Your work is great but I have some issues with pretraining

[GZ-YourZY]

Since my application involves non-natural images, I aim to pre-train the model on a domain-specific dataset. However, I haven't found any relevant tutorials for this task. I would greatly appreciate it if the author could provide guidance or tutorials to help me accomplish this.

[PaulCouairon]

Thanks for your interest in our work! If you want to fine-tune the diffusion model on your own data you can refer to https://huggingface.co/blog/lora