| Intro to ComfyUI: Mini-video series by ThinkDiffusion Learn about the basics of ComfyUI interface, settings, UI, workflows, and more. | /files/txlRnFekuWa4UmXDJnWE | /pages/Ln4HCaK6Rp16tmOukTtj |
| Intro to Stable Diffusion: Mini-video series by ThinkDiffusion Learn about the basics of Stable Diffusion interface, settings, UI, workflows, and more. | /files/lITZ2wsop8qPYLX1VHU7 |
| Create your First Image with ComfyUI & Flux - More control with ComfyUI nodes - Learning curve is higher | /files/LRG0BubkcbmNoSGVlCCf | /pages/KJVZHUi9jIdG67rG5WhH |
| Create your First Image with Automatic1111 - Easier, faster, lesser control overall | /files/1KcnHuwUJSLKpajCRnIf | /pages/cggxhidwY05zGHHg4fC6 |
My ComfyUI workflow is failing. How do I fix it?
If your ComfyUI workflow isn’t running, it’s usually one of these problems. This page will help you check each one step by step.\Run Auto1111 on the Cloud
# Intro to StableDiffusion Course for Beginners Watch step-by-step guide on how to begin with Stable Diffusion on Automatic1111. Run Auto1111 on the Cloud
Find the correct link to right-click on Civitai. You can also use the big download button on the top of the model's page, but when there are multiple files offered, you'll be able to choose individual files from this area.
Find the correct link to right-click on Huggingface with the download icon, NOT the model's name.
# How to use a textual inversion embedding in Automatic1111 {% hint style="info" %} Textual inversions can inject new objects and styles into a model, without having to actually change the model. They can be activated by a certain keyword to trigger the textual inversion’s contents to do their magic. {% endhint %} {% embed url="
# How to view and test Automatic1111 API All Automatic1111 machines have API enabled. Follow these simple steps to view the API docs and test different API endpoints.
1. After launching an A1111 machine, scroll down to the footer of the page where you find a link to the **API** docs page.
3. To access your API remotely you will need the full machine URL which you can get by hovering over the **API** link or by copying the **API** link's URL and removing the **/docs** from the path.
# How to use extensions in Automatic1111 ## **What are extensions?** {% hint style="info" %} Some popular extensions include: *ReActor faceswap, ADetailer, AnimateDiff, AgentScheduler, ControlNet, Deforum, Infinite Zoom, Inpaint Anything, Loopback Wave, Openpose Editor, Regional Prompter, SadTalker, Temporal-Kit, Ultimate SD Upscale, and Wav2Lip Studio*. \ \ **They're all preinstalled on Think Diffusion machines.** {% endhint %}
# How to create a Hypernetwork in Automatic1111 Within the **Train** tab and and under the **Create hypernetwork** tab: **1. Enter a name** for your embedding **2.** And click **Create hypernetwork** * The empty *.pt* file will appear under *../user\_data/a1111/models/hypernetworks/* * **⚡️Protip:** Please ignore the 'Created None' when you do it as it does create the empty .pt file in the correct place **3.** To use the hypernetwork file for training, you can head over to the **Train** tab and you will see your Hypernetwork file available. {% embed url="
**Just getting started? Check out the** [**ComfyUI Introduction Course.**](https://thinkdiffusion.gitbook.io/my-first-page/) {% embed url="
## ## ## How to upload a file from your device {% embed url="
Find the correct link to right-click on Civitai. You can also use the big download button on the top of the model's page, but when there are multiple files offered, you'll be able to choose individual files from this area.
Find the correct link to right-click on Huggingface with the download icon, NOT the model's name.
{% embed url="
# File Management Most AI tools make you re-upload files or burn compute just to grab an output file or check a log. That gets expensive fast - and it wastes your time. ## 🗂️ Folder Structure When you launch a machine on ThinkDiffusion, the platform automatically creates a **top-level folder** for that specific app. Each app has its own folder. You’ll see these in the file browser. {% hint style="info" %} File paths matter. Some workflows will fail if a model isn’t in the right subfolder. {% endhint %} #### Example top-level folders: * `/comfy/` → for ComfyUI machines * `/kohya/` → for LoRA training * `/automatic1111/` → for A1111 sessions Each of these app folders contains its own structure - and they’re separated so you don’t mix tools. #### Inside each app folder, there are common subfolders: **`/logs/`** > Where machine logs are stored. Each time you launch a machine, it writes logs here. File names match the machine ID in your URL. **`/models/`** > Where model files are stored (e.g. LoRAs, checkpoints).\ > Depending on the app, these might be split into: * `/models/checkpoints/` * `/models/loras/` * `/models/vae/` **`/outputs/` or `/outputs/img2img/`** > Saved images, video frames, or render results show up here - depending on the app. **`/input/` or `/images/`** > Where uploaded images, masks, or reference files go. Some workflows look for inputs in specific folders.
**Note:** *On free accounts, files are only accessible while a machine is running. Files are automatically deleted after 48 hours of inactivity. The 24/7 File Browser is available on TD Pro accounts.* ## 🗂️ 24/7 File Browser * Your files persist between sessions * You don’t need to launch a machine just to grab a LoRA * You can prep and organize workflows without paying for idle GPU time * You can debug logs even while your machine is launching With the 24/7 File Browser: {% hint style="info" %} The 24/7 File Browser gives you full access to your files - without launching a machine. You can upload models, check logs, organize folders, and download outputs, all without paying for GPU time.\ \ It’s only available with **ThinkDiffusion Pro**. {% endhint %}
# Navigate your files ## How to master your files like a Pro Our built-in file management browser and tools provide you with a personal and persistent cloud storage drive and a robust system that's essentially an extension of your own device. Your files will stay persistent across all sessions & machines, and with a subscription will have increased storage with no inactivity cap. {% embed url="
1. Don't forget to `Restart` the ComfyUI app and `Refresh` the browser after install. (as instructed by ComfyUI Manager) 2. After restart and refresh, if it still shows missing, 3. Check the logs (using the console logs or by openning the corresponding log file under `/comfyui/logs`) 1. it may show install errors or load errors and should show "FAIL" before the custom node in the launch section. 2. Share the log file with us as it can be a bit technical to read. 3. The custom node may only work on later version of Comfy or other dependency already on ThinkDiffusion BETA release of Comfy. You can try on BETA. 4. We may need to install some dependency. We can determine if you share the log file with us. 4. You can try to stop the machine and launch a new one. Some custom nodes require to come up from a full boot up, but this is less common. 5. If your custom node works after restart and refresh, but fails to load on a new launched machine 6. There a good chance that we need to install some dependency so that it persists between launches. We can determine if you share the log file with us. If you see red nodes in your workflow, it means you're missing some required custom nodes. Follow these steps to install them so your workflow can function properly. 1. Go to ComfyUI Manager > Click Install Missing Custom Nodes
Find the correct link to right-click on Civitai. You can also use the big download button on the top of the model's page, but when there are multiple files offered, you'll be able to choose individual files from this area.
Find the correct link to right-click on Huggingface with the download icon, NOT the model's name.
# Pre-installed Models / Nodes / Extensions # Admin & Billing **What’s the hourly rate policy?** * Pay-as-you-go. You’re charged only for the duration used. Any unused portion is refunded when the machine stops. * **"Is TD-Pro a one-time fee or subscription?"** * It’s a $19.99/month subscription. You still pay machine usage on top of that. * **"What does TD-Pro give me?"** * 200GB persistent storage * 20% discount on machine rates * $10 in monthly credit * Ability to use 24/7 file browser without launching a machine * **"Do I pay the hourly rate in addition to the Pro fee?"** * Yes. You’re charged for actual usage on top of the monthly fee. The $10 credit offsets part of it. ## ## How to find an invoice?
What is ThinkDiffusion and how does it help me create AI Art?
ThinkDiffusion allows users to launch virtual machines with selected open-source apps. Users can use models from anywhere on the internet, such as Hugging Face, Civitai, or their own models. They can also install any extensions for Automatic1111 and custom nodes for ComfyUI. A ThinkDiffusion virtual machine works just like a personal computer.How does ThinkDiffusion handle data privacy and security?
ThinkDiffusion ensures that each machine and workspace is 100% private. Your data is never shared publicly, and you have complete control over your environment. We store user data securely with a top-tier Fortune 50 global provider, ensuring robust security and reliability.What applications are included in the ThinkDiffusion platform?
ThinkDiffusion includes more than 10 cutting-edge applications for Stable Diffusion and other image and video models.\* **Automatic1111** – A comprehensive UI for all Stable Diffusion features. * **Forge** – A faster and more frequently updated fork of Automatic1111. * **ComfyUI** – A workflow/node-based interface for advanced AI workflows. * **Kohya** – A dedicated UI for model training and fine-tuning. * **Fooocus** – Simplifies AI art generation with user-friendly controls. * **And More** – Access additional open-source apps and the latest experimental tools.
Can I access custom models and extensions on ThinkDiffusion?
Yes. ThinkDiffusion offers open access to models from Civitai, Hugging Face, and other open-source repositories. Users can upload their own models and install custom extensions for Automatic1111 and custom nodes for ComfyUI. You can do anything on ThinkDiffusion that you could as if you setup the open-source apps locally on your own computer.How does ThinkDiffusion handle updates and new model releases?
We regularly update all the open source apps to support the latest workflows and new model releases. From the time of release of a new popular model to when these apps are updated could be as quick as 48 hours. Note that, in many cases, we don’t need to update our platform for new models, as users can simply upload and use them as soon as they are created.What models and checkpoints are available?
The machines are like your local computer that you don't have to manage - so any open source model from Hugging face, Civitai, or your own local models are all usable.Are there any restrictions on the available models? Can teams upload and train their own LoRAs?
No restrictions. It is your own virtual computer. You can train LoRAs (and other types of models) and then upload the LoRAs to use on ThinkDiffusion.How does ThinkDiffusion handle session persistence (e.g., saved workflows, ongoing projects)?
All files, customizations, installed nodes, extensions, everything is persistent as long as you have an active TD-Pro or TD-Teams subscription. Note that your files will automatically be deleted within 48 hours of an expired subscription.Does Think Diffusion support direct export to other creative tools like Adobe Suite, DaVinci Resolve, Capture One, etc.?
No, there is no integration to these other tools. However, there may be opensource extensions for Automatic1111, Forge or custom nodes for ComfyUI that can achieve the desired effect of generating outputs that can be used in other closed source tools.Does Think Diffusion plan to support multimodal AI tools in the future (e.g., video generation, 3D, music AI, etc.)?
Video, 3D and music are already offered on ThinkDiffusion through various apps and workflows on those apps such as ComfyUI.How does ThinkDiffusion enhance creative collaboration?
Every workspace can have custom nodes, installed extensions, and shared models that remain persistent. When a team member installs a custom AI model, workflow, or extension, it becomes available to all users within that workspace, ensuring a consistent and collaborative environment.How are individual team member accounts managed? (SSO, email-based, etc.)
When you create an Admin account, you can use your email and password, and invite individuals via their emails. Admins centrally manage billings and can also set limits for each team member’s monthly max usage.How does Thinkdiffusion handle simultaneous usage for multiple team members?
ThinkDiffusion is highly scalable, and each team member can launch one or more dedicated virtual machines simultaneously.Can team members choose different UIs (e.g., Automatic1111, ComfyUI, Fooocus), or is access limited?
Yes, team members can launch any number of apps including those listed as well as others like Kohya, Forge, Live Portrait, AudioWeb, FaceFusion, Swarm, Diffusion Pipe, and more.Can I belong to multiple teams?
Yes, you can be a part of multiple TD-Teams AI workspaces and switch between them using the profile drawer.Are there role-based permissions (e.g., different access levels for team members)?
Yes, admins can manage the account, handle billing, add and remove users, set usage limits, and create new workspaces.How do I add and manage team members?
Team Admins can create any number of workspaces, each fully isolated to keep projects and clients separate. Team Admins can invite any team member to each workspace. Team Admins can set usage limits for each team member. This is perfect for larger teams or classes that need controlled access.Can I access my files without launching an AI machine?
Yes. TD-Teams includes the 24/7 file browser, allowing access to files anytime without additional cost, even when no GPU is running.How do I launch and manage machines within a workspace?
Click on a workspace to enter it. All GPU machines launched within that workspace will remain associated with it.Are there time limits per user session, or can members work as long as needed?
No limits. There is an autostop timer that can be set as a safety to ensure the machines do not run on forever. Admins can also set usage caps for users.What happens if the team expands - is it easy to scale up?
It is as easy as adding more individuals to the account.How To Access Logs In ThinkDiffusion
* Simply navigate to *a1111/logs*, *comfyui/logs,* *fooocus/logs, or kohya/logs.* * Click on the *\
*** If you're still confused about an issue, feel free to reach out to our support team on the ThinkDiffusion[ Discord here](https://discord.com/invite/hAm87ApunD). Don't forget to attach the `logs file` as it helps them resolve your query much faster. **Step-by-step breakdown of how to access Logs on ThinkDiffusion** 1. Navigate to your apps file browser and click on app name, for example - "comfyui"
Download the workflow file and drag & drop it into your ComfyUI window.
### 1. Check your machine and app version Some workflows require more memory or a specific version of ComfyUI/other apps to run correctly. If the workflow silently fails, this could be a potential reason.
* If you're using a workflow from GitHub or CivitAI, check if it mentions: * Required ComfyUI or app version * Specific machine sizes needed for the workflow * Map the app versions you need with the app versions on ThinkDiffusion:
Map the app versions you need with the versions on ThinkDiffusion:
Ensure that you're using the correct machine size you need
If you see red nodes in your workflow, you need to install missing custom nodes
Machine stuck on the “skeleton” screen (UI not loading)
If you see the file browser isn’t showing files, just skeleton placeholders - it’s not communicating with the server. There’s a good chance the server has crashed.# Machine stuck on the “skeleton” screen (UI not loading) If you see the file browser isn’t showing files, just skeleton placeholders - it’s not communicating with the server. There’s a good chance the server has crashed. # Failing to launch – Bad custom nodes # Page 1 # EDU / Teams Commonly Asked This guide is designed to help TD-Teams and TD-EDU users deliver the best experience for sessions, classes, and training events. It covers onboarding, key links, do’s and don’ts, setting up workflows, and common issues to ensure smooth operation. #### **ThinkDiffusion Self-Onboarding & Pricing Links:** **For TD-EDU** * Onboarding Link:[ Set up your TD-EDU Account](https://learn.thinkdiffusion.com/your-td-edu-account/) * Pricing Link:[ View TD-EDU Pricing](https://www.thinkdiffusion.com/edu#teams) **For TD-Teams** * Onboarding Link:[ Set up your TD-Teams Account](https://learn.thinkdiffusion.com/your-td-teams-account/) * Pricing Link:[ View TD-Teams Pricing](https://www.thinkdiffusion.com/teams#teams) *** #### **Ensuring Sufficient Funds for Large Classes** If you’re planning to run a large class with, say, **50 students**, make sure to **add sufficient funds to your team account** so that all **50 students have enough credits to launch machines** without interruptions. **Here’s why this is important:** * **When a student launches a machine**, the system **pre-debits the funds** from your total team balance to secure enough resources for the machine's runtime. * If your team balance **doesn’t have enough funds**, students will face issues launching their machines — even if they haven’t consumed their full usage yet. * For example, if each student requires **$10 worth of credits** to launch a machine, you’ll need at least **$500 pre-loaded** to ensure everyone can start simultaneously. **To avoid this, you can:** 1. **Pre-load sufficient funds** in your account before class starts. 2. Monitor usage under **Manage Teams > Set Members Limit** to ensure fair usage. 3. If a student runs into credit issues, you can **manually increase their limit** or add more funds during the class. *** #### **Setup Credit Spend for Each Student:** To prevent abuse or accidental overuse, you can set individual monthly usage limits for each student or workspace member. If this setting is **OFF**, users will have unrestricted access to the total credits available in your account. **To set limits:** In your Team Members section, click "*Set Member Limits*"
# Page 4