MDT
MDT copied to clipboard
Masked Diffusion Transformer is the SOTA for image synthesis. (ICCV 2023)
Hi authors. I'm trying to merge your model n setup with a different repo [here](https://github.com/JuliaWolleb/diffusion-anomaly/tree/main). I'm trying to solve the errors at test time when I run the classifier_sample_known.py file....
Hi, I am curious about your MDTv2_s2 settings. What is your lr_anneal_steps? Should I set it to 0? And how can I control the training steps? For example, how can...
when cal FID.... we nedd reference batch. how can we get reference batch? can you offer code? thank you very much
Hi @gasvn, I would like to train a model using my custom dataset. However, I noticed that the current training process only supports using image IDs. Is there a way...
Hello, I would like to sample images based on a specific label. For example, if I only want to sample images with label 9, I want to condition the sampling...
Hello, I have a question regarding the forward and backward loop. I'm trying to update it to the Lightning style, but I'm having trouble understanding a particular part. Could you...