I am currently training the SD3.5 model (LORA) based on SimpleTuner framework. The size of my image is 512*512. During the training process, I enabled the flux_schedule_auto_shift. I found that this ...
🎬 The first method that adapts text-to-video DiTs to diverse video editing tasks in a video-free scheme. Easy Training 🚀: With only 100-250 image paired data and minimal computational cost (< 20 ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results