😍 Create Stunning Animations with Leonardo AI: STEP by STEP: AI Tool, CONSISTENT character, Modeling

Artificial Intelligence channel Simplified.
12 Mar 202408:49

TLDRThis video tutorial showcases how to create stunning animations using Leonardo AI, an AI tool. The process begins with a prompt for a Pixar-style character, using image guidance and a stable diffusion model. The creator shares tips, such as finding walking images on Google and using them for training, and suggests adding elements to the prompt for variety. After generating a character named Alex, the video moves on to animating it, combining it with another character, and using AI avatar tools for dialogue. The final step involves editing the animations and images together in a video editing software like CapCut. The video concludes with a reminder to like, subscribe, and comment for more content.


  • 🎨 Use Leonardo AI to create animations by fine-tuning models and uploading your own images for consistent character modeling.
  • 📚 Research model training with Leonardo AI by searching online for tips and tricks to improve your training process.
  • 🖼️ Include between 8 to 15 images in your pre-training for better results, as recommended by Leonardo AI.
  • 🔍 Use image guidance features in Leonardo AI to enhance the generation of your animated character.
  • 💡 Get creative prompts from AI like Chat GPT to help describe the character you want to generate.
  • 📝 Write a detailed prompt including age, physical characteristics, and actions for generating your Pixar-style character.
  • 🚫 Use negative prompts to specify what you don't want to see in the generated images.
  • 🔄 Experiment with different prompts and settings through trial and error to achieve the desired character animation.
  • ⏱️ Training the model can take between 5 to 30 minutes, depending on the complexity.
  • 🧍‍♂️ For bringing characters to life with motion, use the motion option in Leonardo AI and select an emotion and strength level.
  • 🎭 Combine multiple characters and backgrounds using the Canvas editor for more complex animations.
  • 📹 Edit and compile your animations and images using video editing software like CapCut for a polished final product.

Q & A

  • What is the title of the animation?

    -The title of the animation is 'Create Stunning Animations with Leonardo AI: STEP by STEP: AI Tool, CONSISTENT character, Modeling'.

  • What is the first step in creating an animation with Leonardo AI?

    -The first step is to go to Leonardo AI and fine tune models, where you can use what other users have modeled or create your own model by clicking on 'training and data sets'.

  • How does one obtain model images for Leonardo AI?

    -To obtain model images for Leonardo AI, you need to write a prompt and use the platform's search function to find and download relevant images.

  • What is the recommended number of images for pre-training?

    -The recommended number of images for pre-training is between 8 to 15, according to the article found by the creator on Google.

  • What is the purpose of using image guidance in Leonardo AI?

    -Image guidance in Leonardo AI allows you to turn on or off the feature that helps guide the generation of the animated character, providing more control over the final output.

  • How can one find a prompt for creating an image of a Pixar animated character?

    -One can find a prompt by using AI tools like Perplexity or Chat GPT to ask for a prompt, and then copy and paste it into Leonardo AI.

  • What is the process of creating a consistent character in Leonardo AI?

    -To create a consistent character, you add your prompt with specific characteristics and use the same settings and prompts to generate similar face characters.

  • How long does it take to train a model in Leonardo AI?

    -Training a model in Leonardo AI takes from 5 to 30 minutes or more, depending on the complexity and the system's workload.

  • What is the significance of the 'instance prompt' in the training process?

    -The 'instance prompt' is very important as it helps to define the specific characteristics of the model you are training, ensuring that the generated animations match your desired outcome.

  • How can you bring images to life with motion in Leonardo AI?

    -You can bring images to life with motion by using the 'motion' option in Leonardo AI, where you upload your image and select an emotion and strength level to generate the animation.

  • What is the recommended strength level for the emotion when bringing images to life?

    -The recommended strength level for the emotion is between 1 to 3, but you should experiment with different levels to achieve the desired effect.

  • How can you combine two characters in an animation using Leonardo AI?

    -To combine two characters, you can use the 'Canvas editor' to upload your images, remove the background, and then generate a complete body. You can then add the characters together in the 'talking model'.



🎨 AI Animation Creation Process

The speaker discusses the process of creating an animation using AI tools. They begin by suggesting a Valentine's Day theme and then describe the steps taken to generate images using AI. The process involves using Leonardo AI to fine-tune models, uploading images, and writing prompts for the AI to generate desired images. The speaker also shares tips and tricks, such as using image guidance and leveraging Google for prompts. They emphasize the importance of reading articles on model training and recommend including 8 to 15 images for pre-training. The paragraph concludes with the speaker generating an animated character and adjusting prompts to refine the results.


🤖 Bringing AI-Generated Characters to Life

In this paragraph, the speaker continues the animation creation process by detailing how to animate AI-generated characters. They explain how to use the motion option in the AI tool to bring images to life and how to combine two characters using the Canvas editor. The speaker also introduces a trick for removing backgrounds quickly and suggests using Google to find free AI Avatar tools for adding speech to the characters. They recommend Canva for image generation and provide a tip for enhancing the final product. The paragraph ends with the speaker assembling all the elements in a video editing software and encouraging viewers to subscribe and engage with the content.



💡AI tools

AI tools refer to software or platforms that utilize artificial intelligence to perform tasks that would typically require human intelligence. In the context of this video, AI tools are used to create animations. The video script mentions using AI tools to generate images and animations, which is central to the theme of leveraging technology for creative purposes.

💡Leonardo AI

Leonardo AI is a specific AI tool mentioned in the script that is used for creating animations. It is described as a platform where users can fine-tune models, upload images, and train datasets to generate consistent character animations. The video demonstrates how to use Leonardo AI to create a character named Alex, making it a key concept in the tutorial.


Modeling, in the context of this video, refers to the process of creating a 3D representation of a character or object using AI. The script discusses how to use Leonardo AI to model a character by uploading images and training a dataset. This process is essential for generating a consistent character that can be used in animations.

💡Training and datasets

Training and datasets are integral parts of using AI for animations. The script explains the need to upload images to train the AI model, which helps it learn and generate consistent character animations. The process involves creating a dataset and training the model using those images, which is a core aspect of the video's instructional content.


A prompt in the context of AI-generated content is a text input that guides the AI to produce a specific output. The video script describes using prompts to instruct Leonardo AI to generate particular styles of characters or animations. For example, the user writes a prompt to generate 'an animated Pixar character', which directly influences the output of the AI tool.

💡Negative prompt

A negative prompt is a feature in AI tools that allows users to specify what they do not want to see in the generated output. In the script, the user writes a negative prompt to exclude certain elements from the AI-generated character. This is an important aspect of fine-tuning the AI's output to match the user's vision.

💡Image guidance

Image guidance is a feature within Leonardo AI that allows users to include an existing image as a reference for the AI to generate similar outputs. The video demonstrates turning on image guidance and using an example image to guide the creation of an animated character, which helps in achieving a desired look for the character.


Perplexity, in the context of AI, refers to a measure of how well the AI model predicts a given sample. The script suggests using perplexity or chat GPT to ask for a prompt, which implies using AI to help generate the text prompts needed for creating images with Leonardo AI. This is a strategic approach to enhance the creativity and efficiency of the animation process.

💡Stable Diffusion

Stable Diffusion is a type of AI model mentioned in the script as the base model for training the character in Leonardo AI. It is a version 1.5, which suggests it is a specific iteration or version of the AI model that is stable and reliable for generating consistent outputs. This model is crucial for the training process and the final animation results.

💡Canvas editor

The Canvas editor is a tool within Leonardo AI that allows users to manipulate and combine generated images. The script describes using the Canvas editor to bring two characters together in an animation, remove backgrounds, and create a complete body for a character. This tool is essential for post-processing and finalizing the animations.

💡Motion option

The motion option is a feature in Leonardo AI that enables users to add movement to their generated characters. The video script explains using the motion option to bring images to life by adding an element of motion, which is a key step in creating dynamic and engaging animations.


Vidas, as mentioned in the script, is an AI Avatar tool that can be used to generate talking avatars from images. The video suggests using Vidas to add a text overlay to an image, which can then be used in the animation. This tool contributes to the creation of a more interactive and engaging final product.


CapCut is a video editing software mentioned in the script for compiling the final animation. The user imports all the generated videos and images into CapCut to create the final animation product. This software is essential for editing and combining different elements into a cohesive and polished animation.


The animation was created using AI tools, showcasing a step-by-step process.

AI-generated content can be customized with prompts and negative prompts.

Leonardo AI's fine-tune models allow users to build upon previous models.

Uploading images is a crucial step in training the AI model.

Image guidance can be turned on or off to influence the generation process.

Perplexity or chat GPT can be used to generate prompts for creating images.

The importance of including 8 to 15 images in pre-training is emphasized.

Editing and adding images from Google can enhance the training dataset.

The AI can generate animated characters based on specific prompts and characteristics.

Trial and error is a key part of refining the AI-generated animations.

The process of training a model can take between 5 to 30 minutes or more.

The model section allows users to select and use their generated models.

Motion options can be used to bring images to life with animation.

Canvas editor can combine multiple characters and backgrounds for a cohesive animation.

Removing the background from images can be done quickly for a cleaner look.

Vidas is a useful AI Avatar tool for generating text-based animations.

Canva's animey feature can be used for image generation.

Cap Cut is a tool for compiling videos and images into a final product.

The importance of working on frame themes and story for a compelling animation is highlighted.

The final animation product is presented, emphasizing the sunny day theme.