train_text_to_image_sdxl training effect is very poor

[wzhiyuan2016]

I use DeepSpeed for training: train_text_to_image_sdxl.py
1.The data volume is 231 pieces
2. deepspeed json

3.Training Script

4.After training, use the training prompt words again，The generated effect is as follows:

May I ask everyone, what is the reason for the poor generation effect？

[a-r-r-o-w]

cc @sayakpaul

[sayakpaul]

This should be a discussion as there are far too many things that are unknown here.

General comments:

• How do the samples look like in the dataset?
• What is the resolution of the samples in the dataset?
• Have you tried overfitting a single image and checked the results?