Phil Wang

@rom1504 i say just copy into a subfolder Laion has already become an integral dataset to companies large and small. realistically everyone out there will just be training on it...

Already?! 🙏💯🎉

I was going to add training scripts for all the components tomorrow morning ... 😂

I think for the clip guided generation, you will still need a decoder conditioned on the clip image embedding, tho you can probably get away with a small resolution net...

@xiankgx 👋 are you working with Laion? you should, because they have a humongous (and smaller test) datasets

> Thank you for your work! I've modified your code to work with the original CLIP and got the training scripts. What is a good small dataset to test this...

ohh got it, looks like they finally got it to be pip installable. I'll take a look tomorrow at an adapter!

ok, the plan will be to automatically use the openai clip by setting a `use_openai_clip` on both the `Decoder` and `DiffusionPrior`, which will allow researchers to skip the first step...

> > > Thank you for your work! I've modified your code to work with the original CLIP and got the training scripts. What is a good small dataset to...

nice! I'll refactor to use it maybe next week :)