RuiQuan-Li

For the Flux model, after performing fine-tuning/DreamBooth using flux_train.py, the generated images are corrupted.

1

**The training parameters are as follows:** `accelerate launch --mixed_precision bf16 --num_cpu_threads_per_process 1 flux_train.py --pretrained_model_name_or_path ./flux1-dev.safetensors --clip_l ./clip_l.safetensors --t5xxl ./t5xxl_fp16.safetensors --ae ./ae.safetensors --save_model_as safetensors --sdpa --persistent_data_loader_workers --max_data_loader_n_workers 1 --seed 42 --gradient_checkpointing...