theboat · HackerTrans

2 года назадdiscuss

I love how this comment proves the need for audio2audio. I initially read it as sarcastic, but now I can't tell if it's actually sincere.

theboat

2 года назадdiscuss

does this work for diffusion models, e.g. stable diffusion xl?

theboat

2 года назадdiscuss

looks neat. it would help if you hosted the demo apps rather than expecting the user to install and run them themselves to get a feel for it

https://github.com/hyperdiv/hyperdiv-apps/tree/main

theboat

2 года назадdiscuss

I didn't see this in the blog post, but did you train this from scratch or finetune an existing base model?

If from scratch, quite impressive that the model is capable of understanding natural language prompts (English presumably) from such a small, targeted training set.

comments