Ligong Han

Sorry, I do not have a good alternative solution for now, but a workaround is that I can host a temporary http server using our school machine. Because of limited...

Hi @ashawkey, thanks for your swift reply! FYI, I found Latent-Nerf implemented $w(t)$ as $\sqrt{\bar{\alpha}_t}(1-\bar{\alpha}_t)$, https://github.com/eladrich/latent-nerf/blob/f49ecefcd48972e69a28e3116fe95edf0fac4dc8/src/stable_diffusion.py#L144 Now it makes sense. Thank you! In my case where I use SDS to...

Hi @thuanz123 thanks for your interest! The code can be found here: https://github.com/KunpengSong/styleganfusion

Thanks! Very interesting results! Briefly tried this with NeRF model, not sure if it is clearly helpful. Here are some results I got: Hamburger, with `-O` option, baseline  with...

This is what I tried: https://github.com/phymhan/stable-dreamfusion/blob/dcd7fc0557d32d611fc228f890bdaf1245880395/nerf/sd.py#L129 Basically I use `noise_pred` to get the current estimate of x0, then perform one step gradient descent on `noise_pred` to make it closer to...

Yep, that is weird. Will do more tests on this.

Hi @ljzycmd, thanks for your feedback and for conducting a quick test! Looking forward to seeing future developments in the awesome project!

Hi @xu-pping thanks for your interest in our work! Unfortunately, we don't have V100 in our lab. But you are welcome to try if you have the GPU.

Hey @githubnemo, great to see this moving forward! Really appreciate the thoughtful feedback and your willingness to consider integrating this into PEFT. We’re from the same team at [Red Hat...