only for sfx?
is there some way to make it only output like just sounds? like that old stable audio model?
i've been trying some prompts but not really a good result
i'm using in on Wan2gp if it matters
Yes, that's possible. This model is not a typical tts model so there is a some learning curve to prompting it well. People have been complaining that it doesn't really work. But the secret to getting it to work is tuning all the parameters just right so they work in concert with the prompt. We'll try to post a prompting guide on our website in the coming days. We'll be releasing a ComfyUI version week. If you want to get updates, please join our discord here https://discord.com/invite/xC5TSxTNPu.
Yes, that's possible. This model is not a typical tts model so there is a some learning curve to prompting it well. People have been complaining that it doesn't really work. But the secret to getting it to work is tuning all the parameters just right so they work in concert with the prompt. We'll try to post a prompting guide on our website in the coming days. We'll be releasing a ComfyUI version week. If you want to get updates, please join our discord here https://discord.com/invite/xC5TSxTNPu.
thanks for responding, i mean the model itself it's working well! (in wan2gp, i'm not savy enough for comfy yet) and wanted to goof around to only generate sounds, maybe i need to use a native workflow itself instead of wgp, i look forward for that tutorial