Udon

How can I get illustlation id of `Works based on this work`?

1

I'd like to get the illustration id in the `Works based on this work` Section. There is no information with an AppPixivAPI.illust_recommended function. Please let me know XD. https://www.pixiv.net/en/artworks/70502156

[Ask]multiple gpu

4

Hi NVlabs. Please tell me! When I want to use multiple GPUs with this code, how should I do?

About data inputs

2

Hi @fnzhan ! Thank you for providing your nice implementation. I have a question about inputs for networks, especially for a celeba edge case. Correspondence predictor is given RGB images...

Hi, @lyndonzheng! I used your pre-trained weights of [Places2_random](https://drive.google.com/open?id=1L4NAHQqyEJ_ANt4SfEP1hdEVdGrteu4L). But, a network generates poor results. Is the weight correctly trained? ![Uploading image.png…]()

Implementation for TensorRT

2

Hi, I guess that a reverse diffusion process can be performed fastly if an UNet implementation in this library can infer with [TensorRT](https://github.com/pytorch/TensorRT). Would you have the plan to implement...

Hi @pesser! Thank you for sharing the implementation of your wonderful work! I have questions about some techniques. Would you tell me these questions? I have used your pretrained celeba256...

About download of HDR-Eye dataset

1

Hi, @alex04072000 I'm sorry that this issue has nothing to do with your paper. I try to download HDR-Eye dataset using FTP https://www.epfl.ch/labs/mmspg/downloads/hdr-eye/ However, it seems that the server is...

Pretrained weight of upsampler of Places does not work well.

1

Hi, @raywzy I tried to use both FFHQ and Places2 pretrained weights of upsampler. However, the Upsampler's pretrained weight of Places does not have enough quality. We know that the...

Update generate.py

2

To avoid this error #3, I add this config for tf session. My environment + Tensoflow 1.15 + TensorLayer 1.11.1