Open tumurzakov opened 1 year ago
Hi, we do not finetune DreamBooth/LoRA on the input video frames. We simply replace the Stable Diffusion with the personalized model downloaded from CivitAi for different styles.
After you published your paper, I conducted experiments involving fine-tuning a U-Net in conjunction with a motion module, and it yielded promising results for style transfer. Prior to this, I explored LoRA, but the outcomes were less than impressive. I divide the samples into segments of video_length (16 frames) and then train the U-Net with the motion module on these segments as a single batch.
I have observed that the motion module, equipped with a single transformer block, possesses enough capability to capture simple motions. However, it does face limitations in memorizing shapes due to the absence of convolutional layers. Fine-tuning the U-Net, on the other hand, empowers it to retain both textures and shapes.
你好,我想问一下 MagicEdit 预计什么时候能上线使用呢
MagicEdit 哪个时候可以使用到呢?
As I understand you making following steps:
Can you share hyperparameters of finetuning?