Version 5.0 works with latest Comfy Handy Nodes 1.24
manually update if you dont see it in Manager by searching for "Handy Nodes"
cd <your custom nodes folder>
git clone https://github.com/trashkollector/TKNodes
Up to 4 prompts/images.
***** Works for Singing or Talking *****
How this works, supply an audio file, size does not matter as the workflow will chunk the audio.
It will then use alternating photos to keep video dynamic.
Audio now is chunked when there is silence in the audio for better transtion.
Please get Handy Nodes 1.1.5 from Manager.
Anyone with low VRAM change this. this tells the workflow to try use 12 second chunks.
Audio driven video using alternating speakers. See Podcast demo.
Please make sure to get the newest TK Handy Nodes version 1.1.0
Description
fixed the chunks so they have the clean audio.. in case you want to use a specific chunk and a few other minor things.
Minor change.
FAQ
Comments (2)
I checked 4.2, it didn't work too well, at one point it zoomed out and invented a whole new scenario, check the vid. I'm using the camera control static lora, but it didn't help apparently.
EDIT: I tried again, this time i added "The camera dollies forward very slowly towards her face." , the camera didn't actually do that, but it never hallucinate and did pretty well, as you can see in the new vid, and deleted the old vid now that it works fine.
Version 4.2, error getting file. I'm guessing the civitai transition hiccups are the cause. Here's hoping it'll be resolved soon!