Lakonik/pi-FLUX.1

pi-Flow: Policy-Based Flow Models

Distilled 4-step and 8-step FLUX.1 models proposed in the paper:

pi-Flow: Policy-Based Few-Step Generation via Imitation Distillation
Hansheng Chen¹, Kai Zhang², Hao Tan², Leonidas Guibas¹, Gordon Wetzstein¹, Sai Bi^2
1Stanford University, ²Adobe Research
[arXiv] [Code] [pi-Qwen Demo🤗] [pi-FLUX Demo🤗]

Usage

Please first install the official code repository.

We provide diffusers pipelines for easy inference. The following code demonstrates how to sample images from the distilled FLUX models.

4-NFE GM-FLUX (GMFlow Policy)

Note: For the 8-NFE version, replace gmflux_k8_piid_4step with gmflux_k8_piid_8step and set num_inference_steps=8.

import torch
from diffusers import FlowMatchEulerDiscreteScheduler
from lakonlab.pipelines.piflux_pipeline import PiFluxPipeline

pipe = PiFluxPipeline.from_pretrained(
    'black-forest-labs/FLUX.1-dev',
    torch_dtype=torch.bfloat16)
adapter_name = pipe.load_piflow_adapter(  # you may later call `pipe.set_adapters([adapter_name, ...])` to combine other adapters (e.g., style LoRAs)
    'Lakonik/pi-FLUX.1',
    subfolder='gmflux_k8_piid_4step',
    target_module_name='transformer')
pipe.scheduler = FlowMatchEulerDiscreteScheduler.from_config(  # use fixed shift=3.2
    pipe.scheduler.config, shift=3.2, use_dynamic_shifting=False)
pipe = pipe.to('cuda')

out = pipe(
    prompt='A portrait photo of a kangaroo wearing an orange hoodie and blue sunglasses standing in front of the Sydney Opera House holding a sign on the chest that says "Welcome Friends"',
    width=1360,
    height=768,
    num_inference_steps=4,
    generator=torch.Generator().manual_seed(42),
).images[0]
out.save('gmflux_4nfe.png')

4-NFE DX-FLUX (DX Policy)

import torch
from diffusers import FlowMatchEulerDiscreteScheduler
from lakonlab.pipelines.piflux_pipeline import PiFluxPipeline

pipe = PiFluxPipeline.from_pretrained(
    'black-forest-labs/FLUX.1-dev',
    policy_type='DX',
    policy_kwargs=dict(
        segment_size=1 / 3.5,  # 1 / (nfe - 1 + final_step_size_scale)
        shift=3.2),
    torch_dtype=torch.bfloat16)
adapter_name = pipe.load_piflow_adapter(  # you may later call `pipe.set_adapters([adapter_name, ...])` to combine other adapters (e.g., style LoRAs)
    'Lakonik/pi-FLUX.1',
    subfolder='dxflux_n10_piid_4step',
    target_module_name='transformer')
pipe.scheduler = FlowMatchEulerDiscreteScheduler.from_config(  # use fixed shift=3.2
    pipe.scheduler.config, shift=3.2, use_dynamic_shifting=False)
pipe = pipe.to('cuda')

out = pipe(
    prompt='A portrait photo of a kangaroo wearing an orange hoodie and blue sunglasses standing in front of the Sydney Opera House holding a sign on the chest that says "Welcome Friends"',
    width=1360,
    height=768,
    num_inference_steps=4,
    generator=torch.Generator().manual_seed(42),
).images[0]
out.save('dxflux_4nfe.png')

Citation

@misc{piflow,
      title={pi-Flow: Policy-Based Few-Step Generation via Imitation Distillation}, 
      author={Hansheng Chen and Kai Zhang and Hao Tan and Leonidas Guibas and Gordon Wetzstein and Sai Bi},
      year={2025},
      eprint={2510.14974},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2510.14974}, 
}