<s>v2. training. but it doesn't work</s><s>I don't know why.</s><ol><li><s>To increase the diversity of target frames, I increased the number of frame types in the dataset.</s></li></ol><s>Previously, it was fixed at 81 frames, but this time it was trained at 33, 49, 65, 81, 97, 113, and 129 frames.</s><ol><li><s>Lora rank has been lowered to 32.</s></li></ol><s>Previously, it would have been 64.</s><ol><li><s>The front and back padding areas have been increased from 4 frames to 8 frames each.</s></li></ol><s>4 frames are not enough in some case.</s><s>(This occurred when using a lot of different loras.)</s><hr />As we all know, using the End Frame feature in wan 2.2 causes degradation near the last frame.I couldn't stand this.So I tried to making Lora.This is my first attempt, but I think it worked better than I expected, so I'm uploading it to share.This is what Lora does.Creates same extra frames at the beginning and end of the video.It was trained with a dataset of 4 starting frames + loop video for 5-77 frames + 8 subsequent frames.For the FLF2V.The intention is to be able to complete the loop video even by cutting out the frames that VAE distorts.After creating a video, additional work is required to select and cut out duplicate frames.I hope it works as intended.

wan 2.2 padl00p

high - 2500steps.low - 1000steps.An error occurred at step 1000 due to incorrect settings.When learn again, It will start from step 1.I'll update when have a chance.

Files with SHA256: 9d2f837301ce94fd28f6ed43f695ccce31bb24bc400493ead83bd7f13bf3c141