VACE Wan2.1 Video2Video | ComfyUI Installation Guide
Added 2025-04-11 04:00:38 +0000 UTC
🎓Beginner Tutorial: https://youtu.be/ufLMEQMeQDY
Before proceeding with installation, ensure you have:
ComfyUI installed (Tutorial)
A compatible GPU (NVIDIA with at least 8GB, other GPUs might work but it's not guaranteed)
Download
Video Model: Place inside ComfyUI\models\diffusion_models
rename to: "vace_preview_fp32.safetensors"
VAE: Place inside ComfyUI\models\vae
Text encoder: Place inside ComfyUI\models\text_encoders
🚀Advanced Tutorial: https://www.patreon.com/posts/advanced-video-2-127430452
*Workflows attached
💡 Need Help?
Consider upgrading your Patreon membership! Members get access to private support channels, where I’ll personally assist as much as I can to help you solve any problems.
🔗 https://discord.gg/b2jg5JgYgz
Comments
it gave me generation once did everything but now it keeps stopping at video combine. it heeps stopping . tried it in 3 different device. same issue. please help
editor pc
2025-08-26 10:35:51 +0000 UTCYou might need to install it manually using the command window, i put instructions on that under the comfyui installation video
MDMZ
2025-08-23 08:57:42 +0000 UTCi cant see the manager button or anything on the right side
editor pc
2025-08-23 08:47:34 +0000 UTCwhat type of issues ?
MDMZ
2025-08-18 08:51:35 +0000 UTCI'm having issues from the output 😕
Nagarajan S
2025-08-12 11:26:45 +0000 UTCcheck the logs, it could be running slowly in the background or running errors
MDMZ
2025-08-07 02:28:48 +0000 UTCwhen I run it it gets to the WanVideo Sampler and then just goes idle
J
2025-08-05 16:24:07 +0000 UTCyou dont have to rename it, just make sure you select the correct model file from the node, the name doesnt matter
MDMZ
2025-06-20 06:36:21 +0000 UTCI am using Comfy workflow on ThinkDiffusion. The issue is that it does not allow me to upload a file larger than 2GB from my computer. The video model file to be renamed to "vace_preview_fp32.safetensors" is 6.7GB. So, I cannot rename it and upload. The only way is to copy the file over to ThinkDiffusion via a URL. But there is no option to rename the file with this option. Any workaround?
Marcus Lam
2025-06-20 06:13:59 +0000 UTCthanks for the idea
MDMZ
2025-05-05 04:25:58 +0000 UTCCan you do a tutorial for video to video but with specific anime character lora? Would be fantastic
kally
2025-05-04 13:00:24 +0000 UTCdid you try playing with the prompts? and don't drop the resolution too low
MDMZ
2025-05-02 16:45:57 +0000 UTCI have got it working, but my results look so bad. they are nowhere near as clean as yours - I have tried a bunch of different settings / samplers and videos / images, but it always looks like soup. any suggestions? (im on a 3060 with 12GB - not getting any memory errors)
malcolm sutherland
2025-05-02 16:02:50 +0000 UTCHelp!!! Please.........WanVideoVACEEncode shape '[41, 66, 8, 120, 8]' is invalid for input of size 21254400
shawn huang
2025-04-24 02:33:27 +0000 UTCKeep getting "WanVideoModelLoader Invalid WanVideo model selected" error
Rob Shepps
2025-04-23 12:57:59 +0000 UTC
![MeineKraft [64x] Resource Pack - Fanmade](https://xaiju.com/istorage/3923.jpg)
