ThinkDiffusion FAQs
Getting Started
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.
Security & Privacy
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.
Features & Applications
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.
Collaboration & Workspace Management for TD-Teams
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.
Last updated
Was this helpful?