Jianyi Wang
Jianyi Wang
I guess the code currently does not support v-sampling: https://github.com/Stability-AI/stablediffusion/blob/main/ldm/models/diffusion/ddpm.py#L920
Hi, I just test the NIQE algorithm, using RGB images. However, the results seem totally different from those in Matlab version. Is there anything wrong? (I convert BGR to YUV...
@MTlab Thanks for your project. But how to test?
因为这会导致agent以很诡异的姿势走
change the line https://github.com/XPixelGroup/BasicSR/blob/dd501350aee6c0b2af484150bfa7f7e8e1db0ab3/basicsr/data/degradations.py#L744 to `encode_param = [int(cv2.IMWRITE_JPEG_QUALITY), int(quality)]` may fix the problem.
The reason is that the video generation process is fixed to use ffmpeg and no results will be generated if your ffmpeg does not support x264 codec. You can change...
The 768 model should also work? I guess.
> Also I've noticed higher number of steps produces more blurred image. So 4 steps not only the fastest, it also has the best quality. 3 and less produce a...
Hi. Thx for your interest and glad to hear that. We are interested in developing a XL version. But I am currently struggling with my PhD projects and may not...