pip install xfuser

 import torch
 from diffusers import StableDiffusion3Pipeline

 from xfuser import xFuserArgs, xDiTParallel
 from xfuser.config import FlexibleArgumentParser
 from xfuser.core.distributed import get_world_group

 def main():
+    parser = FlexibleArgumentParser(description="xFuser Arguments")
+    args = xFuserArgs.add_cli_args(parser).parse_args()
+    engine_args = xFuserArgs.from_cli_args(args)
+    engine_config, input_config = engine_args.create_config()

     local_rank = get_world_group().local_rank
     pipe = StableDiffusion3Pipeline.from_pretrained(
         pretrained_model_name_or_path=engine_config.model_config.model,
         dtype=torch.float16,
     ).to(f"cuda:{local_rank}")
    
# do anything you want with pipeline here

+    pipe = xDiTParallel(pipe, engine_config, input_config)

     pipe(
         height=input_config.height,
         width=input_config.height,
         prompt=input_config.prompt,
         num_inference_steps=input_config.num_inference_steps,
         output_type=input_config.output_type,
         generator=torch.Generator(device="cuda").manual_seed(input_config.seed),  # or "mps", "xpu", "cpu"
     )

+    if input_config.output_type == "pil":
+        pipe.save("results", "stable_diffusion_3")

if __name__ == "__main__":
    main()

torchrun --nproc_per_node=8 ./inference.py --model models/FLUX.1-dev --data_parallel_degree 2 --ulysses_degree 2 --ring_degree 2 --prompt "A snowy mountain" "A small dog" --num_inference_steps 50