Innovate Futures @ Benji
patreon
(ComfyUI Workflow)Sonic + Kokoro TTS + Flux Image Gen
🕑 Added 2025-02-13 20:53:38 +0000 UTCBased on the Sonic ComfyUI https://www.youtube.com/watch?v=8DTAAOhRx3Q created this workflow.
https://www.patreon.com/posts/sonic-in-comfyui-122186721
Saw some stupid ignorance on YouTube saying, Oh, this is not good, blah blah...
It's true; recently, I listened to Joe Rogan podcast. He said lots of commenters on YouTube are actually losers. Really, I did experience that when I posted on YouTube.
Anyway, back to the topic, this workflow demonstrates how to use an image as input from a Flux. There are a lot of ways to do it. And I added an upscaler on the last group.
For the audio input, I put the load audio node for your audio file if not using TTS.
Updated:
I did 2 types of upscaler
Upscale By Model
Ultimate SD Upscale
Attached files below; enjoy :)
Comments
Coby Christiansen
Hey Benjji ur the man! I look up to you broz.
Benjamin Law
Yes, like other folks config, you can remove the Kokoro TTS and use Load Audio if this error happen.
Lex
Hello Sir received this error on the workflow SONIC_PreData 'NoneType' object is not subscriptable What do you think. thank you
Benjamin Law
Yea sorry, I was trying some Database thing on that web server. You can come to our Discord , many cool people, brilliant people in there too.
Denn_Fi_
Hi Benji, your website thefuturethinker.org seems to have problems! This was ther shortest way to get in touch with you. Best D
Benjamin Law
I mixed with other AI video to do animated. Usually, img2vid I use LTX for open source way. Kling , Runway for Pro way.
Benjamin Law
Thanks
Clayfacer
Great workflow thanks for this compilation.
HestoySeghuro .
animated where?
