Create Stunning Ai Art For Free With InvokeAI: Midjourney Alternative

All Your Tech AI
28 Mar 202308:08

TLDRIn this video, the creator shares his experience with InvokeAI, an open-source alternative to Midjourney for generating AI art. After posting a viral image of Elon Musk and GM CEO Mary Barra, he discusses the blurring line between real and AI-generated photos. He demonstrates setting up a Discord bot using InvokeAI and stable diffusion to create images from text prompts, showcasing various results and customization options. The video also touches on the potential for abuse and the credit system in place to manage usage on his server.


  • 😀 The video showcases the capabilities of AI art generation using InvokeAI, an alternative to Midjourney.
  • 📸 A humorous image of Elon Musk and GM CEO Mary Berra generated over 13.5 million views and a response from Elon Musk himself.
  • 🌐 The video and generated image gained attention on MSN and Snopes, highlighting the public interest in AI-generated 'deep fake' images.
  • 🤖 AI is reaching a point where it's difficult to distinguish between real and AI-generated photos, which is a growing concern and area of awareness.
  • 🔧 The presenter set up a Discord server with a stable diffusion bot using InvokeAI to allow users to generate images from prompts.
  • 💻 The setup requires specific hardware, such as a GPU with at least 4-8GB of VRAM and a computer with 16GB of RAM.
  • 🛠️ InvokeAI and the stable diffusion Discord bot are both free and open-source tools, available for download and local machine setup.
  • 🖼️ Users can input prompts and adjust settings like image dimensions and models to generate custom AI art.
  • 🔄 The system allows for image upscaling to maintain detail at higher resolutions, enhancing the quality of the generated art.
  • 🎨 The AI can generate a variety of images, including human portraits, macro photos, and interior photography, with detailed prompts.
  • 🚫 Unlike some other systems, there are no restrictions on the types of images that can be generated, but users should be respectful of the public channel.
  • 🏆 The presenter offers a credit system for using the AI art generator, with free credits and the option to support the service further.

Q & A

  • What was the initial purpose of posting the picture of Elon Musk and GM CEO Mary Barra on Twitter?

    -The initial purpose was to show off the capabilities of mid-journey version 5 and to entertain Tesla followers with a humorous image.

  • How many views did the posted picture receive in the first few hours?

    -The picture received over 13.5 million views in the first few hours.

  • What was Elon Musk's response to the posted image?

    -Elon Musk responded by saying he would never wear that outfit.

  • What AI techniques are mentioned in the script that are making it difficult to distinguish between real and generated photos?

    -The AI techniques mentioned are stable diffusion and mid-journey.

  • How can one create images using the Discord server with the stable diffusion bot?

    -By joining the Discord server and using the 'slash dream' command along with a prompt to generate an image.

  • What are the minimum hardware requirements to run the stable diffusion bot on a local machine?

    -A minimum of 4 to 8 gigabytes of VRAM on a GPU and about 16 gigabytes of RAM on the main computer.

  • What is the default model used by the stable diffusion bot, and what is a prompt trigger for high-quality human face rendering?

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

  • How can users change the model and sampler settings in the stable diffusion bot?

    -Users can change the model and sampler by accessing the 'tweak' option, which allows modification of various settings including the model and sampler used for image rendering.

  • What is the purpose of the credit system in place for using the stable diffusion bot on the Discord server?

    -The credit system is in place to prevent abuse of the system, as it is running on the host's hardware and home PC.

  • How can users support the stable diffusion bot service to potentially get dedicated hardware and a full-time service?

    -Users can support the service by joining as a member of the channel, which may help in acquiring dedicated hardware for running the service full time.

  • What is the name of the person who demonstrated the use of the stable diffusion bot, and what is his online handle?

    -The person's name is Brian Lovett, and his online handle is 'All Your Tech AI'.



📸 AI-Generated Images and Public Reaction

The speaker recounts their experience of posting an AI-generated image of Elon Musk and GM CEO Mary Barra on Twitter, which quickly garnered over 13.5 million views and responses from Elon Musk himself. The image sparked discussions on the homepage of MSN and Snopes about deepfake images and AI capabilities. The speaker emphasizes the growing difficulty in distinguishing real photos from AI-generated ones and introduces a Discord server setup with a stable diffusion bot using invoke AI to create images from text prompts, which has already seen significant user engagement.


🛠️ Setting Up AI Image Generation and User Interaction

The speaker details the process of setting up an AI image generation system using free, open-source tools like invoke AI and a stable diffusion Discord bot. They discuss the hardware requirements for running such a system, mentioning their own setup with an AMD system and an RTX 3090 video card. The speaker provides a step-by-step guide on how to use the system, including entering prompts and adjusting settings for image generation. They also demonstrate how to upscale images and change models and samplers for different results, showcasing the versatility and potential of AI in creating detailed and realistic images.




InvokeAI is an open-source tool mentioned in the script that enables users to create AI-generated art for free. It is an alternative to Midjourney and is used in conjunction with a stable diffusion bot to generate images based on textual prompts. The script highlights how InvokeAI can be integrated into a Discord server to allow users to create stunning AI art, emphasizing its ease of use and the impressive results it can produce.


Midjourney is a term used in the script to refer to a version of an AI art generation tool. The script discusses how a picture generated using 'mid-journey version 5' featuring Elon Musk and GM CEO Mary Berra gained significant attention, including a response from Elon Musk himself. This highlights the capabilities and impact of AI in creating realistic and engaging images.


Deepfake refers to the use of AI to create synthetic media where a person in an existing image or video is replaced with someone else's likeness. In the script, the term is used in the context of AI-generated images that are so realistic they can be mistaken for real photos, sparking discussions about the authenticity of media and the capabilities of AI tools like stable diffusion.

💡Stable Diffusion

Stable Diffusion is an AI model mentioned in the script that is capable of generating images from textual descriptions. It is used as the backend for the Discord bot set up by the script's narrator, allowing users to input prompts and receive AI-generated images. The script emphasizes the high quality and detail of the images produced by Stable Diffusion.

💡Discord Server

A Discord server is a platform where communities can communicate in real-time through text, voice, and video. In the script, the narrator describes setting up a stable diffusion bot on a Discord server using InvokeAI, which allows members to generate AI art by inputting prompts, showcasing the collaborative and interactive nature of AI art creation.

💡AI Techniques

AI Techniques in the context of the script refer to the methods and algorithms used by AI models to generate images, text, or other forms of media. The script discusses the increasing difficulty in distinguishing between real photos and those generated by AI, indicating the advancement and effectiveness of these techniques in mimicking reality.


A GPU, or Graphics Processing Unit, is a specialized electronic circuit designed to rapidly 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 art generation tools, with a GPU being essential due to its ability to handle the complex computations involved.


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


Upscaling in the AI art context 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 without losing detail, demonstrating the flexibility and control users have over their creations.


A sampler in AI art generation is an algorithm that determines how the AI interprets the prompt and generates the image. The script mentions different samplers available in the system, such as Euler, and how changing the sampler can result in different artistic interpretations of the same prompt.

💡Credit System

The credit system mentioned in the script is a mechanism to prevent abuse and manage the usage of the AI art generation tool on the Discord server. Users are given a certain number of free credits to use the service, with additional credits provided periodically, highlighting the need for resource management in communal AI tools.


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

The viral image prompted a response from Elon Musk about his outfit and was featured on MSN and Snopes discussing deep fake images and AI capabilities.

Difficulty in distinguishing between real photos and AI-generated images is increasing due to tools like stable diffusion and mid-journey.

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

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

Hardware requirements for running these tools include at least 4-8 GB of VRAM on a GPU and 16 GB of RAM.

The author uses an AMD system with 64 GB of RAM and an RTX 3090 with 24 GB of VRAM for running the AI tools.

Instructions on setting up the AI tools on a Discord server are available upon request in the comments.

Users can join the author's Discord server to test out stable diffusion and generate images.

The process involves entering a prompt and adjusting settings such as width, height, and model for image generation.

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 the prompt, change settings, and select different models and samplers to refine the image generation process.

Images can be upscaled within the system to maintain crisp detail at a higher resolution.

Creative prompts from the community have generated a variety of interesting and high-quality AI art.

The AI can render non-human subjects, such as a macro photo of a beetle, with impressive detail.

Interior photography prompts can also be used to generate detailed and realistic images, such as an industrial kitchen island.

The system allows for specifying camera and lens details in the prompt for a more tailored image result.

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

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