This workflow combines Wan 2.2 SVI Pro with HuMo. It allows you to create long speech sequences with non-repeating animations (Which, for example, is a problem with Infinite Talk). You can load an image and an audio file with voice and then animate them. It's also possible to continue an existing video or, for example, extend another video with an audio speech sequence, as in my example video.
For anyone who, for whatever reason, can't find the link for the missing nodes in the workflow (the big red box), here's the link: https://github.com/drozbay/WanExperiments
You'll need to install it yourself using "git clone"
Installation is at your own risk. However, I had no problems with Linux.
IMPORTANT:
If you want to expand an video with an talking sequence!
Let's assume you have an SVI video that you want to expand. The video lasts 20 seconds. After 20 seconds the character should speak. Now you have to load an audio file where there is no talking sound for the first 20 seconds (music is filtered out) and start your voice sequence after these 20 seconds. This workflow cannot synchronize existing videos. It can only expand the whole thing after.
Description
FAQ
Comments (12)
Could you upload your final video with metadata? Lip syncing isn't working in my workflow and I am using all the files and images from the same girl you provided. By the way Fantastic workflow, thank you.
That's funny because everything you need is in the zip file. What do you want to try? IA2V or VA2V?
@Thalion7 I'm trying to replicate the video you uploaded using I2V. The final output in the SVI chain in my workflow gives me the video of the girl moving over the car and her voice in the background, but her lips aren't moving. I had to edit the voice file to make it shorter because the workflow's default duration is 11 seconds @ 24fps, so I edited the voice audio to match the 11 seconds. I think there's something I'm not triggering.
@Thalion7 I tested the video input and somehow the lip sync works although the lips barely move, but if the source comes from the svi generation, the lips don't move at all.
@abeslu425 Not that we're talking past each other. Let's assume you have an SVI video that you want to expand. The video lasts 20 seconds. After 20 seconds the character should speak. Now you have to load an audio file where there is no sound for the first 20 seconds and start your voice sequence after these 20 seconds. This workflow cannot synchronize existing videos. It can only expand the whole thing after, for example, 20 seconds.
custom node not showing up in , ComfyUI Manager
@userx11xz Read the red boxes. You have to install it manually.
@Thalion7 Could you share a link to the instructions of installing it? There's not Github repo on those custom node. Only a github page.
Interesting workflow. I have a lot of red, but no missing nodes 🤷♂️
If it is WanExperiments, you have to install it separatly. The red "help" boxes should answer your question. And upgrade ComfyUI to the last version.
From where are you people installing the missing custom nodes called Wanx. For sure you can't install it via Manager. The author talks of installing it manually but looking it up takes you to a github.io page. https://wanx-troopers.github.io/svi.html and not some github repo.
Asking the community since the author doesn't seem to be interested in replying this particular query.
Here you go. The link is in the workflow, too. https://github.com/drozbay/WanExperiments