Roi Bar-On issues

Repositories
Issues
Comments

Results 1 issues of


                                            Roi Bar-On

SDS loss

According to section 2 in the paper, `epshat = pred_noise_text + guidance_scale * (pred_noise_text - pred_noise_uncond)`. While it seems that in the implementation in [sd.py](https://github.com/ashawkey/stable-dreamfusion/blob/main/nerf/sd.py#L95), it's assigned as: `epshat =...