SANA-Sprint

Install

pip install "libreyolo[gen]"

The gen extra installs diffusers, transformers and accelerate. SANA-Sprint loads as the diffusers SanaSprintPipeline, which needs diffusers 0.38.0 or later. Importing LibreGen imports none of them; they load on first use.

Generation runs on a CUDA GPU or on Apple silicon through MPS. device="auto" picks CUDA, then MPS, then the CPU, where the pipeline loads in fp32 and image generation is not practical.

Predict

from libreyolo import LibreGen # Needs a CUDA GPU or Apple silicon (MPS); generation is not practical on CPU.model = LibreGen("sana-sprint-0.6b")   # weights download on first useresult = model("a red fox sleeping in fresh snow", seed=0) result.save("fox.png")                 # the PNG also records prompt, seed and settingsprint(result.generated.array.shape)    # (1024, 1024, 3)

# Saves four images as .png under runs/generate/predict.libreyolo generate prompt="a red fox sleeping in fresh snow" model=sana-sprint-0.6b seed=0 n=4

from libreyolo import LibreGen model = LibreGen("sana-sprint-0.6b") result = model("a red fox sleeping in fresh snow", imgsz=(768, 1024))  # height, widthresult = model("a red fox sleeping in fresh snow", steps=4)            # more sampling stepsresult = model("a red fox sleeping in fresh snow", guidance=3.0) # Two prompts, two images each (seeds 0 and 1), written to runs/generate/predict.results = model(    ["a red fox sleeping in fresh snow", "a lighthouse on a rocky coast"],    seed=0,    n=2,    save=True,)

from libreyolo import LibreGen model = LibreGen("sana-sprint-0.6b")result = model("a red fox sleeping in fresh snow", seed=0) g = result.generatedprint(g.array.shape, g.array.dtype)   # (1024, 1024, 3) uint8, RGBprint(g.prompt, g.seed)               # what to pass to make it againprint(g.params)                       # model, imgsz, steps, guidance g.image.save("fox.jpg")               # a PIL imageprint(result.summary())               # one JSON-ready row

One prompt with n=1 returns a Results; a list of prompts or n > 1 returns a flat list in prompt order, and stream=True a generator. A string is always a prompt, never a path. result.generated is a GeneratedImage: array is the (H, W, 3) uint8 RGB image and image the same image as a PIL.Image, prompt the text, seed the integer that reproduces it, and params the model, imgsz and every setting in effect, defaults included. result.save(path) writes the image, and a PNG also stores prompt, seed and params as JSON in a libreyolo text chunk. result.plot() returns the image. save=True writes each image to a new runs/generate/predict folder per call, the file named after its index, prompt and seed; output_path names the file instead, for one prompt with n=1.

The first call downloads about 7.7 GB at a pinned revision, with nothing gated and no Hugging Face login, from Efficient-Large-Model/Sana_Sprint_0.6B_1024px_diffusers into weights/LibreSanaSprint0.6b/. Only the pipeline's component folders are fetched. LibreGen(path) loads a local directory that holds a SanaSprintPipeline in the diffusers layout instead, such as an offline copy or a fine-tune made with upstream tooling. sana-sprint is an alias of sana-sprint-0.6b.

A seed, with the same model and settings, gives the same image. Image i of a prompt uses seed + i, and every prompt in a list starts from the same seed. Without a seed, a fresh one is drawn for each prompt and recorded in result.generated.seed. The seed drives a random generator on the CPU, so the starting noise is the same on every device; the image can still differ across devices and precisions by numerical error.

Image-conditioned generation is not available yet: source= raises NotImplementedError.

Settings

Every setting has a default, so all are optional. A name the model does not have raises TypeError and lists the supported ones.

The constructor takes device, dtype and offload. dtype="auto" is bf16 on CUDA (fp16 on a GPU without bf16), bf16 on MPS from macOS 14, and fp32 on the CPU and on older macOS; "bf16", "fp16" and "fp32" force one. offload=True keeps idle pipeline components off the GPU; it needs CUDA and raises on any other device. model.pipeline is the loaded diffusers SanaSprintPipeline, for anything the LibreGen call does not cover.

Export

Export is not implemented: the model is a sampling loop over several networks, and LibreYOLO has no exportable graph contract for that yet (ADR 0030 in the library). export(), train() and val() raise NotImplementedError. train(data=...) is reserved for fine-tuning on captioned images, and val(data=...) for generation metrics on a captioned image set.

Licensing

Citation

@misc{chen2025sana-sprint,
      title={SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation},
      author={Junsong Chen and Shuchen Xue and Yuyang Zhao and Jincheng Yu and Sayak Paul and Junyu Chen and Han Cai and Song Han and Enze Xie},
      year={2025},
      eprint={2503.09641},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2503.09641},
    }