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 creating AI-generated images. The platform offers a user-friendly web interface, fine-grained control over image generation, and a variety of models, including photorealistic and paper art styles. Users can explore top creations by the community, remix images, and utilize platform and community models for custom outputs. Berman demonstrates the process of generating images, creating icon sets, and fine-tuning models. He also highlights the prompt generation feature and a new AI canvas tool, which allows users to manipulate canvas size and build upon images. The video concludes with a call to action for viewers to ask questions, share creations, and engage with the channel.

Takeaways

  • 🎨 **Leonardo.ai Introduction**: Matt Berman introduces a new AI image generation tool, Leonardo.ai, as an alternative to Midjourney with more control and it's free.
  • 🌐 **Web Interface**: Leonardo.ai has a web interface which is more convenient than using Discord, according to Matt.
  • 🖼️ **Top Creations**: The platform showcases top creations by community members, displaying a variety of styles and high-quality images.
  • 🔍 **Image Information**: Each image on Leonardo.ai provides detailed information including the model used for generation.
  • 🎭 **Fine-Grained Control**: Users have more fine-grained control over image generation, allowing for closer matches to their vision compared to Midjourney.
  • 📈 **Featured Models**: The platform features different models, including a photo-realistic model and a paper art style which are highly praised by Matt.
  • ⏱️ **Image Generation Time**: Image generation with Leonardo.ai takes about the same time as Midjourney, if not slightly faster.
  • 🔄 **Remix Feature**: Users can remix any image directly on the platform, offering more creative flexibility.
  • 🛠️ **Fine-Tune Models**: Leonardo.ai allows for fine-tuning of models, providing more lifelike and stylized options.
  • 🤖 **Prompt Generation**: A unique feature of Leonardo.ai is the ability to generate base prompts for users, aiding in the creative process.
  • 📦 **Icon Sets**: The platform enables the creation of icon sets without the need for additional software like Photoshop.
  • 🏢 **Community Models**: Leonardo.ai supports community-created models, allowing users to train their models with their own images.
  • 📱 **AI Canvas**: A new feature in beta, AI Canvas, lets users manipulate canvas size and build upon images, offering more creative control.

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 in the video is Leonardo.ai.

  • What does the presenter find more convenient about Leonardo.ai compared to Midjourney?

    -The presenter finds the web interface of Leonardo.ai more convenient than using Discord for Midjourney.

  • What feature of Leonardo.ai allows users to have more fine-grained control over the image generation process?

    -Leonardo.ai provides users with much more fine-grained control over every aspect of the image generation, allowing them to get closer to their envisioned image.

  • How does the presenter describe the image quality of the top creations by community members on Leonardo.ai?

    -The presenter describes the image quality as high quality, very cool, and featuring very differing styles.

  • What is the name of the model that the presenter used to create a paper art style image?

    -The presenter used the 'paper art style' model to create the image.

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

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

  • What is the benefit of using the 'stable diffusion 1.5' model in the context of the video?

    -The 'stable diffusion 1.5' model is used to generate images without needing to add a specific style like 'Leonardo style', and it allows for the creation of images without showing faces if desired.

  • What feature of Leonardo.ai allows users to create icon sets without additional post-processing?

    -Leonardo.ai allows users to create icon sets directly through the platform, with the icons ready to go without needing to use software like Photoshop for assembly.

  • What is the presenter's opinion on the AI canvas feature of Leonardo.ai?

    -The presenter finds that the AI canvas feature is still in beta and while it allows for the selection of canvas size and the addition or removal of images, the generated images tend to be of lower quality and more blurred.

  • How does the presenter suggest users can improve the resolution of their generated images in Leonardo.ai?

    -The presenter suggests that using higher resolution images in the training set will result in higher resolution output images.

  • What feature of Leonardo.ai is the presenter excited about and believes is not available in Midjourney?

    -The presenter is excited about the prompt generation feature of Leonardo.ai, which automatically generates ideas for the user's base prompt, a feature not available in Midjourney.

  • What does the presenter recommend for viewers who have questions or have created something using Leonardo.ai?

    -The presenter recommends that viewers with questions drop them in the comments and those who have created something to share it in the comments as well.

Outlines

00:00

🎨 Exploring Leonardo.ai for AI-Generated Art

The first paragraph introduces the viewer to Leonardo.ai, a platform for creating AI-generated images in various styles. The host, Matt Berman, discusses the convenience of its web interface compared to Discord and showcases high-quality images created by the community. He highlights the fine-grained control over image generation, which allows for more specific outcomes than with Mid-Journey. Featured models like 'Deliberate 1.1' for photorealism and 'paper art style' are presented. The paragraph also covers the process of using the platform, including selecting models, generating images, and remixing existing creations. It contrasts Leonardo's detailed control with Mid-Journey's more general approach.

05:00

🤖 Training Custom Models and Prompt Generation

The second paragraph delves into training custom models on Leonardo.ai, which can be done with a user's own images and takes about 30 minutes. It emphasizes the ability to create and use custom models immediately after training. The host shares examples of community-created models, such as sticker styles and realistic cat portraits, and explains the process of remixing images and using them as seeds or models. The paragraph also touches on the prompt generation feature, which provides creative ideas for base prompts, and introduces AI canvas, a feature that allows users to manipulate canvas size and build upon images, though it is noted to be in beta and not as high-quality as other features. The host shares some of his favorite creations made using 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 algorithms can interpret and replicate various styles of art, creating unique images based on textual prompts. In the video, AI-generated images are the main focus, showcasing how Leonardo.ai can produce images in different styles with more control and customization options than Midjourney.

💡Leonardo.ai

Leonardo.ai is an AI image generation platform that the video is centered around. It is presented as an alternative to Midjourney, offering a web interface for creating images in various styles. The platform is highlighted for its user-friendly interface, fine-grained control over image generation, and the ability to create icon sets and remix existing creations.

💡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 context of the video, Leonardo.ai's web interface is praised for being more convenient than using Discord for similar tasks, allowing users to easily navigate and generate images through their browser.

💡Models

In the context of AI image generation, models refer to the underlying algorithms or neural networks that interpret prompts and produce images. The video discusses various models available on Leonardo.ai, such as 'Deliberate 1.1' for photorealism and 'Paper Art Style' for creating images in a specific artistic style.

💡Remix

To remix an image in the context of the video means to use an existing image as a starting point for creating a new one. Leonardo.ai allows users to remix images directly from the platform, providing more control and the ability to modify and generate new images based on community creations or personal prompts.

💡Fine-grain control

Fine-grain control refers to the ability to make very specific adjustments or customizations. In the video, it is mentioned that Leonardo.ai offers more fine-grain control over the image generation process compared to Midjourney, allowing users to get closer to their envisioned outcome.

💡Prompts

Prompts are the textual descriptions or instructions given to an AI image generation system to guide the creation of an image. The video emphasizes the importance of prompts in determining the style and content of the generated images, and how Leonardo.ai allows for more specific prompts to achieve desired results.

💡Icon sets

Icon sets are a collection of images that are visually consistent and typically used for graphical user interfaces or design elements. The video demonstrates how Leonardo.ai can generate an icon set from a single prompt, eliminating the need for manual assembly using external software like Photoshop.

💡Community models

Community models are AI models that are created and trained by the user community of a platform. In the video, it is mentioned that users can upload their own images to train a model on Leonardo.ai, which can then be used to generate new images in the same style, fostering a collaborative and creative environment.

💡Prompt generation

Prompt generation is a feature that assists users in creating textual prompts for AI image generation by suggesting ideas or phrases. The video showcases this feature of Leonardo.ai, which can generate base prompt ideas for users to use as a starting point for their image creation process.

💡AI Canvas

AI Canvas is a feature mentioned in the video that allows users to manipulate the canvas size and composition of generated images, adding or removing elements to create a final piece. It is noted as being in beta and offering a different approach to image generation compared to the main features of Leonardo.ai.

Highlights

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

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

High-quality images in various styles can be found, showcasing the community's top creations.

Users can click on images to view detailed information, including the model used.

Leonardo.ai offers fine-grain control over image generation, allowing for more specific outcomes.

Featured models include photorealistic and paper art styles, among others.

The platform allows users to remix any image directly from the interface.

Image generation with Leonardo is comparable in speed to Midjourney.

Users can select the number of images, dimensions, and other parameters for custom image generation.

Negative prompts can be used to exclude certain elements, like faces, from the generated images.

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

The platform includes fine-tune models that users can generate new images with.

Community models are available, allowing users to train their models with their own images.

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

AI Canvas is a new feature that lets users build upon images by selecting canvas sizes and adding or removing elements.

Leonardo.ai provides settings to tailor the feed to user interests and toggle NSFW content.

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

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