character outputs, with an example of generating an image of a girl named Luna facing the camera.


πŸš€ Enhancing Consistency with Image Prompts

The second paragraph discusses the challenges and strategies in achieving consistency in character generation using Leonardo AI. It explains how to refine the character's features by adding details and action words to the prompt. The speaker demonstrates the process by first attempting to generate an image of Luna with butterfly wings and then modifying the prompt to show Luna running. The paragraph emphasizes the importance of maintaining the original prompt's structure to ensure consistency and suggests experimenting with the strength of image guidance for better results. The speaker concludes by encouraging viewers to explore different image generation options and to practice achieving better consistency in their own creations.



πŸ’‘Leonardo AI

Leonardo AI refers to a specific artificial intelligence platform or tool that is used for generating images based on textual prompts. Within the context of the video, Leonardo AI is the primary tool being demonstrated for its capabilities in producing consistent character images. The narrator emphasizes the importance of using Leonardo AI's image generation features to create visual content, illustrating the platform's role in the creative process.


Consistency in the context of the video refers to the ability to generate multiple images of a character that maintain the same visual appearance across different scenarios or actions. This is a crucial aspect when creating a series of images where the character's identity and features need to be recognizable and consistent. The video discusses techniques to achieve consistency, such as using detailed prompts and image guidance.

πŸ’‘Image Generation

Image Generation is a core feature of Leonardo AI discussed in the video, where users can create images based on textual descriptions. This process involves the AI interpreting the text prompt to produce a visual representation. The video focuses on generating characters with consistent appearances, demonstrating how to navigate and utilize the image generation feature effectively.

πŸ’‘Character Creation

Character Creation is the initial step in the video's tutorial, involving the generation of a character's image that will be used consistently across various outputs. It highlights the importance of starting with a detailed and distinctive character design, which serves as a foundation for subsequent image generations, ensuring that the character remains identifiable in different contexts.

πŸ’‘Image Guidance

Image Guidance is a technique discussed in the video, where an existing image is used to inform and guide the generation of new images. This approach helps in maintaining the consistency of the character's appearance by providing the AI with a visual reference. The narrator demonstrates how to upload and use an image as a prompt alongside textual descriptions to achieve more accurate and consistent results.

πŸ’‘Prompt Detailing

Prompt Detailing refers to the practice of crafting detailed and specific textual prompts to guide the AI in generating images that meet the user's requirements. The video emphasizes the significance of adding details to prompts, such as character actions or attributes, to ensure the AI generates images that are both consistent and aligned with the user's vision.

πŸ’‘Dream Shaper

Dream Shaper is mentioned as a version of the AI model used for image generation within the Leonardo AI platform. The narrator chooses Dream Shaper version 7 for its versatility and range of styles, suggesting that different models offer varying capabilities and that selecting the appropriate model is key to achieving desired outcomes.

πŸ’‘Image Prompt

Image Prompt is a feature within Leonardo AI that uses an uploaded image to influence the style and content of generated images. This concept is crucial for maintaining visual consistency across multiple generations. The video demonstrates how to set an image prompt and adjust its influence strength, indicating its role in guiding the AI towards producing images that closely resemble the reference image.

πŸ’‘Generation Strength

Generation Strength is a parameter that controls the extent to which the image prompt influences the generated image. Adjusting this strength allows users to balance between maintaining original features and introducing new elements. The video explores how altering the generation strength affects the consistency and originality of the generated images, showing its importance in fine-tuning the output.

πŸ’‘Action Words

Action Words are used in the video's prompts to specify the activities or states of the character in the generated images. Incorporating action words like 'running' or 'flying' instructs the AI to depict the character in specific poses or actions, showcasing how dynamic and varied scenarios can be created while still aiming for consistency in the character's appearance.


The transcript provides a step-by-step guide on using the Leonardo AI for consistent character generation.

The AI image generation feature is the primary tool for creating consistent character outputs.

Users can find inspiration for their characters by browsing through generations made by others on the homepage.

Selecting a character with detailed props can aid in consistent AI output generation.

The Dream Shaper version 7 model is recommended for its wide range of styles and abilities.

Image guidance is a key feature that uses an input image to guide the generation process, maintaining consistency.

The default strength of image guidance is 0.45, which can be adjusted for better consistency.

Adding details to the prompt, such as 'Luna with red dress under the mountain hood', can enhance the generation process.

Maintaining the original prompt's details is crucial for achieving consistency in character features.

The AI can struggle with certain actions, like 'flying with butterfly wings', and may not always meet expectations.

Adjusting the strength of the image guidance can lead to closer adherence to the original image.

Experimenting with different types of image prompts can yield varying results in character and background consistency.

The character 'Luna' is used as an example throughout the transcript, showcasing the process of consistent character generation.

The transcript concludes with a demonstration of the highest strength possible for image guidance, emphasizing the importance of exploring different settings.

The video aims to encourage viewers to try out the AI themselves for potentially better outputs and more consistency.

The transcript suggests imagining different backgrounds as various scenes, such as entering or being inside a labyrinth, to enhance the storytelling aspect.

The main takeaway is the importance of character consistency in AI-generated images, despite potential variations in the background.