Creator's Club Documentation

Welcome Creators! Thank you for your support of RunDiffusion! We are thrilled to have you as a member of our community, creating incredible art on our platform! To show our appreciation, we have created this document specifically for you, to help you make the most of your subscription. We are confident that it will be an invaluable resource for you.

Benefits

  • $10 per month of promotional balance awarded
  • Discount on Large Hardware
  • 100 GB Private Storage
  • Persisted Settings
  • #CreatorsClub Discord
  • Upload/Merge Models
  • Upload to File Browser
  • Train Models (DreamBooth)
  • Deforum, Embeddings & Hypernetworks

Server Variations

We have three options when it comes to choosing the hardware to use when working on RunDiffusion. We keep this simple. We have tailored our hardware options to match the software for a good experience. Here is a brief explanation of the options.

  • Small (SM) - 8GB VRAM. Perfect for diffusion, image generation, and can do deforum at small resolutions.
  • Medium (MD) - 16GB VRAM. Faster than the small server. Perfect for diffusion, image generation, ControlNet, and Deforum. Does do Dreambooth training but takes about 30 to 45 minutes to train a model at 1500 steps.
  • Large (LG) 24GB VRAM. This does it all. Perfect for all the jobs you need done. Diffusion can be done in batches and your image output can be multiplied by a factor of 3. The extra VRAM enables for a very fast and stable Dreambooth experience. We have discounted this server for all our Creative Club Members because honestly it gives the best experience.

Access to Discord

Once you have signed up for Creator's Club, click the "Connect to Discord" button on the top of the UI. This will open a dialog box to connect your discord account and give you the Creator's Club role, giving access to the Creator's Club section of the Discord.

Storage

As a Creators Club member, you will receive 100GB of storage space exclusively for your use. You can increase your storage space for an additional fee, and you can also choose to add backups for an additional fee. Otherwise, there will be no backups made. Reach out to RunDiffusion to make those arrangements. Please note that you are responsible for the contents of your storage space and should ensure that they comply with the Stability Ai usage agreement. Keep in mind that this space is reserved exclusively for you and is not accessible to anyone else. https://huggingface.co/spaces/CompVis/stable-diffusion-license

You will start with an empty storage, minus a few essentials like the base model for Stable Diffusion. You will want to load up the models you like, as you won't have access to the shared storage models. Use this list of models from the shared servers to download the models you liked and want to use. https://learn.rundiffusion.com/models-available-on-rundiffusion/

Additional models can be found on HuggingFace, Civitai and across the web.

Logins and Drives

You have two different drives and storage mounts you need to be aware of:

  1. SDUser: This is your private 100GB of storage. In here is where you will load models, embeddings, and you will find your generated images/videos/models.
  2. Webui: This is the base StableDiffusion directory. Everything in this mount is wiped when you start a new session. At the moment, extensions are loaded here.

SDUser Volumes and Paths

Sometimes the software will need the path to find files you’ve uploaded. Here are the common formats you will be using.

  1. Pop open the Filebrowser, we find it's best in a new tab - less crowded!
  1. To access the stable diffusion folder structure, type in “sduser” and “password” into the filebrowser login. This will drop you into the Creator's Club private storage directory where you can upload models and find your generated images.
  2. The path for these files is /mnt/private/

Webui Volumes and Paths

Sometimes the software will need the path to find files you’ve uploaded in the Stable Diffusion base directory. Be careful when modifying files here, as it could crash your server. Here is a method you can use:

  1. Pop open the Filebrowser, we find it's best in a new tab - less crowded!
  2. To access the stable diffusion folder structure, type in “webui” and “password” into the filebrowser login. This will drop you into the stable diffusion webui directory where you can upload and move files. (Be careful in here!)
  3. The path for these files is /home/workspace/stable-diffusion-webui/
  4. Sometimes the trailing "/" is not needed depending on where you are sing it.
  5. Sometimes when you’re inside the software and it’s needing the stable-diffusion-webui files simply using the directory after /home/workspace/stable-diffusion-webui/ is enough. You will have to play with the different variations for each of the tools. It can be a nuisance. Feel free to drop a line in #support!

Errors (Terminal)

If you are experiencing errors that you cannot view because you do not have access to the terminal, you can view your terminal via the Logs folder on your storage. Open the logs file there to see the error message that might be popping up. Great for troubleshooting or getting help.

You can track your logs in the file browser shell using the following command: tail -n 30 -f /mnt/private/logs/auto1111.log

Errors (Bad Gateway)

If you get a black screen, but the timer frame and file browser still stays there you may have a "Bad Gateway". If you highlight the black portion of the screen you will see those words! There are generally three causes of Bad Gateway errors:

  1. Out of storage. Check your account in the top right of the Smart Timer and see how much storage you are using. If you are over 100GB you will need to delete some models or other files until it is below 100GB. Try to keep some room free at all times.
  2. Installing an Extension. When you install an extension and then refresh your UI, you will get a bad gateway error. Hit refresh on your browser after a minute and see if the UI loads. Note some extensions take longer to get out of a "Bad Gateway" state.
  3. Extension problem or misconfiguration. If you are trying different extensions, settings, scripts or VAE, you may find you get a bad gateway on boot. This can be fixed by either deleting the offending file if you know it, or by resetting to back up. To reset to backup, use file browser to rename your "Auto1111" folder to Auto111.bak - Then close down and start a new session. This will make another Auto1111 folder and should boot as normal. Then transfer over anything you need from the .bak folder and delete it.

Custom Models Uploading/Download to Server

Because of the size of models, we don’t recommend uploading them to your server through Filebrowser. (Unless you have blazing fast internet upload speeds). Your server is equipped with a 5Gbps fiber internet that can download models in seconds. We recommend the following methods over anything else.

Through Filebrowser Terminal

Don’t be scared, this is easy.

  1. First watch the video to see how it’s done in 90 seconds. https://streamable.com/f7cwr5 - Quick Version https://streamable.com/o3x2p6 - Detailed Explanation
  2. Spin up a SM server.
  3. Open Filebrowser and navigate to the top right to “open image gallery in” a new tab.
  4. Go to the folder you want to upload the model in. We recommend uploading to models/v1 or v2 depending on if it is a 1.5 or 2.1 model respectively.
  5. Now go back to the top right and click on the icon that looks like this “< >”.
  6. At the bottom of your screen you will see a “Terminal”

You have three commands you can use.

aria2c

  • aria2c is a torrent client that has been installed for your use. You can download from any URL or magnet link. This can be very very fast if you use the right option to download.
  • Get your URL and type aria2c -x8 [URL]
  • e.g. aria2c -x8 https://huggingface.co/protogen_model.ckpt

gdown

  • To download something from Google Drive you have to first allow the file to be shared. You will then take that link and bring it into your server and use “gdown” to download it.
  • Log into your Google Drive
  • Find the file you would like to download to your server.
  • Right click and find “Share”
  • Under “General access” change “Restricted” to “Anyone with the link”
  • Copy this link to your clipboard
  • Open the terminal in Filebrowser. In the terminal type:
    gdown --fuzzy [URL]
    gdown --fuzzy https://drive.google.com/file/d/etcetcetc...
    You will not add a space or a new line after the --fuzzy flag. The url is just too long for the line on this page.
  • The download will start and you’ll see the model in your filebrowser once you refresh

wget
wget is the easiest to use. It’s simple.
wget https://huggingface.co/protogen_model.ckpt
Note that we find that aria2c is generally better and faster!

Deforum

Deforum: The Wild West of AI Video
For a beginner’s overview of Deforum, check out this great walkthrough video by Matt Wolfe here... For an advanced rundown of Deforums features and settings, please check this video. Yes, it’s long but Matt has kindly indexed it so you can jump to what you need! Prompting and JSON Use
Check our information on Deforum here!

Dreambooth

There are a few ways to run Dreambooth. First way is through Automatic1111 and the Dreambooth extension, and the second way is through a new Linux distribution with a graphical interface.

Our more detailed docs are here:

Dreambooth Training
Dreambooth can be a tricky process, so be warned! You will need to be willing to try things possibly many times before you get a result you are fully satisfied with. It’s best to approach with a curious and experimental mindset to make the best of the tools available to

Automatic1111 Training

  1. Launch an Automatic1111 v1.5 server that is MD or LG (SM does not support Dreambooth)
  2. Go to the settings tab and make sure your paths are set correctly. They should look like this:
  3. Pop out Filebrowser so it’s easier:
  4. In Filebrowser, create a new folder. Call it “DBFiles” with no spaces.
  5. Inside this folder create two more folders. 'Input" and "Steps"
  6. Inside of the “Input” folder, you will put the images you are trying to train the new checkpoint model on.Go back to your server in Automatic1111 and back to the Dreambooth tab. Find the paths and set your paths. In your case it will be /mnt/private/DBFiles/Input/ and /mnt/private/DBFiles/Steps/
  7. There are a number of different settings for Dreambooth that change every now and then! Please reach out on Discord for the latest. We have a deep dive Deforum overview for Creators Club members here:
  1. Wait for your model to finish and you’ll be able to reload in the top right and try out your new model. All models output into your model library storage.

If you need to contact RunDiffusion, we are here to help. Please reach out to us:

Contact

Email: admin@rundiffusion.com
Discord: https://discord.com/invite/wH6dTyBpCf  #support

Great! You’ve successfully signed up.

Welcome back! You've successfully signed in.

You've successfully subscribed to RunDiffusion Docs.

Success! Check your email for magic link to sign-in.

Success! Your billing info has been updated.

Your billing was not updated.