Overview

Qwen Image Lightning is a high-efficiency text-to-image model designed for developers who need to balance visual fidelity with low-latency inference. Unlike heavy diffusion models that require significant VRAM and long sampling times, this model is optimized for rapid generation, making it ideal for real-time applications, iterative prototyping, and scalable cloud deployments. It integrates easily into existing pipelines via standard API endpoints and is released under the permissive Apache-2.0 license, allowing for full commercial flexibility. Whether you are building dynamic UI assets or automating content generation, Qwen Image Lightning offers a streamlined alternative to slower, resource-intensive image generators without sacrificing prompt adherence.

Highlights

Rapid inference speeds for real-time image generation
Permissive Apache-2.0 license for commercial use
Low latency suitable for scalable production environments
Strong prompt adherence for precise visual control

Usage

Install

# Install Hugging Face transformers
pip install transformers torch

SDK Usage

# Load model with transformers
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("lightx2v/Qwen-Image-Lightning")
tokenizer = AutoTokenizer.from_pretrained("lightx2v/Qwen-Image-Lightning")

Hugging Face Download

We recommend downloading the model via the Hugging Face CLI or Hub SDK.

Guidance：Before downloading, install huggingface_hub with:

Guidance

pip install -U huggingface_hub

CLI Download

Download the full repository

huggingface-cli download lightx2v/Qwen-Image-Lightning

Download a single file to a local folder (e.g. config.json into ./dir)

huggingface-cli download lightx2v/Qwen-Image-Lightning config.json --local-dir ./dir

See the official docs for more CLI options

SDK Download

# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('lightx2v/Qwen-Image-Lightning')

Git Download

Make sure git-lfs is installed first

Git Download

git lfs install
git clone https://huggingface.co/lightx2v/Qwen-Image-Lightning

To skip LFS large-file downloads, use:

Skip LFS

GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/lightx2v/Qwen-Image-Lightning

Model files are hosted on the Hugging Face Hub — download directly via HF CLI / SDK / Git, not through this site.

PyTorch / Transformers Usage

Install Transformers

pip install -U transformers torch

Load the model and run inference

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('lightx2v/Qwen-Image-Lightning')
tokenizer = AutoTokenizer.from_pretrained('lightx2v/Qwen-Image-Lightning')

Model Download

We recommend downloading the model via the ModelScope CLI or SDK.

Guidance：Before downloading, install ModelScope with:

Guidance

pip install modelscope

CLI Download

Download the full repository

modelscope download --model lightx2v/Qwen-Image-Lightning

Download a single file to a local folder (e.g. README.md into ./dir)

modelscope download --model lightx2v/Qwen-Image-Lightning README.md --local_dir ./dir

See the docs for more CLI options

SDK Download

# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('lightx2v/Qwen-Image-Lightning')

Git Download

Make sure git-lfs is installed first

Git Download

git lfs install
git clone https://www.modelscope.cn/lightx2v/Qwen-Image-Lightning.git

To skip LFS large-file downloads, use:

Skip LFS

GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/lightx2v/Qwen-Image-Lightning.git

ModelScope 模型页直接下载模型文件；无需将模型文件放在本站服务器。

Notebook Quickstart

Install the ModelScope library

pip install "modelscope[audio,cv,nlp,multi-modal,science]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html

Load the model and run inference

from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

p = pipeline('text-generation', 'lightx2v/Qwen-Image-Lightning')

Full Documentation

来源: HuggingFace

---
license: apache-2.0
language:

en

zh

base_model:

Qwen/Qwen-Image

pipeline_tag: text-to-image
tags:

Qwen-Image

distillation

LoRA

lora

library_name: diffusers
---

Please refer to Qwen-Image-Lightning github to learn how to use the models.

use with diffusers 🧨:

make sure to install diffusers from main (pip install git+https://github.com/huggingface/diffusers.git)

code

from diffusers import DiffusionPipeline, FlowMatchEulerDiscreteScheduler
import torch 
import math
From https://github.com/ModelTC/Qwen-Image-Lightning/blob/342260e8f5468d2f24d084ce04f55e101007118b/generate_with_diffusers.py#L82C9-L97C10
scheduler_config = {
    "base_image_seq_len": 256,
    "base_shift": math.log(3),  # We use shift=3 in distillation
    "invert_sigmas": False,
    "max_image_seq_len": 8192,
    "max_shift": math.log(3),  # We use shift=3 in distillation
    "num_train_timesteps": 1000,
    "shift": 1.0,
    "shift_terminal": None,  # set shift_terminal to None
    "stochastic_sampling": False,
    "time_shift_type": "exponential",
    "use_beta_sigmas": False,
    "use_dynamic_shifting": True,
    "use_exponential_sigmas": False,
    "use_karras_sigmas": False,
}
scheduler = FlowMatchEulerDiscreteScheduler.from_config(scheduler_config)
pipe = DiffusionPipeline.from_pretrained(
    "Qwen/Qwen-Image", scheduler=scheduler, torch_dtype=torch.bfloat16
).to("cuda")
pipe.load_lora_weights(
    "lightx2v/Qwen-Image-Lightning", weight_name="Qwen-Image-Lightning-8steps-V1.0.safetensors"
)
prompt = "a tiny astronaut hatching from an egg on the moon, Ultra HD, 4K, cinematic composition."
negative_prompt = " "
image = pipe(
    prompt=prompt,
    negative_prompt=negative_prompt,
    width=1024,
    height=1024,
    num_inference_steps=8,
    true_cfg_scale=1.0,
    generator=torch.manual_seed(0),
).images[0]
image.save("qwen_fewsteps.png")