Better Than Midjourney: Openjourney Stable Diffusion
TLDRThe video introduces a method to run mid-journey as a local service on a PC, enabling unlimited free image generation. It guides viewers through downloading an open-source mid-journey model from Hugging Face and using it with a local hosted version of stable diffusion. The process involves using prompts from various sites and adjusting settings to achieve detailed, stylistic images without the need for a monthly subscription.
Takeaways
- 🌟 The speaker introduces an alternative to the mid-journey AI stable diffusion website, which requires a monthly subscription.
- 🚀 The alternative allows users to run mid-journey as a local service on their own PC, enabling unlimited free image generation.
- 💡 The process is based on training data from actual mid-journey images, ensuring results similar to the original service.
- 📱 Users need to have followed a previous tutorial on setting up automatic 1111 on their local Windows machine to proceed.
- 🤖 Hugging face is highlighted as a valuable resource, offering a variety of training datasets, models, and more for stable diffusion.
- 🌐 The open Journey model, an open-source mid-journey trained model, can be downloaded from Hugging face and used locally with automatic 1111.
- 🔍 Users can explore different models by searching for 'mid-journey' on Hugging face and trying various options.
- 🎨 The speaker demonstrates the use of creative indie, a site with 644 mid-journey style prompts, to generate images using the new local service.
- 📸 The results showcase detailed and intricate images that reflect the style specified in the prompts, such as HR Geiger's surreal underwater world and Frank Frazetta's epic battle scenes.
- 🛠️ Prompt building is crucial for getting the most out of stable diffusion, and websites like Prompt Hero can assist in crafting effective prompts.
- 💬 The speaker encourages users to share their generated images on the Discord Channel for feedback and further exploration.
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 and what are its limitations?
-Mid-journey is an artificial intelligence stable diffusion website that allows users to connect to Discord and generate artwork. Its limitations include the requirement of a monthly subscription and a limited number of images that can be created based on the subscription plan.
What is the significance of the open Journey model found on hugging face?
-The open Journey model is an open source mid-journey trained model available on hugging face, which can be downloaded and used with a local hosted version of stable diffusion. This allows users to generate images similar to mid-journey without any cost.
How does one set up a local service for mid-journey?
-To set up a local service for mid-journey, one needs to follow a tutorial on setting up automatic 1111 on their local Windows machine, download the checkpoint file for the open Journey model, and place it into the models directory inside the stable diffusion install.
What are some features of the stable diffusion UI?
-The stable diffusion UI allows users to select the model they are using, input prompts, use negative prompts to exclude certain elements, and adjust sampling methods and steps to improve image quality. It also enables users to upscale the resolution of the generated images.
What kind of results can be expected from using the open Journey model?
-The results from using the open Journey model include highly detailed and intricate images, often styled after specific artists or themes as prompted by the user. The images can range from surreal underwater worlds to historical epic battle scenes and steampunk airships.
How can one find effective prompts for stable diffusion?
-Effective prompts for stable diffusion can be found on websites like creativeindie and prompthero, which provide a list of prompts and examples of generated images. These prompts can be directly used in automatic 1111 to achieve similar results.
What is the role of the Discord Channel mentioned in the video?
-The Discord Channel mentioned in the video serves as a community space for users to share their results, discuss their findings, and potentially discover better models or prompts for stable diffusion.
What are some tips for refining the prompts in stable diffusion?
-Refining prompts in stable diffusion involves adjusting the wording to be more specific, using negative prompts to exclude undesired elements, and experimenting with different sampling methods and steps to improve the quality and detail of the generated images.
What is the potential benefit of using the local service for mid-journey?
-The potential benefit of using the local service for mid-journey is that it allows users to generate an unlimited number of images for free, without the need for a monthly subscription or being limited by the number of images they can create.
Outlines
🖌️ Exploring Mid-Journey Alternatives
This paragraph introduces an alternative to the Mid-Journey AI art generation platform, which requires a paid subscription. The speaker proposes a method to run Mid-Journey as a local service on one's PC, enabling unlimited free image generation. The process involves using training data from Mid-Journey images and setting up a local instance of the AI model through Hugging Face, an online resource for machine learning models. The speaker also references a previous tutorial on setting up Automatic 1111, a crucial step for this method.
🚀 Generating Art with Open Journey Model
The speaker demonstrates how to utilize the Open Journey model, an open-source version of Mid-Journey, to generate AI art. They guide the audience through downloading a checkpoint file from Hugging Face and integrating it with their local stable diffusion setup. The paragraph highlights the ease of using different models and experimenting with various prompts to achieve detailed and stylized images. The speaker also mentions a Discord channel for sharing results and suggests using prompt-building websites for better outcomes.
Mindmap
Keywords
💡Artificial Intelligence
💡Mid-Journey
💡Stable Diffusion
💡Discord
💡Hugging Face
💡Open Journey
💡Prompts
💡Neural Network
💡Upscale
💡Community
💡Tutorial
Highlights
The introduction of a method to run mid-journey as a local service on a personal computer, enabling the generation of unlimited free images.
Comparison of mid-journey's paid subscription model with the proposed free, local service alternative.
The requirement of following a tutorial on setting up automatic 1111 on a local Windows machine as a prerequisite for this method.
The utilization of hugging face, a website with various training datasets and models for stable diffusion.
Discovery of an open source mid-journey trained model on hugging face that can be used with automatic 1111.
A simple process of downloading the checkpoint file from hugging face and adding it to the stable diffusion install directory.
The ability to test different models by searching for 'mid journey' on hugging face and selecting from the available datasets.
The setup of a Discord Channel for sharing results and finding better models.
Use of creativeindie website for mid-journey style prompts to generate images with automatic 1111.
The use of specific prompts to generate detailed, stylistic images such as a surreal underwater world in the style of HR Giger.
Adjusting the sampling method, steps, and using an upscaler to enhance the quality and resolution of the generated images.
The exploration of prompt hero website for the best open Journey prompts and detailed information on generating images.
The process of refining prompts and details of images for achieving desired results.
The generation of a highly detailed robot image using a specific prompt and negative prompt to avoid undesired features.
The creation of a photorealistic image of a young South Korean girl with detailed facial features and styling.
The discussion of mixed results and the potential use of face fix features to improve image outcomes.
The overall concept of having a free version of mid-journey on a personal computer and the invitation to join a community for sharing and feedback.