Leonardo AI: Negative Prompts Explained

AI in 5 Minutes
29 Aug 202303:55

TLDRThis video tutorial guides viewers on how to use Leonardo AI's negative prompt feature to generate images. The process begins with accessing the Leonardo AI website and signing in with a Google, Apple, or Microsoft account. After logging in, users navigate to the AI image generation tool and input a standard prompt describing the desired image, such as a person with long hair wearing a suit in a full body shot. To refine the image generation, the video demonstrates adding a negative prompt to exclude unwanted elements like multiple heads, distorted hands, or low-quality images. The video also mentions the option to generate more realistic images by using the photo-real feature, which requires more tokens. The demonstration shows how the system successfully creates images that adhere to the given prompts and negative prompts, resulting in high-quality images without the specified undesirable features.

Takeaways

  • 😀 Visit the Leonardo AI website and use the 'start using Leonardo' option to access the image generation tool.
  • 😀 If you are already whitelisted, select 'yes I'm white listed' to proceed to the sign-in page.
  • 😀 Log in using your Google, Apple, or Microsoft account to authenticate your access.
  • 😀 Navigate to the AI image generation tool located on the mid-left of the page and start your image generation process.
  • 😀 Create a basic prompt for the image, specifying details like appearance and style (e.g., 'full body shot in Cinematic photography style').
  • 😀 Enhance image generation by adding negative prompts to exclude unwanted elements (e.g., 'no two heads, two faces, distorted hands').
  • 😀 Utilize Leonardo diffusion for more controlled and accurate image rendering based on both positive and negative prompts.
  • 😀 Specify detailed exclusions in the negative prompt like 'more than five fingers' to avoid generating images with these features.
  • 😀 Review the generated images to ensure they meet the specifications of your prompt, focusing on details like the number of fingers and facial symmetry.
  • 😀 For more realistic images, use the 'photo real feature' which may require more tokens but provides higher fidelity results.

Q & A

  • How can one start using Leonardo AI for image generation?

    -To start using Leonardo AI, go to their website, click on 'start using Leonardo', and if you have an account, click 'yes I'm white listed'. This will take you to the sign-up page where you can log in using a Google, Apple, or Microsoft account.

  • What is the purpose of the negative prompt feature in Leonardo AI?

    -The negative prompt feature allows users to specify what they do not want to appear in the generated images, which helps in creating more accurate and desired outcomes.

  • How does one add a negative prompt to their image generation request?

    -After writing the normal prompt, you can add a negative prompt by clicking on the 'add negative prompt' option and then typing out the elements you wish to exclude from the image.

  • What kind of examples are given for negative prompts in the video?

    -Examples of negative prompts include 'two heads', 'two faces', 'two noses', 'weird teeth', 'non-tometrical face', 'distorted hands', 'muted face', 'ugly', 'blur', and 'low quality images'.

  • Can you specify a more advanced negative prompt in the video?

    -Yes, the video mentions an advanced negative prompt example where the user specifies 'more than five fingers' to ensure the generated image does not have any distortions in the number of fingers.

  • What style of photography is suggested in the video for the image prompt?

    -The video suggests using a 'Cinematic photography' style for the image prompt.

  • How does Leonardo AI ensure the quality of the generated images?

    -Leonardo AI ensures quality by allowing users to add both positive prompts (what they want in the image) and negative prompts (what they don't want), which guides the AI to generate images that meet the user's specifications.

  • What happens if you want a more realistic image?

    -If you want a more realistic image, you can use the 'photo real' feature in Leonardo AI, which will take more tokens to generate the image but will produce a higher quality result.

  • What is the final step after adding the prompts and negative prompts?

    -The final step is to hit the 'generate' button, after which you wait for Leonardo AI to create your results.

  • How does the video demonstrate the effectiveness of the negative prompt feature?

    -The video demonstrates the effectiveness by showing before and after examples where the negative prompts were used to correct issues like the number of fingers and facial distortions, resulting in a more accurate and higher quality image.

  • What is the main takeaway from the video regarding image generation with Leonardo AI?

    -The main takeaway is that by using both positive and negative prompts, users can guide the AI to generate images that closely match their desired outcome, with a high level of detail and accuracy.

  • Can the negative prompt feature be used to avoid common image generation pitfalls?

    -Yes, the negative prompt feature is specifically designed to help users avoid common pitfalls in image generation, such as unwanted features or distortions, by explicitly stating what should not be included in the image.

Outlines

00:00

🎨 Generating Images with Leonardo's Negative Prompt

This paragraph introduces the process of using Leonardo AI's negative prompt feature to generate images. It guides the user to visit the Leonardo AI website, sign up or log in with an existing account, and navigate to the AI image generation tool. The user is instructed to write a normal prompt describing the desired image, such as a person with specific hair color and a suit, and then enhance the prompt with a negative prompt to exclude unwanted elements like multiple heads or distorted features. The user is also shown how to generate the image and review the results, ensuring the image meets the criteria set by the prompts and avoiding any unwanted distortions.

Mindmap

Keywords

💡Leonardo AI

Leonardo AI is an advanced image generation tool that utilizes artificial intelligence to create images based on textual prompts provided by the user. In the video, it is the main platform through which the user interacts to generate images. It is used to demonstrate the process of creating images with specific features and avoiding undesired elements by using both positive and negative prompts.

💡Negative Prompts

Negative prompts are a feature within Leonardo AI that allows users to specify what they do not want to appear in the generated images. This is crucial for refining the image generation process and ensuring that the final output aligns with the user's vision. In the video, the user adds negative prompts such as 'two heads,' 'weird teeth,' and 'distorted hands' to prevent these elements from appearing in the generated images.

💡Image Generation

Image generation refers to the process of creating images from textual descriptions using AI algorithms. It's the central theme of the video, as the user guides viewers through the steps of using Leonardo AI to generate images. The process involves entering prompts and negative prompts to direct the AI in creating the desired visuals.

💡AI Image Generation Tool

An AI image generation tool is a software application that uses artificial intelligence to generate images based on user input. In the context of the video, the Leonardo AI is the specific tool being used for generating images. It is depicted as a powerful and user-friendly platform that enables the creation of complex and detailed images.

💡Cinematic Photography Style

Cinematic photography style is a term used to describe the visual aesthetic often associated with movies, characterized by a certain quality of lighting, composition, and mood. In the video, the user specifies this style in their prompt to guide the AI towards generating images with a dramatic and visually engaging look.

💡Full Body Shot

A full body shot is a type of photograph or image that captures a person from head to toe. It is mentioned in the video as part of the user's prompt, indicating that they want the generated image to include the entire body of the person, rather than just a close-up or cropped portion.

💡White Listed

Being 'white listed' typically means being granted special access or privileges. In the context of the video, selecting the 'yes I'm white listed' option suggests that the user has been pre-approved or given certain rights within the Leonardo AI platform, possibly to access advanced features or to bypass certain limitations.

💡Google, Apple, or Microsoft Account

These are popular technology companies that offer various services, including user account systems. In the video, they are mentioned as options for users to log in to the Leonardo AI website, indicating that the platform supports single sign-on functionality for convenience and ease of access.

💡Tokens

In the context of AI image generation, tokens often refer to the computational resources or units of processing required to generate an image. The video mentions that generating more realistic images with the 'photo real feature' requires more tokens, suggesting that higher quality or more complex image generation is more resource-intensive.

💡null

💡Photo Real Feature

The 'photo real feature' is likely a setting or option within the Leonardo AI tool that enhances the realism of the generated images. It is mentioned as a way to produce images that are more lifelike, at the cost of requiring more tokens for processing.

💡Fingers

In the video, the user specifically mentions not wanting 'more than five fingers' in the generated image as part of their negative prompt. This detail highlights the level of control and specificity that users have over the elements that appear in their generated images.

💡Facial Structure

Facial structure refers to the arrangement and proportions of the features of a person's face. The video emphasizes the importance of a well-defined and non-distorted facial structure in the generated images, showcasing the AI's ability to understand and replicate human facial anatomy accurately.

Highlights

The video teaches how to generate images using Leonardo AI's negative prompt feature.

Access Leonardo AI website and start using the platform if you have an account or sign up if you don't.

Log in with Google, Apple, or Microsoft accounts to use Leonardo AI.

Navigate to the AI image generation tool on the mid left of the page to begin.

Create a basic prompt with a description of the desired image, such as a person with specific hair color and attire.

Enhance the prompt by adding a cinematic photography style for better image generation.

Add a negative prompt to specify what should not be included in the generated image.

Use Leonardo diffusion to refine the image generation process with negative prompts.

Examples of negative prompts include avoiding two heads, distorted hands, and low-quality images.

For more advanced image requirements, specify details like not having more than five fingers.

After setting the prompts, hit generate to create the image.

Wait for the AI to process and create the results based on the prompts.

Leonardo AI generates close to perfect images adhering to the provided prompts.

Review the generated images for accuracy, such as correct number of fingers and facial structure.

The video demonstrates generating an image of a frog with the same process, maintaining the negative prompt considerations.

For more realistic images, use the photo-real feature, which may require more tokens to generate.

The video concludes with a summary of how to use Leonardo AI for image generation with negative prompts.

Thank the viewers for watching and end the tutorial.