New Midjourney Alternative but UNLIMITED and FREE! (Tutorial)

Matthew Berman
15 Feb 202308:19

TLDRIn this tutorial, Matt Berman introduces Leonardo.ai, a free and unlimited alternative to Midjourney for creating AI-generated images. He highlights the platform's web interface, diverse styles, and fine-grained control over image generation. The video showcases how to use different models, including photo-realistic and paper art styles, and how to remix images to create unique visuals. Berman also demonstrates the platform's features like generating icon sets, fine-tuning models, and using community models. Additionally, he covers prompt generation and the AI canvas feature, which allows users to build upon existing images. The video concludes by emphasizing Leonardo.ai as a superior and cost-free choice for AI image creation.

Takeaways

  • 🎨 **Leonardo.ai** is a platform for creating AI-generated images in various styles with more control than Midjourney and it's free.
  • 🌐 It has a web interface which is considered more convenient than using Discord for similar tasks.
  • 🖼️ High-quality images in different styles can be viewed and remixed directly from the community creations.
  • 🔍 Users have fine-grained control over the image generation process, allowing for more specific outcomes.
  • 📈 Featured models are available, including photorealistic and paper art styles, offering diverse creative options.
  • 🚀 The process of generating an image with a selected model is straightforward and relatively fast.
  • 📦 Users can create icon sets and other collections without needing additional software like Photoshop.
  • 🧩 There's an option to fine-tune platform models or use community models, which can be trained with personal images.
  • 📈 The platform allows for the training of personal models with a dataset of images, influencing the output quality.
  • 💡 Prompt generation is a unique feature not available in Midjourney, assisting users in creating base prompts for images.
  • 🖼️ AI Canvas is a new feature for generating images with customizable canvas sizes, though it's still in beta.
  • ⚙️ Settings allow users to customize their experience based on interests and toggle NSFW content.

Q & A

  • What is the name of the AI image generation platform discussed in the video?

    -The name of the AI image generation platform discussed is Leonardo.ai.

  • What is the main advantage of using Leonardo.ai over Midjourney?

    -Leonardo.ai offers more fine-grained control over the image generation process, allowing users to get closer to their envisioned image, and it is unlimited and free to use.

  • What are the different styles of images that Leonardo.ai can generate?

    -Leonardo.ai can generate images in various styles, including photorealistic, paper art style, and isometric sci-fi building styles.

  • How does the web interface of Leonardo.ai compare to using Discord for image generation?

    -The web interface of Leonardo.ai is considered more convenient than using Discord for image generation.

  • What feature allows users to create icon sets without additional editing software?

    -Leonardo.ai has a feature that allows users to create icon sets directly within the platform, eliminating the need for additional editing software like Photoshop.

  • How long does it take to train a custom model in Leonardo.ai?

    -It takes about 30 minutes to train a custom model in Leonardo.ai.

  • What is the name of the feature that allows users to generate ideas for their base prompt?

    -The feature that generates ideas for the base prompt is called Prompt Generation.

  • What is the name of the feature that allows users to select the canvas size and add or remove images?

    -The feature that allows users to manipulate the canvas size and images is called AI Canvas.

  • How does the AI Canvas feature differ from the main image generation feature in terms of image quality?

    -The AI Canvas feature tends to generate images that are more odd and blurred between different features, whereas the main image generation feature produces higher quality images.

  • What is the process for using a community-created model in Leonardo.ai?

    -To use a community-created model, one can find a model created by a community member, follow the Creator, remix the image, copy the prompt, use the image as a seed, or just use the model directly.

  • What is the significance of the resolution of images used to train a custom model in Leonardo.ai?

    -The resolution of the images used to train a custom model affects the output resolution. If low-resolution images are used, the generated images will also be low-resolution.

  • How can viewers provide feedback or share their creations with the presenter?

    -Viewers can drop additional questions in the comments section of the video and share their creations made with Leonardo.ai in the comments as well.

Outlines

00:00

🎨 Introduction to AI Image Generation with Leonardo.ai

Matt Berman introduces viewers to Leonardo.ai, a platform for creating AI-generated images in various styles with greater control over the creative process compared to mid-journey. He highlights the convenience of its web interface, showcases examples of community creations, and explains how users can remix images and have fine-grained control over image generation. Matt also discusses the different models available, such as photorealistic and paper art styles, and demonstrates how to use the platform by creating an image of a Japanese village in paper art style. He compares the features and customization options of Leonardo.ai with those of mid-journey, noting the ability to create icon sets and the platform's models, including community models that users can train with their own images.

05:00

🤖 Exploring Advanced Features of Leonardo.ai

The video continues with Matt demonstrating the advanced features of Leonardo.ai, including the training of personal models using one's own images, the creation of high-resolution sticker-style images, and the remixing of community images. He also discusses the prompt generation feature, which assists users in coming up with ideas for their base prompts. Matt introduces AI canvas, a new feature that allows users to manipulate canvas size and build upon images, though he notes that the quality of images generated through this feature is not as high as the others. He concludes with a few examples of his favorite creations made with Leonardo.ai and encourages viewers to ask questions, share their creations, and subscribe for more content.

Mindmap

Keywords

💡AI-generated images

AI-generated images refer to visual content created using artificial intelligence algorithms. These images are not produced by human artists but are instead synthesized by AI systems based on input data or prompts. In the video, AI-generated images are the central theme, showcasing how Leonardo.ai can create images in various styles, from photorealistic to paper art.

💡Leonardo.ai

Leonardo.ai is an AI platform mentioned in the video that allows users to generate images using different models and styles. It is described as having a user-friendly web interface and offering more control over the image generation process compared to other services like Midjourney. The platform is highlighted for its convenience, variety of styles, and the ability to fine-tune the generated images.

💡Web interface

A web interface is a way for users to interact with a software application or service over the internet. In the context of the video, Leonardo.ai's web interface is preferred over using Discord for its convenience and ease of use. It allows users to view examples, select models, and generate images directly through their web browser.

💡Models

In the context of AI image generation, models refer to the specific algorithms or neural networks that are used to create the images. The video discusses various models available on Leonardo.ai, such as 'Deliberate 1.1' for photorealistic images and 'Paper Art Style' for a unique artistic look. These models determine the style and quality of the generated images.

💡Remix

Remixing, in the context of the video, means to take an existing AI-generated image and modify it or use it as a base to create a new image. This feature allows users to build upon community creations or their own previous works, changing elements like style or theme, as demonstrated when the presenter remixed an RPG icon set into an FPS game set.

💡Prompt

A prompt is a text input or description given to an AI system to guide the generation of an image. It defines the concept or scene the user wants the AI to create. In the video, the presenter uses prompts to generate specific images, such as a 'Japanese Village' in paper art style or an 'icon set' for a game, showcasing how precise prompts can lead to desired outcomes.

💡Negative prompt

A negative prompt is a directive given to an AI image generation system to exclude certain elements from the generated image. In the script, the presenter uses a negative prompt to specify that they do not want any faces shown in the generated images, which helps refine the output to match the user's preferences.

💡Icon set

An icon set refers to a collection of images or symbols that are used to represent various concepts or functions, often in a consistent style. The video demonstrates how Leonardo.ai can generate an icon set for a game, all at once, which saves the user from having to create and compile individual icons manually.

💡Fine-tune models

Fine-tune models are pre-existing AI models that have been adjusted or customized to better suit specific needs or styles. In the video, the presenter discusses 'Leonardo creative' and other platform models that have been fine-tuned for different visual styles, such as lifelike anime or isometric sci-fi buildings, allowing for more precise control over the image generation.

💡Community models

Community models are AI models that are created and trained by the users of the platform, as opposed to the default or platform models. The video mentions that users can upload their own images to train a model, which can then be used to generate new images in a similar style. This feature enables a collaborative and customizable approach to AI image generation.

💡Prompt generation

Prompt generation is a feature that assists users in coming up with ideas for their text prompts. The video describes how Leonardo.ai can generate suggestions for base prompts, making it easier for users to start the image creation process. This tool aids creativity by providing a starting point for the prompts that guide the AI in generating images.

💡AI canvas

AI canvas, as mentioned in the video, is a feature that allows users to manipulate the canvas size and composition of the generated images. It is still in beta and enables users to add or remove elements from an image and build upon it, offering a more interactive approach to image creation beyond the initial generation.

Highlights

Leonardo.ai is an AI image generation platform offering more control and style options than Midjourney, and it's completely free.

The platform features a user-friendly web interface, which is more convenient than using Discord.

High-quality images in various styles can be generated, including hyper-realistic and paper art styles.

Users can view and remix top creations by community members, offering a wide range of inspiration.

Leonardo.ai provides fine-grained control over image generation, allowing for more specific outcomes compared to Midjourney.

Featured models on the platform include photorealistic and paper art styles, with the ability to generate images in these styles.

The platform allows users to generate images with specific prompts, such as 'Japanese Village' in a paper art style.

Leonardo.ai offers options for selecting the number of images, image dimensions, guidance scale, step count, and tiling.

Users can create icon sets without the need for additional software like Photoshop, thanks to the platform's integrated features.

The platform includes fine-tune models, which are pre-built models that users can select for specific styles.

Community models are also available, allowing users to train their models with their own images for personalized image generation.

Leonardo.ai enables users to follow creators, remix images, copy prompts, and use images or models directly from the community creations.

The platform provides a prompt generation feature to help users come up with ideas for their base prompts.

AI Canvas is a new feature that allows users to generate, modify, and build upon images in a unique way.

The AI Canvas feature is still in beta and offers the ability to erase and add to images, providing a new level of creative control.

Users can customize their feed based on their interests and toggle NSFW content.

Matt Berman, the presenter, showcases his favorite creations from Leonardo Ai, demonstrating the platform's capabilities.

Leonardo.ai is presented as a superior and free alternative to Midjourney for AI image generation.