search

kohya-ss / sd-scripts

Apache License 2.0
5.33k stars 881 forks source link

Has anyone already done finetuning a flux model（not lora)? Why is the image quality of the model generated by my finetune so poor? #1681

Open xiaohaier123 opened 1 month ago

xiaohaier123 commented 1 month ago

I pulled the code from the sd3 branch, used the flux_train.py script, and fine-tuned it based on my own 130,000 images, but the inference images became of poor quality, blurry, and the human body was deformed（3w step）.

kelisiya commented 1 month ago

Could you share the current training script? I am trying to fine-tune with less data, and I will share the relevant results here.

voytez commented 1 month ago

having the same issue fine tune with sd3 branch, wasn't sure if it settings or low steps number 1000 on 10 images but tried DreamBooth on SD1.5 with those settings before and results were good

AbstractEyes commented 1 month ago

I've had good luck just finetuning through lora and merging.

kohya-ss commented 1 month ago

having the same issue fine tune with sd3 branch, wasn't sure if it settings or low steps number 1000 on 10 images but tried DreamBooth on SD1.5 with those settings before and results were good

Unfortunately SD1.5/2/SDXL training with sd3 branch is not tested yet. Please use main branch for them.

ymzlygw commented 3 weeks ago

flux is a distillation model not for fine-tune, but lora works well. Maybe distillation model can't be used for base model fine-tune?