News for hackers. Stuff that matters.

sahil_chaudhary

Dropping the batch size
Yeah the license issue is the only reason why I didn't release the weights yet.
I'm training a 65B model right now, also I believe you can use lora-alpaca to train on this data on a much smaller machine.
Given how many people are asking for the weights, I'm working to make them available now. So you'll be able to run them locally as well.
Yeah the weights did change.
All included it costs under 70$ for the 13B model. Training 65B now so will report what that will cost.
Interesting, in my experiments alpaca-lora performed worse but definitely possible that isn't the case generally.
Re:Reverse engineer Stable Diffusion images on Wednesday February 08, 2023 @05:06PM (#34716056)
That was an issue on my end, should be fine now
Re:Reverse engineer Stable Diffusion images on Wednesday February 08, 2023 @11:56AM (#34710892)
You can find my email on my HN profile
Re:Reverse engineer Stable Diffusion images on Wednesday February 08, 2023 @10:58AM (#34709869)
Ah yes, this model treats this purely as image captioning. The model isn't open source yet.
Re:Reverse engineer Stable Diffusion images on Wednesday February 08, 2023 @10:54AM (#34709806)
Nice, does this use clip-interrogator?
Re:Reverse engineer Stable Diffusion images on Wednesday February 08, 2023 @10:26AM (#34709325)
Glad you enjoy it! It hasn't been trained on non-generated images so is unpredictable when uploading a real photo, specially one with people in it

Older »