A workflow using the latest Index TTS 2.
The Index TTS 2 is a bit hard to install locally in comfyUI. So if you get stuck, you could check out my installation video first or try it online.
Free try out link: https://www.runninghub.ai/post/1966017826458865665
Video Instructions:
All the model details are within the workflow
The video generation is resource-heavy. If your local computer is unable to run this workflow or you just want to see how good the model is and check all the workflow parameter settings before downloading, please open the link above to run it online for free on RTX4090. Just click and run. No brain-racking local setup.
1000 credits upon signing in using the above link(One gen only takes about 10-30 credits), with an extra 100 credits on daily login.
Description
FAQ
Comments (5)
Your instructions seem great. The question is whether if one waits, there will be 'better' support for this TTS model in Comfy, without so many 'delicate' support library issues. In other words, will anyone code native support in the near future?
Thanks. The author said he was working on using emotion control words between the sentences. And about native comfyUI support, I have no info on that yet.
@blobby99 and if they did not die until now they still live happily together
I love this workflow. I wonder if its a posible instead of photo add 5s Video ?? So for example if voice is longer like 5s then will be generated from last frame of this 5s.
I just wish to add some small movement scene.
Hi, can You update this WF as its stop working. Probably bc new version od seedvr 2 upscale adn tts ??
