Sign In
homemodelsimagesvideospostsarticlesbountiestoolschallengeseventsupdatesshop

Wan14B in 1 click with workflows included - RunPod Template

168

HearmemanAI's Avatar

HearmemanAI

Apr 8, 2025

tool guide
comfyuirunpodrunpod templatebeginnervideo generation
Wan14B in 1 click with workflows included - RunPod Template

FOLLOWING MY RECENT UPDATE:

BEFORE deploying the template, please click additional filters and change CUDA version to 12.8

Deploy the template here (works with all CUDA 12.8 GPUs):
https://get.runpod.io/wan-template

Troubleshooting guide:
https://docs.google.com/document/d/1822H-x7AevWz2T_jzMu8-9e5UlQ-zrH0FhCFmQ6FtRc/edit?usp=sharing

CHANGELOG:

Edit June 19:

Added Self Forcing LoRA workflows

Edit June 4:

  • Added 60FPS Workflows for T2V/I2V

Edit June 1 (MASSIVE OVERHAUL):

  • Upgraded to CUDA 12.8 and Pytorch 2.8.0

  • MUCH faster downloads (template is ready in 5 minutes)

  • Added VACE 1.3B/14B workflow and models

  • Optimized some existing workflows

This video covers deploying a RunPod template that provides a complete local video generation package with Wan2.1 and ComfyUI with workflows included for T2V/I2V/ControlNet/VACE.

Remember to change the environment variables to True to download the models

For those of you who just want the workflows, please see my main profile for all my Wan workflows.

For all my other RunPod Templates:
https://docs.google.com/spreadsheets/d/1NfbfZLzE9GIAD5B_y6xjK1IdW95c14oS1JuIG9QihL8/edit?usp=sharing

ANYTHING BELOW IS OUTDATED

********************************************************************************************************

Edit April 30:

  • I have released an additional template designed for the RTX 5090, you can deploy it HERE

  • Added VACE video outpaint to both templates

Edit April 8:

  • Pushed a major update to the template, please refer to the README file (question mark icon) before deploying the template to understand the new environment variables.

Edit April 2:

  • Added Wan Fun support (New environment variables and added workflow)

Edit March 27:

  • Updated CUDA to 12.4

  • Added SageAttention and Triton installation (This will make the deployment SLOWER but generations much faster!, you can disable this in the environment variables)

  • Bypassed SLG on native workflows as it's currently not working

  • Added Power LoRA Loader to native workflows

Edit March 19:

  • I2V workflows now including multi LoRAs

  • Added Skip Layer Guidance nodes

  • Slightly modified the workflows to have an easy swap between Non Tiled/ Tiled VAE Decode

Edit March 11:

  • All workflows are now including LoRA support.

  • All workflows now support TeaCache and SageAttention

  • All model downloads are now using huggingface-cli, this enabled faster model downloads, I was able to get a template running in 5 minutes with full I2V and T2V model downloads!

Edit March 8:

  • Pushed some code changes that turn on video preview by default, videos will show as they generate so you can detect bad movement and abort.

  • Added automatic LoRA downloading using my CivitAI downloader
    Learn how to use it here: https://civitai.com/articles/12333

Edit March 3:
Updated the non-native workflows to support TeaCache – Image generation should now be faster!
The workflows that support TeaCache are

  • Wan_Video_Image2Video-Upscaling_FrameInterpolation

  • Wan_Video_Text2Video-Upscaling_FrameInterpolation

  • Wan_Video_Video2Video-Upscaling_FrameInterpolation

Also, Fixed Video2Video workflow

168

Comments