This topic describes how to use the ComfyUI, Kohya, and Stable Diffusion WebUI tools.
Log on to the PAI ArtLab console.
Tool types and versions
The Toolbox includes the following tools:
Stable Diffusion WebUI: Supports features such as text-to-image, image-to-image, and animated image generation. For more information, see PAI ArtLab Stable Diffusion WebUI.
Kohya: Supports features such as dataset image annotation, batch generation, and model fine-tuning. For more information, see PAI ArtLab Kohya.
ComfyUI: Allows you to build node-based workflows. For more information, see PAI ArtLab ComfyUI.
The differences between the versions are as follows:
Difference | Shared edition | Exclusive edition |
Resource difference | Shared machine resources. | Dedicated machine resources. |
Billing difference | You are not charged for starting the tool. You are charged only for the actual GPU time consumed during image generation. For example, if you start a tool, click Generate on the tool's WebUI page, and an image is generated after 10 seconds, you are billed for 10 seconds. | Billing starts after the tool is successfully launched and stops after the tool is closed. You are billed hourly based on the unit price of the cloud machine type selected when you start the tool. For example, billing starts as soon as you see the tool's WebUI page. If the tool is open for 20 minutes, you are billed for 20 minutes, regardless of whether you use it. Closing the browser tab for the tool also closes the tool. Billing stops after the tool is successfully closed. |
Difference in custom installation of models and node plug-ins | Does not support custom plug-in installation. Only a few basic plug-ins are pre-installed, such as text-to-image, image-to-image, and ControlNet. | Supports custom installation of models, nodes, and plug-ins. For more information, see Upload a local model to the PAI ArtLab platform. |
Difference in generation task queuing | Queuing may occur during peak hours. | No queuing. |