Views
No views yet
FuseDiTPipeline in our codebase to run inference:1import torch
2from diffusion.pipelines import FuseDiTPipeline
3pipeline = FuseDiTPipeline.from_pretrained("/path/to/pipeline/").to("cuda")
4image = pipeline(
5 "your prompt",
6 width=512,
7 height=512,
8 num_inference_steps=25,
9 guidance_scale=6.0,
10 use_cache=True,
11)[0][0]
12image.save("test.png")1@article{tang2025exploringdeepfusion,
2 title={Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis},
3 author={Bingda Tang and Boyang Zheng and Xichen Pan and Sayak Paul and Saining Xie},
4 year={2025},
5 journal={arXiv preprint arXiv:2505.10046},
6}