Nicholas Bardy
Nicholas Bardy
Give them time to fix mistakes. The release just happened there is a lot to get right.
This also adds model checkpointing now.
Context Deadline exceeding. Need to sort this flake out first. Then will soak overnight again.
Found out how to soak a shit ton of jobs of circle. About 30 here, running 70 more: https://app.circleci.com/pipelines/github/wandb/client-ng?branch=tests%2Fall_media_types
I'll squash and re commit this with an example.
Agreed. It's easy enough to just document how to add to the multimethods. But, I'm thinking it would be nice to write a helper function and possibly rewrite some of...
`dromni/nerfstudio` I ended up finding a docker image. I think this is probably the better way to do it. > I also don't think we to install the [editable version](https://github.com/modal-labs/modal-examples/pull/724/files#diff-bfb14c16c6f7a0f93aa27d394e670a613b76a3ab6c9c6d4d6bc195e61deff0c9R45-R49)...
Looks like the checklist is a little out of date seems @patil-suraj is already stated on T5. This looks like a good place for me to start. Train improved VQGANs...
Can look into setting up some eval sets as well. - [ ] Collect different prompts for intermediate evaluations (Can reuse the prompts for dalle-mini, parti-prompts).
Has anyone tried this? I feel like in theory training a LORA on the Sona Sprit weights with the standard DDIM should still work. But haven't had a chance to...