Madhav Agarwal

@revoconner Hey! Did you able to train it on 512x512? Which dataset did you use for this resolution?

@fpandza Did you able to train the model with custom keypoints detected from a separate model? @AliaksandrSiarohin I want to replace the keypoints with some third-party model, like dlib. Can...

I am planning to use dlib for estimating the keypoints and use them to train a motion model. For every image, instead of training a unsupervised model for getting keypoints,...

Hi @AliaksandrSiarohin, In keypoint_detector.py, I made some changes to create a key-point map of [1,68,58,58] where each 58x58 matrix has all zeros except one. The location where dlib keypoint is...

Hi @AliaksandrSiarohin , Thanks for your suggestion. I set `equivariance_value: 0` and `equivariance_jacobian: 0`. The code starts working. The perceptual loss also starts reducing. I checked the visualization and it...

Can you confirm what is the image size for 20ms/50 FPS metric calculation ?

> I believe the problem comes from inconsistency when defining the return of the function, > > ``` > type(model.encode(imgs)) > Out[7]: torch.Tensor > > type(model.model.encode(imgs)) > Out[8]: dict >...

Hi @phizaz, Yes, I am looking for something similar. I need to reconstruct the image using the diffusion model. The conditioning i.e. z_sem should come from image feature space while...

1. I have an autoencoder that transfers an RGB image into a feature space. 2. Thanks for clarifying. 3. Pretrained DDIM: I was referring to the model generated using 'ffhq128_ddpm_130M'...