Create Stunning Ai Art For Free With InvokeAI: Midjourney Alternative

All Your Tech AI
28 Mar 202308:08

TLDRThe video showcases the capabilities of AI-generated art with InvokeAI, an alternative to Midjourney. After tweeting an AI-generated image of Elon Musk and Mary Berra, the creator received over 13 million views and a response from Musk. The video demonstrates setting up a Discord bot using free tools like InvokeAI and stable diffusion to generate high-quality images from text prompts. The creator guides viewers through the process, highlighting features like upscaling and model selection, and encourages joining the Discord server to explore AI art creation.

Takeaways

  • 😀 The creator posted an AI-generated image of Elon Musk and GM CEO Mary Berra on Twitter, which received over 13.5 million views and a response from Elon Musk.
  • 📰 The image and its AI origin were discussed on the homepage of MSN and Snopes, highlighting the capabilities of AI in creating realistic images.
  • 🤖 The creator set up a Discord server with a stable diffusion bot using invoke AI, allowing users to generate images with custom prompts.
  • 🛠️ The process involves using free and open-source tools like invoke AI and a stable diffusion Discord bot, which can be installed and run on a local machine.
  • 💻 Hardware requirements for running the AI include a GPU with at least 4-8 GB of VRAM and 16 GB of RAM, with the creator using an AMD system with 64 GB of RAM and an RTX 3090.
  • 🔍 Users can join the Discord server to generate images by entering prompts and adjusting settings such as width, height, and model.
  • 🖼️ The AI can generate high-quality images of various subjects, including human faces, with detailed features and settings that can be tweaked for different results.
  • 🔄 Users can also upscale images to higher resolutions within the system without losing detail, as demonstrated with a macro photo of a beetle.
  • 🎨 The AI is capable of creating images in different styles, such as photorealistic, portrait, and even futuristic scenarios based on prompts.
  • 🏠 It can also generate interior photography with specific styles and details, as shown with an industrial kitchen island image.
  • 📈 The creator has implemented a credit system to prevent abuse, providing users with free credits and additional credits daily, with the option to support the service further.

Q & A

  • What was the initial reaction to the AI-generated image of Elon Musk and Mary Berra posted on Twitter?

    -The image received over 13.5 million views in the first few hours and garnered a response from Elon Musk himself, as well as attention from the homepage of MSN and Snopes discussing deepfake images and AI capabilities.

  • How does the AI-generated image differ from a real photo, and why is it important for people to be aware of this?

    -It's becoming increasingly difficult to distinguish between AI-generated images and real photos. People should be aware to understand the capabilities of AI and to discern authenticity in digital media.

  • What is InvokeAI and how is it related to the AI art generation process described in the script?

    -InvokeAI is a free and open-source tool that can be downloaded from GitHub. It is used in conjunction with a stable diffusion Discord bot to generate AI art, similar to how mid-journey works.

  • What hardware requirements are needed to run the AI art generation tools mentioned in the script?

    -The hardware requirements vary, but one can start with a GPU having at least 4 to 8 gigabytes of VRAM and about 16 gigabytes of RAM on the main computer. The script's author uses an AMD system with 64 gigabytes of RAM and an RTX 3090 with 24 gigabytes of VRAM.

  • How can someone set up their own Discord server with a stable diffusion bot using InvokeAI?

    -After downloading and installing InvokeAI from GitHub, one should be able to run it on their local machine. The author offers to provide a detailed overview in the comments if there's interest.

  • What is the process of generating an image using the stable diffusion bot in the Discord server?

    -Users enter a prompt into the Discord server, set various settings like width, height, and model, and then generate an image. The bot then returns an image based on the input prompt.

  • What is the 'shoot style' prompt trigger used for in the AI art generation process?

    -The 'shoot style' prompt trigger is used to indicate that the AI needs to perform a high-quality rendering of a human face.

  • How can users modify the generated image or adjust the settings for a new image?

    -Users can modify the prompt, change the model, adjust the aspect ratio, or select different samplers through the 'tweak' function in the Discord server interface.

  • What is the purpose of the credit system in place for using the AI art generation bot?

    -The credit system is in place to prevent abuse of the system since it runs on the author's hardware and home PC. Users are given 500 free credits and an additional 10 credits twice a day.

  • How can users support the AI art generation bot to potentially get dedicated hardware and a full-time service?

    -Users can support the bot by joining as a member of the channel, which could help in getting dedicated hardware and running the service full time.

  • What are some examples of prompts users have used to generate images with the AI art bot?

    -Examples include prompts for a model shoot of a 30-year-old woman in a city, a macro photo of a beetle, a 3D render of a fluffy ranchula cat hybrid, and an editorial style photo of an industrial kitchen island.

Outlines

00:00

🚀 AI and the Future of Image Creation

The script begins with the creator sharing an experience of posting a manipulated image of Elon Musk and GM CEO Mary Berra, which garnered significant attention and even a response from Elon Musk. It highlights the capabilities of AI tools like 'stable diffusion' and 'mid-journey' in generating realistic images, blurring the line between real and AI-generated photos. The creator then introduces a Discord server setup with a 'stable diffusion bot' using 'invoke AI' to generate images from text prompts, demonstrating the ease of use and the creative potential of these AI tools. Hardware requirements and the process of setting up the bot on a local machine are discussed, along with an invitation for viewers to join the server and experiment with image generation themselves.

05:01

🎨 Exploring AI Image Generation with Various Prompts and Settings

This paragraph delves into the practical use of the AI image generation system, showcasing how users can input prompts to create a variety of images, from futuristic scenes to macro photography of a beetle. The creator demonstrates how to adjust settings such as aspect ratio, model, and sampler to achieve different results, and also how to upscale images for higher resolution without losing detail. Examples of generated images, including a 'hyper realistic very cute multi-pastel dotted fluffy ranchula cat hybrid' and an 'editorial style photo' of an industrial kitchen, are provided to illustrate the system's capabilities. The script also mentions the importance of being respectful when sharing images in public channels and introduces a credit system to prevent abuse of the AI system running on the creator's hardware.

Mindmap

Keywords

💡InvokeAI

InvokeAI is an open-source tool that enables the creation of AI-generated art. It is highlighted in the video as an alternative to Midjourney for generating stunning images without cost. The script describes how the presenter used InvokeAI to set up a Discord bot that generates images based on user prompts, demonstrating its capability to produce a variety of artistic outputs.

💡Midjourney

Midjourney is a term used in the script to refer to a version of a software that creates AI-generated images. The video starts with a story about how a picture generated using Midjourney version 5 gained significant attention, including a response from Elon Musk, showcasing the impact and recognition AI art can achieve.

💡Deepfake

Deepfake refers to synthetic media in which a person's likeness is swapped with another using AI. In the context of the video, the term is used to discuss the challenges of distinguishing real photos from those generated by AI, such as the image of Elon Musk and GM CEO Mary Berra, which was mistaken for real and gained widespread attention.

💡Stable Diffusion

Stable Diffusion is a type of AI model mentioned in the script that is capable of generating images from textual descriptions. It is used in conjunction with the Discord bot to create images as part of the InvokeAI setup, illustrating the script's theme of exploring AI's creative potential.

💡Discord Server

A Discord server is a platform where communities can interact through voice, video, and text channels. In the video, the presenter mentions setting up a stable diffusion bot on their Discord server using InvokeAI, allowing users to generate images by providing prompts, demonstrating the practical application of AI in a social setting.

💡AI Techniques

AI Techniques in the script refer to the methods and processes used by artificial intelligence to create content, such as images. The video discusses how these techniques are becoming increasingly sophisticated, making it harder to differentiate between real and AI-generated photos.

💡GPU

GPU stands for Graphics Processing Unit, a specialized electronic circuit designed to manipulate and alter memory to accelerate the creation of images in a frame buffer intended for output to a display device. The script mentions the hardware requirements for running AI image generation tools, with a GPU being essential for handling the computational tasks.

💡Prompt

In the context of AI art generation, a prompt is a text description that guides the AI in creating an image. The script provides examples of prompts used to generate various images, such as 'model shoot style' and '30-year-old woman in a city,' illustrating how specific or creative prompts can direct AI to produce particular artistic outcomes.

💡Upscale

Upscale in the video refers to the process of increasing the resolution of an image while maintaining or enhancing its quality. The script describes how users can upscale their AI-generated images to achieve higher resolutions, showcasing the flexibility and control users have over the final output.

💡Sampler

A sampler in AI art generation is an algorithm that determines how the AI interprets the prompt and creates the image. The script mentions different samplers that can be used to achieve various styles and effects in the generated images, such as Euler, which was used to create an image with unique hand positioning.

💡Credit System

The credit system mentioned in the script is a mechanism to manage and limit the usage of the AI image generation service to prevent abuse. Users are given a certain number of credits to use the service, with additional credits provided periodically, reflecting the need to balance accessibility with resource management.

Highlights

A picture of Elon Musk and GM CEO Mary Berra generated using mid-journey version 5 gained over 13.5 million views in a few hours.

Elon Musk responded to the generated image, commenting on his outfit.

The generated image sparked discussions on deep fake images and AI capabilities on platforms like MSN and Snopes.

Difficulty in distinguishing between real and AI-generated photos is increasing.

A Discord server was set up with a stable diffusion bot using invoke AI to generate images from prompts.

Invoke AI and stable diffusion Discord bot are free and open-source tools available on GitHub.

Hardware requirements for running the AI image generation include at least 4-8GB of VRAM on a GPU and 16GB of RAM.

The system can be run on a local machine, as demonstrated with an AMD system and an RTX 3090 video card.

Users can generate images by entering prompts into the Discord server's art prompts channel.

The default model used is called 'stably diffused wild', and 'model shoot style' is a prompt trigger for high-quality human face rendering.

Users can tweak image generation settings such as width, height, and model.

The system allows changing the aspect ratio, model, and sampler for image generation.

Images can be upscaled within the system to increase resolution without losing detail.

The AI can generate a variety of images, including futuristic scenarios, macro photos, and hyper-realistic renders.

Interior photography prompts can also be used to generate detailed and themed images.

The system does not have the same restrictions as other platforms, allowing for more freedom in image generation.

A credit system is in place to prevent abuse, with 500 free credits and an additional 10 credits twice daily.

Support for the system can be provided through membership, potentially leading to dedicated hardware and full-time service.