New Midjourney Alternative but UNLIMITED and FREE! (Tutorial)

Matthew Berman
15 Feb 202308:19

TLDRMatt Berman introduces Leonardo.ai, a free and unlimited alternative to Midjourney for generating AI images. He highlights the platform's user-friendly web interface, diverse styles, and fine-grained control over image generation. Berman showcases the ability to remix images, the selection of models including photo-realistic and paper art styles, and the customization options. He also demonstrates creating an icon set and generating images with community models. Berman discusses the prompt generation feature and the AI canvas, which allows for image manipulation. He concludes by encouraging viewers to explore Leonardo.ai for a superior and cost-free image generation experience.

Takeaways

  • 🎨 Leonardo.ai is an alternative to Midjourney that allows users to create AI-generated images in various styles with more control over the final output.
  • 🌐 It features a web interface, which is considered more convenient than using Discord for similar tasks.
  • 🖼️ The platform showcases high-quality images created by the community, offering a wide range of styles and inspirations.
  • 🔍 Users can click on any image to view detailed information, including the model used for generation.
  • 🎭 Leonardo.ai provides fine-grained control over image generation, allowing for more precise results compared to Midjourney.
  • 🏞️ The platform offers a variety of models, including photorealistic and paper art styles, for users to choose from.
  • 🔄 Users can remix any image directly on the platform, utilizing the same model or a different one for new creations.
  • 📈 The interface allows for customization of image dimensions, guidance scale, step count, and tiling for a consistent look.
  • 🚀 Leonardo.ai also enables the creation of icon sets without the need for additional software like Photoshop.
  • 🤖 The platform includes 'fine-tune models' and 'community models', where users can train their models using their own images.
  • 📝 Prompt generation is another feature not available in Midjourney, where Leonardo.ai can suggest ideas for base prompts.
  • 🖼️ AI Canvas is a new feature in beta that allows users to manipulate canvas size and build upon images, offering more creative flexibility.

Q & A

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

    -The platform discussed in the video is called leonardo.ai.

  • What is the main advantage of leonardo.ai over Midjourney according to the video?

    -Leonardo.ai offers more fine-grained control over image generation, allowing users to get closer to their envisioned image compared to Midjourney.

  • How does the web interface of leonardo.ai differ from using Discord?

    -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 post-processing?

    -Leonardo.ai allows users to create icon sets directly within the platform, eliminating the need for post-processing with software like Photoshop.

  • What is a unique feature of leonardo.ai that is not available in Midjourney?

    -Leonardo.ai offers a prompt generation feature, which is not available in Midjourney.

  • 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 build off of certain images and create a canvas size?

    -The feature is called AI canvas.

  • What type of control does leonardo.ai provide over the image generation process?

    -Leonardo.ai provides fine-grained control over every aspect of the image generation, allowing for more specific results.

  • What is the name of the model that produces a paper art style?

    -The model that produces a paper art style is not explicitly named, but it is one of the featured models in leonardo.ai.

  • How does the community involvement in leonardo.ai enhance the platform?

    -Community involvement in leonardo.ai enhances the platform by allowing users to create and train their own models, share prompts, and remix images, thus expanding the diversity of styles and options available.

  • What is the process for using a community model in leonardo.ai?

    -To use a community model, a user can select the model, click 'generate with this model', and then input their specific prompt to create an image.

  • How does the AI canvas feature in leonardo.ai differ from the standard image generation?

    -The AI canvas feature allows users to select the canvas size, add or remove certain images, and build off of them, providing more flexibility in creating a composition. However, it is noted to be in beta and may not generate as high quality images as the standard feature.

Outlines

00:00

🎨 Exploring Leonardo.ai for AI-Generated Images

Matt Berman introduces Leonardo.ai, a platform for creating AI-generated images in various styles with high control. The platform features a user-friendly web interface, showcasing community creations and offering detailed information about each image, including the model used. Users can remix images and have fine-grained control over image generation, which is more specific than other tools like mid-journey. The video demonstrates how to use different models, such as photorealistic and paper art styles, to create images based on user prompts. It also covers the process of generating images with specific settings like the number of images, dimensions, guidance scale, and step count. Additionally, the video shows how to use negative prompts to exclude certain elements, like faces, from the generated images.

05:00

🤖 Customizing and Training Models on Leonardo.ai

The video continues with a discussion on customizing and training models on Leonardo.ai. Users can train their models using their own images, which takes about 30 minutes, and then use these models for image generation. The host shares an example of a sticker-style model trained with images of Pokemon and demonstrates how to generate new images using this custom model. The video also introduces prompt generation, a feature that suggests ideas for base prompts, aiding users in the creative process. A new feature called AI canvas is explored, which allows users to generate images and then edit the canvas size, add or remove elements, and build upon the generated images. The AI canvas feature is in beta and offers a different approach to image creation. The host shares some of their 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 that is created using artificial intelligence algorithms. These algorithms can interpret and learn from existing styles and patterns to produce new, unique images. In the context of the video, the host discusses using a platform called leonardo.ai to create AI-generated images in various styles, which is the main theme of the video.

💡Midjourney

Midjourney is a term used in the video to refer to a specific AI image generation platform. It is used as a point of comparison to leonardo.ai, highlighting the differences in control, style, and user experience. The host suggests that leonardo.ai offers more control and a wider range of styles for creating images.

💡Web interface

A web interface is a way for users to interact with a software application via the internet, using a web browser. In the video, the host mentions that leonardo.ai has a web interface, which is more convenient than using Discord, another platform mentioned for its chat and community features. This interface allows users to easily access and utilize the AI image generation tools.

💡Community members

Community members are users who actively participate in a shared online space or platform. In the context of the video, community members contribute by creating and sharing their AI-generated images on leonardo.ai, which serve as examples and inspiration for others. Their creations are featured in the platform's gallery.

💡Model

In the context of AI image generation, a model refers to a specific set of algorithms or parameters that dictate the style and characteristics of the generated images. The video mentions different models available on leonardo.ai, such as 'Deliberate 1.1' for photorealistic images and 'paper art style' for a more artistic approach.

💡Fine grain control

Fine grain control refers to the ability to make very specific adjustments or customizations. In the video, the host emphasizes that leonardo.ai allows for fine grain control over the image generation process, enabling users to get closer to their envisioned outcome compared to other platforms.

💡Remix

To remix, in the context of digital content, means to take an existing creation and modify it to create something new. The host demonstrates how users can remix images on leonardo.ai, changing aspects such as the style or theme, to generate new images based on community creations.

💡Stable Diffusion

Stable Diffusion is a specific model or algorithm used for AI image generation. It is mentioned in the video as one of the options users can select when generating images on leonardo.ai. It is associated with producing high-quality images.

💡Negative prompt

A negative prompt is a direction given to an AI system to exclude certain elements or characteristics from the generated content. In the video, the host uses a negative prompt to specify that faces should not be included in the generated images, demonstrating the level of control users have over the output.

💡Icon set

An icon set is a collection of related icons that are used for visual representation in digital interfaces. The video discusses how leonardo.ai can be used to generate icon sets, which are sets of visually consistent images that can be used in various applications without the need for additional editing.

💡Prompt generation

Prompt generation is the process of creating textual instructions or suggestions that guide the AI in generating specific types of images. The video introduces a feature of leonardo.ai that generates ideas for base prompts, assisting users in coming up with creative starting points for their image generation process.

💡AI Canvas

AI Canvas is a feature mentioned in the video that allows users to generate and manipulate images in a more interactive way. It is described as being in beta and offering the ability to select canvas sizes, add or remove elements from images, and build upon existing creations for a more customized result.

Highlights

Leonardo.ai is an alternative to Midjourney for creating AI-generated images with more control and it's free.

The platform offers a web interface, which is more convenient than using Discord.

Leonardo.ai features a gallery of top creations by community members in various styles.

Users can click into images to see details, including the model used for generation.

The platform allows for fine-grain control over every aspect of image generation.

Featured models include photorealistic and paper art styles.

Remixing images is possible directly from the gallery.

Leonardo.ai provides specific prompts and models for generating images, like a Japanese Village in paper art style.

The interface includes options for selecting the number of images, image dimensions, guidance scale, and step count.

Users can upload an image as a base seed for image generation.

Leonardo.ai allows for the creation of icon sets without the need for additional software.

The platform has fine-tune models and community models, which are created and trained by users.

Training a personal model with your own images takes about 30 minutes.

The Creator feature allows users to follow, remix, and use images or models from other creators.

Prompt generation is a unique feature that helps users come up with ideas for their base prompt.

AI Canvas is a new feature that allows users to generate the same image with different canvas sizes and features.

Settings allow users to specify interests and toggle NSFW content.

Matt Berman, the presenter, shares examples of his favorite creations made with Leonardo.ai.

Leonardo.ai is presented as a superior and free alternative to Midjourney.