Andreas

Results 10 comments of Andreas

text generation webui llama generating random nonsense

same here

text generation webui llama generating random nonsense

delete what and where?

The context is not updating - the AI does not remember

I'm having the same issue

RuntimeError: Failed to load audio: ffmpeg error (see stderr output for detail)

same issue

RuntimeError: Failed to load audio: ffmpeg error (see stderr output for detail)

Can y'all test this and see if it works? Worked for me. :) https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/issues/711#issue-1795198576

Error with directML

bump

I can't find the path where the models are stored, where are the automatically downloaded models stored?

It downloaded to this directory on my pc `C:\Users\USERNAME\.cache\huggingface\hub\models--stabilityai--stable-cascade-prior\snapshots\621fc2ddab5500e57079e716c15358a25b649090`

会不会针对FLUX2.进行模型的释放呢？

> Z-image is much better than Flux2, so we prioritize adapting to it and can enjoy sub second generation I don't believe one is better than the other, but Flux2...

会不会针对FLUX2.进行模型的释放呢？

> > I agree. Also, focusing on a turbo distilled model with relatively small paramaters seems odd, it's already incredibly fast and runs on midrange consumer cards. > > Flux...

Sage Attention 3 public release and need to add a node to select attention type on steps

How did you make it work on qwen?