pytorch-CycleGAN-and-pix2pix VS SPADE

Click to Learn more...

pix2pix (https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix) - This is a PyTorch implementation of the pix2pix algorithm for image-to-image translation. Given a set of images, the model can learn to generate a new image from a different domain that is similar to the input image.

Using junyanz/pytorch-CycleGAN-and-pix2pix as a basis for pix2pix, I applied the same blending method to fix seams. It essentially takes an input image and generates an output. The results depend on the paired training data. In this case, each map (height, roughness, etc.) is a separate checkpoint and had to be trained on paired training data with the diffuse as the input and the respective map as the output.

Code for https://arxiv.org/abs/1611.07004 found: https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix

pix2pix algorithm is used for translating Civ6Maps to heightmaps. Synthesized terrain was rendered in blender.

https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix

I'm working on creating a face-to-wojak model using PyTorch CycleGan/Pix2Pix [0] and found some of my outputs to be outrageous yet somehow relatable. People are into it so thought I'd share on HN

[0] https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix

GauGAN (https://github.com/NVlabs/SPADE) - This is a PyTorch implementation of the SPADE (SPatially-Adaptive (DE)normalization) algorithm, which can generate images from segmentation maps. You can use it to generate realistic images of objects, landscapes, and other scenes.

It is open source, if that helps. Here is a GitHub link.

Generating photorealistic landscapes from brush strokes: Semantic Image Synthesis with Spatially-Adaptive Normalization

This look like an AI image synthesized with Nvidia's SPADE.

Spade Nvidia