Leonardo AI Masterclass 2024: Basic to Advance Prompting Tutorial

The video begins by introducing Leonardo AI, a sophisticated AI art generator and design platform that is revolutionizing the art world. The speaker welcomes viewers back to the channel, SkillCV, which focuses on new cutting-edge technologies. The video aims to explore the technology behind Leonardo AI, its capabilities, advancements, and how it can be utilized by various professionals, including artists, designers, marketers, and entrepreneurs. The speaker emphasizes the tool's ability to generate realistic 3D images using expertly designed prompts and its potential to unlock the creative potential of AI art creation.

The speaker discusses the Real-Time Canvas feature of Leonardo AI, which allows users to transform their drawings into stunning artworks almost instantaneously. This feature offers an immersive and intuitive creative process, similar to painting on a digital canvas. Users can start by selecting a brush tool, choosing a color, and drawing or uploading an existing image. The AI then updates the output in real-time as the user continues to draw or add prompts. Advanced settings allow users to adjust guidance, creativity strength, and enable high-quality options for more refined results. The speaker provides a practical example of creating an image using this feature, demonstrating how it can be used to generate a green alien with a specific background.

The Canvas Editor feature of Leonardo AI is highlighted next, which enables users to edit, refine, add details, and modify styles of their images. The speaker showcases the feature by selecting an image from the Leonardo AI gallery and using the canvas editor to enlarge and add details to the image. The interface offers various options such as deleting canvas history, selecting, drawing masks, and more. The speaker demonstrates how to use the editor to create a photo-realistic masterpiece with a focus on space, harmony, love, and happiness, emphasizing the ability to add details and adjust the image's aspect ratio using AI-generated prompts.

The speaker delves into the process of image generation with Leonardo AI, explaining the importance of crafting the perfect prompt. The video outlines a formula for effective prompts, which should include a clear description of the subject, the type of image, image style, camera viewpoint, and additional rendering details. The speaker provides examples of prompts and demonstrates how they can be used to generate stunning and realistic images, including a surreal landscape of a moss-covered lighthouse. The video also discusses additional parameters and options for image generation, such as photo-realistic style, raw mode, and public images.

The video introduces the concept of negative prompts, which allow users to exclude specific elements they dislike from their images. This feature provides greater control over the final output, ensuring that the results match the user's preferences. The speaker explains how to use negative prompts to avoid certain colors, features, or styles in the images. A practical example is given, where the speaker creates an image of an elder under a Garn tree, excluding elements like modern clothing, overly clean appearance, stiffness, broad smile, sharpness, distracting background, and cold colors. The output showcases how negative prompts can refine the AI-generated images to align with the user's vision.

The speaker discusses various use cases for Leonardo AI, focusing on creating realistic images and portraits. The video explains how to adjust settings for photo-realistic images, emphasizing the use of the photo-real option and cinematic mode. Examples are provided for creating a weathered wood carver and a ballerina in mid-air, highlighting the details and realism achieved through the AI's image generation capabilities. The speaker also covers the creation of human portraits, using detailed prompts to generate images that capture the essence of the subject, such as a young woman with wind-swept hair and a child bathed in golden sunlight.

The video continues by exploring the creation of anime characters, cartoons, and 3D renders with Leonardo AI. The speaker explains how to disable the photo-real option and select the appropriate style for each category. Detailed prompts are used to generate an anime celestial being and a cartoon character with mismatched socks and defying gravity hair. The video also demonstrates the creation of 3D renders, using a prompt to generate an image of a spaceship navigating a maze of translucent crystal skyscrapers. The speaker emphasizes the versatility of Leonardo AI in producing various styles of images, catering to different creative needs.

The final section of the video focuses on creating landscapes with Leonardo AI. The speaker provides a prompt for generating an image of sky bridges weaving between crumbling towers, emphasizing overgrown architecture and a sense of melancholic wonder. The use of negative prompts is also discussed, with the speaker detailing how to exclude unwanted elements such as solid colors, sharp outlines, and flat lighting to achieve the desired aesthetic. The resulting landscapes are showcased, demonstrating the platform's ability to create realistic and hypothetical worlds, bringing the viewer's imagination to life.