Fed up?
Models too big filling up your storage, nodes a nightmare to install with constant errors, GPU RAM always running out and crashing halfway? RunningHub solves it all! With RTX 4090 24G VRAM in the cloud, all models and nodes pre-integrated, just sign up with Gmail to get 1000 free credits and run your workflow instantly — smooth, fast, and hassle-free!
Workflow Link:https://www.runninghub.ai/workflow/1966336112350441473?inviteCode=rh-v1153
This workflow can generate dialogues for either a single speaker or two speakers, using [S1] and [S2] to distinguish who is speaking. It also allows emotion and tone control through three methods: text description, numerical variables, and audio reference—making it really fun to use.
It’s recommended to try it out on RunningHUB first, since installing the INDEX nodes can be a bit complicated.
In the workflow zip file, I’ve included the voice files of Jinx and Sett from League of Legends, for experimental use with the workflow only. Have fun~
Description
Comments (2)
Incompatible with ComfyUI, requires to update transformers, update have no effect.
"The checkpoint you are trying to load has model type qwen3 but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date."
It seems like this issue might be related to your Python version or environment setup. Unfortunately, I’m not able to assist directly with that part. You could try running it on my online workflow first to see if it works there. As for the issue on your local machine, I’m afraid you’ll need to rely on ChatGPT for troubleshooting. Sorry about that!