SD3 different inference result using sd3_minimal_inference.py and diffusers

Using sd3_minimal_inference.py and diffusers to inference open source sd3 model can get totally different result, is it because of the scheduler? it seems that you use your own-written scheduler rather than the scheduler from diffusers.

Start by reproducing the different inference results with sd3_minimal_inference.py and diffusers using the open source SD3 model. Compare the scheduler behavior and configuration in both paths, then document the confirmed cause and the conditions under which the results match.

Written by the indexing model from the issue text.