CycleNet

CycleNet copied to clipboard

Has anyone reproduced this method？

2

I tried the summer2winter model，but the results are out of expectations，the parameters as follows: process(input_image, 'winter', 'summer', num_samples=1, image_resolution=512, ddim_st eps=100, guess_mode=False, strength=1.0, scale=9.0, seed=1000, eta=1.0, denoise_strength=0.5) input image: ![iTerm2...

wzr1201

hello, great work! How to train the model based on Scene/Object-Level Manipulation dataset or ManiCups dataset? @Mars-tin @Roihn @h6kplus @SihanXU Or how to sample based on pre-trained models?

pokameng

Hi, great job. as mentioned, will you release the full training code of winter to summer?

wzr1201

Thanks for great work! I followed the example provided with cfill dataset. -> https://github.com/sled-group/CycleNet/blob/main/docs/train.md I found 2 differences with the original works. 1. Training with batch size = 1 cost...

yryun

great job! I have a question that is ok that make images as condition instead of text? for example, as for original [dataset](https://huggingface.co/datasets/fusing/fill50k) the dataset structure is like this: ```...

sapkun

I am using 4 GPUS A6000 to train the model based on cyclefill50, and the epoch is now 6. However, the result is not good:  @Mars-tin @SihanXU

pokameng