thwgithub
thwgithub
@Kinyugo @noamelata Hi，everyone. I have implemented the experiment on butterflies dataset(len=1000), which the result trained 10000 steps(max_step) is better, FID5=0.2028 with five steps sampling, and FID1 =0.2165 with one step...
I suspect there is something wrong with the structure of Unet, but i am not sure about it.
@Kinyugo Hello, thank you for your instant reply. I found a error in your codes as follows ： in the timesteps_schedule function, def timesteps_schedule(....): num_timesteps = final_timesteps**2 - initial_timesteps**2 #...
@Kinyugo However, this trivial error should not obscure the concision aesthetics of your code, this is an excellent work. As far as i know , your code is first one...
@Kinyugo Thanks for sharing your findings with me. I have not pay attention to the paper "[Analyzing and Improving the Training Dynamics of Diffusion Models]". Regarding the issue #7 ,...
@Kinyugo Hello, I have successfully incorporated the ncsn++ network(https://github.com/openai/consistency_models_cifar10/blob/main/jcm/models/ncsnpp.py) into your consistency model. Unfortunately, I did not still achieve good results. At the same time, I looked repeatedly your codes...
----- 原始邮件 ----- 发件人：Kinyugo ***@***.***> 收件人：Kinyugo/consistency_models ***@***.***> 抄送人：thwgithub ***@***.***>, Comment ***@***.***> 主题：Re: [Kinyugo/consistency_models] Reproducing CIFAR10 result from paper: Improved Techniques For Consistency Training (Issue #5) 日期：2023年12月26日 18点03分 Awesome. Ping me...
@Kinyugo I have sent it to email. Did not you receive it?