ApplicationTemplates Library
Instances
Deploy InstanceMy Instances
Serverless
Deploy ServerlessMy Endpoints
Other
Image PrewarmNetwork VolumeJobsSettings
QUICK ACCESS
BillingPricing
docs
Docs
Back to Templates Library
Can't be used normally? Clickhereto let us know.
Comfyui:Wan2.1-t2v-14B
Favorite
Copy Link
Official template
novitalabs/comfyui:Wan2.1-t2v-14B
Updated time: 19 Jan 2026
README
Configuration

Run Wan2.1-t2v-14B on Novita AI

What is Wan2.1-t2v-14B

a comprehensive and open suite of video foundation models that pushes the boundaries of video generation. You can learn more information in Wan2.1's official repository.

Run Wan2.1-t2v-14B on Novita AI

Step 1: Console Entry Launch the GPU interface and select Get Started to access deployment management. image
Step 2: Package Selection Locate Wan2.1-t2v-14B in the template repository and begin installation sequence. image
Step 3: Infrastructure Setup Configure computing parameters including memory allocation, storage requirements, and network settings. Select Deploy to implement. image
Step 4: Review and Create Double-check your configuration details and cost summary. When satisfied, click Deploy to start the creation process. image
Step 5: Wait for Creation After initiating deployment, the system will automatically redirect you to the instance management page. Your instance will be created in the background. image
Step 6: Monitor Download Progress Track the image download progress in real-time. Your instance status will change from Pulling to Running once deployment is complete. You can view detailed progress by clicking the arrow icon next to your instance name. image
Step 7: Verify Instance Status Click the Logs button to view instance logs and confirm that the Comfyui service has started properly. image
Step 8: Environment Access Launch development space through Connect interface, then initialize Start Web Terminal. image

How to use

Template details

This template calls the Wan2.1-t2v-14B model through the Comfyui service and includes the Jupyter application. Comfyui and Jupyter services are both regulated through supervisor.

Process management

  • You can use supervisortl in the web terminal to manage the corresponding services. Here are some command usage demonstrations. More usage methods can be found in the official documentation. You can also view detailed information on the project website of this project. Here are some basic commands to use.
1# The status parameter is used to view the status of each managed process
2$ supervisorctl status
3# The stop, start, restart parameters followed by the service name are used to stop, start, or restart the specified service
4supervisorctl stop comfyui
5supervisorctl start comfyui
6supervisorctl restart comfyui
  • The startup script for Comfyui can be found in the /opt/supervisor directory. This template comfyui service is bound by default to the default 8188 port at address 0.0.0.0. You can use the python3 ~/ComfyUI/main.py -h command to view more detailed startup configurations. After changing the script, restart the comfyui service using the supervisorctl restart comfyui command .After ensuring that the Comfyui service status is running, you can access the Comfyui service again.
1# This command is used to view the startup script of the Comfyui service
2cat /opt/supervisor/comfyui.sh
3# This command is used to view various startup parameters of the Comfyui service
4python3 ~/ComfyUI/main.py -h
5# If you modify the startup script of Comfyui, you can use the following command to restart the Comfyui service
6supervisorctl restart comfyui

Demo

Step 1: Click on 'connection to HTTP server[Port 8188]' in the Connect interface,and you will enter the corresponding service. image
Step 2: Select the provided basic workflow for testing. image

Advanced Usage

You can learn detailed usage instructions in the official documentation of Comfyui.