Better Than Midjourney: Openjourney Stable Diffusion

All Your Tech AI
6 Mar 202309:52

TLDRThe video introduces a method to run mid-journey as a local service on a PC, enabling unlimited free image generation. It highlights the limitations of the original mid-journey platform, which requires a paid subscription. The tutorial guides users through setting up a local version using a free, open-source model from Hugging Face, demonstrating the process with various prompts and showcasing the resulting images. The video also recommends resources for crafting effective prompts and invites viewers to share their creations on Discord.

Takeaways

  • 🎨 The video introduces an alternative to the mid-journey AI art generation platform, which requires a paid subscription.
  • πŸ–ŒοΈ By running a local service on one's PC, it's possible to generate unlimited free images similar to those produced by mid-journey.
  • πŸ’‘ The process is based on training data from actual mid-journey images, ensuring comparable results without the need for payment.
  • πŸ“Ή Following a previous tutorial on setting up Automatic 1111 is a prerequisite for this method.
  • πŸ€– Hugging Face is a valuable resource for various models and training datasets, including open-source versions of mid-journey.
  • πŸ” The 'Open Journey' model by Prompt Hero is a specific example of an open-source model that can be used with stable diffusion.
  • πŸ“‚οΈ To use the 'Open Journey' model, one simply downloads the checkpoint file and places it into the models directory of the stable diffusion installation.
  • 🌐 There are numerous prompt sites available that provide a list of prompts for generating specific styles of images with stable diffusion.
  • 🎭 Examples of generated images include a surreal underwater world, a historical epic battle scene, and a steampunk airship, showcasing the versatility of the AI.
  • πŸ› οΈ Prompt Hero is highlighted as a useful website for finding the best open Journey prompts and detailed information on how to achieve specific results.
  • πŸ“Έ The results from the AI-generated images are highly detailed and can mimic the style of various artists, demonstrating the potential of this free alternative to mid-journey.

Q & A

  • What is the main topic of the video?

    -The main topic of the video is about running mid-journey as a local service on one's own PC to generate unlimited free images, based on training data from actual mid-journey images.

  • What is mid-journey?

    -Mid-journey is an artificial intelligence stable diffusion website that allows users to connect to Discord and generate amazing pieces of artwork.

  • What are the limitations of using mid-journey?

    -The limitations of using mid-journey include the requirement of a monthly subscription fee and a limited number of images that can be created based on the subscription plan.

  • How can one bypass the limitations of mid-journey?

    -One can bypass the limitations of mid-journey by running it as a local service on their own PC, which allows for the generation of unlimited free images.

  • What is the role of Hugging Face in this process?

    -Hugging Face is a website that hosts a variety of different training datasets, models, and other resources that can be used for stable diffusion. It provides an open source mid-journey trained model that can be downloaded and used locally.

  • What is the name of the open source model found on Hugging Face that is similar to mid-journey?

    -The open source model found on Hugging Face that is similar to mid-journey is called Open Journey.

  • How does one utilize the Open Journey model?

    -To utilize the Open Journey model, one needs to download the checkpoint file from Hugging Face and place it into the models directory inside their local stable diffusion installation.

  • What are some resources mentioned in the video for generating prompts?

    -The video mentions Creative Indie and Prompt Hero as resources for generating prompts. Creative Indie has a list of 644 mid-journey prompts, while Prompt Hero has a section on the best open Journey prompts.

  • How can one improve the quality of the generated images?

    -The quality of the generated images can be improved by increasing the sampling steps to 150 and using a high-resolution fix and upscaler, such as ESRGAN 4X, to increase the resolution of the images.

  • What kind of results can be expected from using the local service setup?

    -The results from using the local service setup can be highly detailed and intricate images, similar to what one would get from the mid-journey platform, but without the limitations or costs associated with it.

  • How can one refine their prompts for better image generation?

    -One can refine their prompts by using websites like Prompt Hero that provide examples of successful prompts and their parameters. By adjusting the prompts and details based on these examples, users can achieve a more accurate representation of what they are aiming for.

Outlines

00:00

πŸ–ŒοΈ Exploring Mid-Journey Alternatives

The paragraph discusses an alternative method to using the Mid-Journey AI stable diffusion website by running it as a local service on one's PC. This allows for the generation of unlimited free images, contrasting with Mid-Journey's paid subscription model. The speaker references a tutorial on setting up Automatic 1111 and introduces Hugging Face as a resource for downloading an open-source Mid-Journey trained model. The process of integrating this model with stable diffusion is explained, and the speaker shares their experiences with the results, highlighting the quality and style of the generated images.

05:01

🎨 Generating Detailed Artworks with AI

This paragraph delves into the speaker's exploration of generating detailed and intricate artworks using the local service setup. The speaker demonstrates how to use various prompts to create images in the style of renowned artists, showcasing the versatility of the AI model. They discuss the use of different prompts and sampling methods to refine the output and achieve high-quality results. The speaker also mentions the use of upscaling techniques to enhance the resolution of the generated images and shares their excitement about the potential of this technology. Additionally, they provide tips on finding effective prompts and encourage viewers to share their own creations.

Mindmap

Keywords

πŸ’‘Artificial Intelligence

Artificial Intelligence (AI) refers to the simulation of human intelligence in machines that are programmed to think, learn, and problem-solve like humans. In the context of the video, AI is used to generate artwork through a platform called 'stable diffusion', which is a website that leverages AI to create stunning pieces of art based on user inputs or prompts.

πŸ’‘Mid-Journey

Mid-Journey is an artificial intelligence-based platform that allows users to generate artwork by connecting to Discord and inputting prompts. It is highlighted in the video as a service that requires a monthly subscription and has limitations on the number of images that can be created based on the user's subscription plan.

πŸ’‘Stable Diffusion

Stable Diffusion is an AI model used for generating images from text prompts. It is an open-source technology that can be run locally on a user's PC, allowing for the creation of unlimited free images. The video provides a tutorial on how to set up Stable Diffusion on a local machine, enabling users to bypass the subscription fees and limitations of platforms like Mid-Journey.

πŸ’‘Discord

Discord is a communication platform originally designed for gaming communities but has since evolved to be used by various groups, including tech and AI communities. In the video, Discord is mentioned as a platform that can be connected to 'mid-journey' to generate artwork through AI.

πŸ’‘Hugging Face

Hugging Face is an open-source platform that provides a wide range of AI models and datasets, including those for stable diffusion. In the video, the speaker uses Hugging Face to find and download an open-source model trained on 'mid-journey' images, which can then be used with Stable Diffusion running locally on a PC.

πŸ’‘Open Journey

Open Journey is an open-source model that has been trained similarly to the 'mid-journey' platform. It is available on Hugging Face and can be downloaded to be used with local instances of Stable Diffusion, allowing users to generate images in the style of 'mid-journey' without any subscription fees.

πŸ’‘Prompts

In the context of AI-generated art, prompts are textual inputs or descriptions that guide the AI in creating a specific image. Prompts can range from simple ideas to detailed descriptions and play a crucial role in determining the output of the generated artwork. The video discusses using various prompt sites to find or create effective prompts for Stable Diffusion.

πŸ’‘Stable Diffusion UI

The Stable Diffusion UI refers to the user interface of the Stable Diffusion software, where users can input their prompts and configure settings to generate AI-based artwork. The video walks through the process of using the UI to select models, enter prompts, and adjust parameters to create images.

πŸ’‘Upscale

Upscaling in the context of image generation refers to the process of increasing the resolution of an image to make it larger and more detailed. The video mentions using an 'esrgan 4X' upscaler to increase the resolution of the generated images from 512x512 to 2048x1024 pixels.

πŸ’‘Community and Collaboration

Community and collaboration are central themes in the video, emphasizing the sharing of resources, knowledge, and results among users of AI art generation platforms. The speaker encourages viewers to join a Discord channel to share their generated images and discuss their experiences with the Stable Diffusion setup.

Highlights

The introduction of a method to run mid-journey as a local service on a personal PC, enabling the generation of unlimited free images.

The comparison of mid-journey's paid subscription model with the proposed free alternative using local service.

The requirement of having set up automatic 1111 on a local Windows machine as a prerequisite for this tutorial.

The use of hugging face, a website with various training datasets and models for stable diffusion, including an open source mid-journey trained model.

The simplicity of downloading and using the open Journey model directly with automatic 1111.

The availability of 21 different datasets for mid-journey on hugging face, allowing for diverse model training options.

The setup of a Discord Channel for sharing results and finding better models.

The demonstration of using creative indie's list of 644 mid-journey prompts with automatic 1111.

The detailed explanation of the prompt and settings used to generate a surreal underwater world in the style of HR Giger.

The use of DPM plus plus 2m sampling method and high-resolution upscalers to enhance image quality.

The presentation of the results, showcasing the intricate details and unique styles generated by the AI model.

The exploration of prompt hero's collection of the best open Journey prompts and the impact on generating specific styles.

The practical application of using prompts from prompt hero to achieve highly detailed and stylistically consistent images.

The discussion on refining prompts and the iterative process of achieving desired image outcomes.

The invitation to join a community for sharing and improving generated images, fostering a collaborative learning environment.