Fangzhenxuan
Fangzhenxuan
Thank you for sharing your excellent work!! In your test code, it seens we only need to provide benchmark HR test images, but how could I test on a real-world...
https://github.com/greatlog/UnpairedSR/blob/771312ee2bd4d3c8b84621e115fcf0151c050548/codes/config/PDM-SR/archs/deg_arch.py#L207 其中 noise 的shape为[B, 1, 1, 1],而 x 的shape为[B, 3, 32, 32] 请问一下作者生成的noise对LR图像的每一个通道和每一个pixel都是相同的吗?
Thank you for your outstanding work! I am very interested in the work with SD-Turbo. May I ask if its training is the same as SD-2.1? Do you only replace...
Thanks for your excellent work. When I run generate_vqgan_data.py in training CFW, I find it takes more than 20 days to generate 100K paired training data (30 sec per image...
The default value of n_samples is 2, while the batch size is 1 in test phase. What is the function of text_init = ['']*opt.n_samples