DiT Prompt-conditioning model instead of class-conditioning

"We provide a training script for DiT in train.py. This script can be used to train class-conditional DiT models, but it can be easily modified to support other types of conditioning."

Does anyone have a clue about modifying the model to the prompt-conditioning model?

Mar 05 '24 20:03 anarabiyev

Can you use self-trained data to generate images?

Mar 10 '24 09:03 wuzelei123

Can you use self-trained data to generate images?

I didn't understand what you meant. My purpose is to modify this model so that I can feed prompt as input instead of class labels.

Mar 10 '24 09:03 anarabiyev

The error occurred when I used the weight file generated during the official code training in sample.py. Like： RuntimeError: CUDA error: device-side assert triggered Compile with TORCH_USE_CUDA_DSA to enable device-side assertions. What parameters did you modify during training?

Mar 11 '24 02:03 wuzelei123

I haven't modified any parameters yet, I am trying to analyze code and find a clue where to start.

Mar 11 '24 08:03 anarabiyev

okok，thank you. I've just solved my problem.

Mar 11 '24 08:03 wuzelei123

@wuzelei123 Hello, I have the same problem, how did you solve it。The error occurred when I used the weight file generated during the official code training in sample.py. Like： RuntimeError: CUDA error: device-side assert triggered Compile with to enable device-side assertions. What parameters did you modify during training?TORCH_USE_CUDA_DSA

Nov 04 '24 05:11 twinkleyang1