pi-Qwen-Image

20
license:apache-2.0
by
Lakonik
Image Model
OTHER
New
0 downloads
Early-stage
Try on Hugging FaceAdd to Compare
Edge AI:
Mobile
Laptop
Server
Unknown
Mobile
Laptop
Server
Quick Summary

Distilled 4-step Qwen-Image models proposed in the paper: pi-Flow: Policy-Based Few-Step Generation via Imitation Distillation Hansheng Chen 1 , Kai Zhang 2 ,...

Code Examples

4-NFE GM-Qwen (GMFlow Policy, Recommended)pythonpytorch
import torch
from lakonlab.models.diffusions.schedulers import FlowMapSDEScheduler
from lakonlab.pipelines.pipeline_piqwen import PiQwenImagePipeline

pipe = PiQwenImagePipeline.from_pretrained(
    'Qwen/Qwen-Image',
    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-Qwen-Image',
    subfolder='gmqwen_k8_piid_4step',
    target_module_name='transformer')
pipe.scheduler = FlowMapSDEScheduler.from_config(  # use fixed shift=3.2
    pipe.scheduler.config, shift=3.2, use_dynamic_shifting=False, final_step_size_scale=0.5)
pipe = pipe.to('cuda')

out = pipe(
    prompt='Photo of a coffee shop entrance featuring a chalkboard sign reading "Ļ€-Qwen Coffee šŸ˜Š $2 per cup," with a neon '
           'light beside it displaying "Ļ€-通义千问". Next to it hangs a poster showing a beautiful Chinese woman, '
           'and beneath the poster is written "eā‰ˆ2.71828-18284-59045-23536-02874-71352".',
    width=1920,
    height=1080,
    num_inference_steps=4,
    generator=torch.Generator().manual_seed(42),
).images[0]
out.save('gmqwen_4nfe.png')
4-NFE DX-Qwen (DX Policy)textpytorch
import torch
from lakonlab.models.diffusions.schedulers import FlowMapSDEScheduler
from lakonlab.pipelines.pipeline_piqwen import PiQwenImagePipeline

pipe = PiQwenImagePipeline.from_pretrained(
    'Qwen/Qwen-Image',
    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-Qwen-Image',
    subfolder='dxqwen_n10_piid_4step',
    target_module_name='transformer')
pipe.scheduler = FlowMapSDEScheduler.from_config(  # use fixed shift=3.2
    pipe.scheduler.config, shift=3.2, use_dynamic_shifting=False, final_step_size_scale=0.5)
pipe = pipe.to('cuda')

out = pipe(
    prompt='Photo of a coffee shop entrance featuring a chalkboard sign reading "Ļ€-Qwen Coffee šŸ˜Š $2 per cup," with a neon '
           'light beside it displaying "Ļ€-通义千问". Next to it hangs a poster showing a beautiful Chinese woman, '
           'and beneath the poster is written "eā‰ˆ2.71828-18284-59045-23536-02874-71352".',
    width=1920,
    height=1080,
    num_inference_steps=4,
    generator=torch.Generator().manual_seed(42),
).images[0]
out.save('dxqwen_4nfe.png')

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.