Leonardo AI: Negative Prompts Explained

AI in 5 Minutes
29 Aug 202303:55

TLDRIn this video, the presenter explains how to use Leonardo AI's negative prompt feature to generate images. The process begins by accessing the Leonardo AI website and signing in with a Google, Apple, or Microsoft account. Users then navigate to the AI image generation tool and enter a basic prompt describing the desired image, such as a person with long hair wearing a suit. To refine the image generation, the 'add negative prompt' option is utilized, allowing users to specify elements they wish to avoid, like multiple heads or distorted hands. The video demonstrates how to input these negative prompts and generate images that meet the specified criteria. The presenter also shows how to adjust prompts for more realistic images using the 'photo real' feature, which requires more tokens. The video concludes with a demonstration of the generated images, showcasing the effectiveness of the negative prompt feature in creating high-quality images.

Takeaways

  • 🎨 Use Leonardo AI's negative prompt feature to generate images by visiting the website and signing in with an account.
  • 📝 Start with a basic prompt, such as describing a person's appearance and desired photo style.
  • ➕ Add a negative prompt to specify what you don't want in the image, like 'two heads' or 'distorted hands'.
  • 🚫 Avoid common image imperfections by listing them in the negative prompt, including 'ugly', 'blur', and 'low quality'.
  • 🔍 For more advanced control, you can specify things like 'more than five fingers' to ensure accuracy in the generated images.
  • 🖼️ Generate images by hitting the 'generate' button after setting your prompts.
  • ⌛️ Wait for the AI to process and create the images based on your prompts.
  • 👀 Review the generated images to ensure they meet the criteria set by your prompts, checking for details like the number of fingers.
  • 🐸 Try different prompts with the same negative prompt settings to see how the AI handles various subjects.
  • 🖼️ With successful prompts, the AI can produce images that are free from the specified negative attributes.
  • 📈 For more realistic images, use the 'photo real' feature, which may require more tokens to generate.
  • 📚 The video concludes with a thank you and a goodbye, summarizing the use of negative prompts in image generation with Leonardo AI.

Q & A

  • How can one start using Leonardo AI to generate images?

    -To start using Leonardo AI, go to their website and select the 'start using Leonardo' option. If you have an account, click 'yes I'm white listed' and proceed to the sign-up page.

  • What are the different methods to log in to Leonardo AI?

    -You can log in to Leonardo AI using your Google, Apple, or Microsoft account.

  • Where is the AI image generation tool located on the Leonardo AI website?

    -The AI image generation tool is located on the mid-left of the page.

  • What is a normal prompt in the context of image generation?

    -A normal prompt is a description of the image you want to generate, such as 'person with long brown hair, wearing a suit, full body shot in cinematic photography style'.

  • What is a negative prompt and how is it used?

    -A negative prompt is a feature that allows you to specify elements you do not want in the generated image. You add it by clicking 'add negative prompt' and typing out what you want to avoid, like 'two heads, two faces, distorted hands'.

  • What is the Leonardo diffusion technique used for in this context?

    -Leonardo diffusion is a technique used to generate better images by incorporating negative prompts to avoid unwanted elements in the image.

  • How can you ensure the generated image does not have more than five fingers on a hand?

    -You can specify 'more than five fingers' in the negative prompt to ensure that the generated image will not include this distortion.

  • What happens after you hit the 'generate' button?

    -After hitting 'generate', you wait for the system to create the results based on your prompts and negative prompts.

  • How can you view the generated images?

    -You can view the generated images by opening them individually and examining the details to ensure they match your prompts and do not contain the elements you specified in the negative prompts.

  • What is the photo-real feature and how does it affect image generation?

    -The photo-real feature is an option that can be selected for more realistic images. It may require more tokens to generate the image.

  • What is the final step after generating the images?

    -The final step is to review the generated images to ensure they meet your expectations and do not contain the elements you specified to avoid in the negative prompts.

  • How can one improve the quality of the generated images?

    -To improve the quality of the generated images, one can use more advanced prompts and negative prompts, and also utilize the photo-real feature for a more realistic look.

Outlines

00:00

🎨 Generating Images with Leonardo's Negative Prompt Feature

This paragraph introduces the video's main topic, which is how to generate images using Leonardo AI's negative prompt feature. The process begins with accessing the Leonardo AI website and signing up or logging in with various account options. Once logged in, users navigate to the AI image generation tool and input a standard prompt, such as a description of a person's appearance. The key feature explained is the addition of a negative prompt to refine the image generation process by specifying what should not appear in the image, such as distortions or unwanted features. The video demonstrates this by generating images with specific instructions and avoiding common image errors, showcasing the effectiveness of the negative prompt feature.

Mindmap

Keywords

💡Leonardo AI

Leonardo AI is an advanced image generation tool that utilizes artificial intelligence to create images based on user-provided prompts. It is the central focus of the video, as the speaker guides viewers on how to use its features to generate high-quality images.

💡Negative Prompts

Negative prompts are a feature within Leonardo AI that allows users to specify elements they do not want to appear in the generated images. This is crucial for refining the image generation process, ensuring that the final images meet the user's expectations by avoiding unwanted features.

💡AI Image Generation

AI Image Generation refers to the process of creating images using artificial intelligence. In the context of the video, Leonardo AI employs this technology to generate images based on textual descriptions provided by the user, making it a key component of the tutorial.

💡Cinematic Photography Style

Cinematic photography style is a visual aesthetic often used in movies that aims to capture images with a dramatic and engaging quality. In the video, the user specifies this style when generating an image, indicating a preference for a more artistic and visually impactful result.

💡Full Body Shot

A full body shot is a type of image that captures a subject from head to toe. The video script mentions this as a desired outcome for the image generation, emphasizing the user's intention to create a comprehensive representation of the subject.

💡Distorted Hands

Distorted hands refer to an undesirable outcome in image generation where the hands of a subject appear unnatural or misshapen. The video instructs Leonardo AI to avoid this by including it in the negative prompts, highlighting the importance of accuracy in the depiction of the subject's anatomy.

💡Muted Face

A muted face in the context of image generation implies a facial expression or feature that lacks clarity or detail. The script mentions avoiding a muted face as part of the negative prompts, indicating the user's desire for a clear and well-defined facial representation in the generated images.

💡Low Quality Images

Low quality images are the antithesis of what users aim for when using Leonardo AI. By including 'low quality images' in the negative prompts, the user instructs the AI to prioritize image resolution and detail, ensuring the final output meets a high standard of visual fidelity.

💡Photo Real Feature

The photo real feature is an option within Leonardo AI that enhances the realism of the generated images. It requires more computational resources, as indicated by the mention of 'tokens' in the script, but results in a more lifelike and detailed final image.

💡Tokens

In the context of AI image generation, tokens represent the computational units or resources required to generate an image. The script mentions that using the photo real feature will take more tokens, indicating that it is a more complex and resource-intensive process.

💡White Listed

Being 'white listed' on a platform like Leonardo AI typically means that a user has been granted special access or privileges. In the video, users who are white listed can bypass certain steps in the sign-up process, demonstrating a level of trust or pre-approval by the service.

Highlights

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

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

Log in using your Google, Apple, or Microsoft account.

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

Enter a normal prompt describing the image you want to generate.

Specify the style, such as 'Cinematic photography', to refine the image generation process.

Add a negative prompt to exclude unwanted elements from the generated image.

Use Leonardo's diffusion model to generate images with the specified and excluded features.

Examples of negative prompts include avoiding 'two heads', 'weird teeth', and 'distorted hands'.

The negative prompt feature allows for advanced specifications like 'more than five fingers'.

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

Leonardo AI generates images that closely match the prompts and exclude the negative features.

The generated images are checked for accuracy, such as the number of fingers and facial structure.

The video demonstrates generating an image of a person and a frog using the negative prompt feature.

The 'photo real' feature can be used for more realistic image generation at the cost of more tokens.

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

The video provides a step-by-step guide on using negative prompts for better image generation.

Leonardo AI's negative prompt feature is showcased as a powerful tool for image generation customization.

The video ends with a thank you message and a goodbye.