luser350
luser350
Hi, I want to train a model on 1k resolution. Since it is mentioned in the readme that FFHQ images were resized to 512x512. Does your model support 1K resolution...
Hi, I have been trying to train [ffhqr](https://github.com/skylab-tech/ffhqr-dataset) at 1024 x 1024 resolution. Here are the changes in my config file. I am using [ffhq](https://github.com/NVlabs/ffhq-dataset) as low-quality images. ```python class...
Hi @guyuchao the current VQFR model is trained on 512x512 FFHQ but I want to train it on 1024x1024. There are some questions I would like to ask before proceeding...
Hi, thanks for sharing your awesome work. I want to train DiffBIR on 1024 x1024 [ffhqr dataset](https://github.com/skylab-tech/ffhqr-dataset). I want to use [ffhq dataset](https://github.com/NVlabs/ffhq-dataset/tree/master) as input (1024x024). I have modified [codeformer](https://github.com/XPixelGroup/DiffBIR/blob/main/dataset/codeformer.py)...
Hi, I am training a face-retouching model using FFHQ and FFHQR datasets. Since I am training on 1024x1024 my batch size is 2. Here is the sample output  As...
@zsyOAOA how to train FFHQ on 1024x1024 resolution. I have checked the [swinIR_ffhq512](https://github.com/zsyOAOA/DifFace/blob/master/configs/training/swinir_ffhq512.yaml) the img_size : 64 (at line8).
Are there any accuracy gains if you train GFPGAN with multiple GPUs?
Hi, thanks for sharing your great work. I have a dataset with ground truth (prepared by myself). Your training script is for the WB dataset. Please guide me, on what...
Hi, Thanks for sharing your great work. I have a paired dataset of glare and no glare glasses. To my understanding of the paper, I need to train Stage 1...