A checkpoint refers to a large model, which contains comprehensive and extensive recorded information. In addition to these large models, there are smaller models like Lora, Embeddings, and Hypernetworks that fine-tune the large model in more detailed ways.
Learn About Embeddings
If you select an embedding on Civitai, you'll notice that their sizes are usually around 20 or 30 KB, which is very small. How is this possible? Think of a checkpoint as a dictionary, and an embedding as a bookmark within it, guiding you to the definitions of specific words. In other words, embeddings can be used to capture and restore character features, such as this Lucy Lu embedding.
To use an embedding, download the file first. Then, upload it into the "embeddings" folder. When you can see the embedding file in that folder, it means the upload was successful. Don't forget to include the trigger words in your prompt, as the embedding might not work without them.
Learn About Lora
Lora helps convey accurate features and clear subjects to the AI during the training of painting styles. If embeddings are like bookmarks, then Lora is like a coloring page tucked inside the dictionary, detailing all definitions, characteristics, and illustrations. This allows the AI to have a clear and detailed understanding of the image the user wants to generate.
Lora files typically range from 100 to 200 MB and are often used for game and manga characters.
To use Lora, find the Lora you want on Civitai and click "download." Then, go to WEBUI, navigate to the models folder, find the Lora folder, and upload the Lora file you downloaded.
Let's try this prompt:
jinx \(league of legends\), 1girl, solo, long hair, breasts, looking at viewer, smile, bangs, gloves, bare shoulders, very long hair, blue hair, braid, teeth, black gloves, belt, fingerless gloves, pink eyes, nail polish, grin, blurry, twin braids, crop top, hand on hip, tattoo, leaning forward, blurry background, blue nails, freckles, asymmetrical bangs, arm tattoo, shoulder tattoo, pink pants
Learn About Hypernetwork
Hypernetwork is used to improve the overall style of generated images,which is painting style. However, Hypernetwork are not considered as mainstream.
FInd the hypernetwork you want to use from Civitai, click download. Back to WEBUI, find models folder, click in and find hypernetworks. Then upload the hypernetwork you just downloaded.
How to download Auto1111
For Users Familiar with Python and Git:
- Download and Install via Git:
- If you have a Python environment set up and are comfortable with Git:
- Clone the Stable Diffusion repository from GitHub using the following command:
- git clone https://github.com/StableDiffusion/StableDiffusion.git
- Navigate into the cloned directory (
StableDiffusion
) and proceed with installation as per the provided documentation.
For Beginners or Those Using an Integration Pack:
- Download and Install Using an Integration Pack:
- Visit the official website of Stable Diffusion or an integration pack provider like auto1111. https://github.com/AUTOMATIC1111/stable-diffusion-webui
- Download the integration package (typically a zip file).
- Use decompression software such as Bandzip or WinRAR to extract the downloaded zip file.
- Or through a cloud service vendor, who generally has Stable diffusion pre-built and setup.
- Setting Up Stable Diffusion:
- Create a new folder on your computer for Stable Diffusion. Ensure the folder path contains only English characters and has sufficient local disk storage.
- Unzip the contents of the downloaded zip file into this new folder.
- Running Stable Diffusion:
- Locate and double-click the
run.bat
file within the Stable Diffusion folder. - Wait for the application to load; this may take a moment.
- The Stable Diffusion WebUI homepage should automatically open in your default web browser.
- Locate and double-click the
- Operating Stable Diffusion:
- Keep the command-line interface (CLI) window open while using the Stable Diffusion WebUI.
- Interact with the WebUI through your browser to generate AI images or perform other tasks.
- Remember to keep the command-line interface running while using the WebUI, and close it when you're done operating in the browser.