From 7b7be7d8b33dcd99866024e830e05907f087c095 Mon Sep 17 00:00:00 2001 From: sayakpaul Date: Thu, 20 Mar 2025 17:24:13 +0530 Subject: [PATCH] add a note about max_timesteps --- docs/source/en/api/pipelines/sana_sprint.md | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/docs/source/en/api/pipelines/sana_sprint.md b/docs/source/en/api/pipelines/sana_sprint.md index 482ef3c2c99d..8db4576cf579 100644 --- a/docs/source/en/api/pipelines/sana_sprint.md +++ b/docs/source/en/api/pipelines/sana_sprint.md @@ -18,7 +18,7 @@ LoRA -[SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation](https://huggingface.co/papers/2503.09641) from NVIDIA and MIT HAN Lab, by Junsong Chen, Shuchen Xue, Yuyang Zhao, Jincheng Yu, Sayak Paul, Junyu Chen, Han Cai, Enze Xie, Song Han +[SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation](https://huggingface.co/papers/2503.09641) from NVIDIA, MIT HAN Lab, and Hugging Face by Junsong Chen, Shuchen Xue, Yuyang Zhao, Jincheng Yu, Sayak Paul, Junyu Chen, Han Cai, Enze Xie, Song Han The abstract from the paper is: @@ -84,6 +84,10 @@ image = pipeline(prompt).images[0] image.save("sana.png") ``` +## Setting `max_timesteps` + +Users can tweak the `max_timesteps` value for experimenting with the visual quality of the generated outputs. The default `max_timesteps` value was obtained with an inference-time search process. For more details about it, check out the paper. + ## SanaSprintPipeline [[autodoc]] SanaSprintPipeline