LokiXun comments

Results 5 comments of


                                            LokiXun

Question in paper: For ablation study "Compare ControlNet and LAControlNet"

> Yes, we keep the architecture of ControlNet unchanged and trained it from scratch on ImageNet1k. Got it! May I ask another question. For Ablation study of "finetuning StableDiffusion v2",...

What's the right parameter to eval on REDS4 x4 SR data? Using the old-movie parameter result in Garbage...

> Have you managed to get a better result? I used their default parameters on my dataset and the results are really bad. > > If not, do you possibly...

Missing Head and Tail Frame when inference a whole video.

Thanks for relpy. 😃 Seems like only use one frame to inference for the initial frame & end frame respectively? How could model use the temporal information when only input...

Missing Head and Tail Frame when inference a whole video.

Hello, I test the commited code. It does work and return such error when inference the initial frame. ``` File "xxx/FMA-Net-main/model.py", line 618, in forward F, KD, f_Y, f, anchor_D...

Missing Head and Tail Frame when inference a whole video.

hello~is there any solution for this issue?