Qwen Image Lightning
简介
核心亮点
- 原生支持中文,提示词理解精准且地道
- 极速出图能力,显著降低推理等待时间
- Apache-2.0 协议,对商业应用非常友好
- 适用于实时生成、快速原型设计等场景
使用方法
# 安装 Hugging Face transformers
pip install transformers torch
# 使用 transformers 加载模型
from transformers import AutoModel, AutoTokenizer
model = AutoModel.from_pretrained("lightx2v/Qwen-Image-Lightning")
tokenizer = AutoTokenizer.from_pretrained("lightx2v/Qwen-Image-Lightning")
Hugging Face 下载
我们推荐使用命令行或者 Hugging Face Hub SDK 来进行模型的下载。
操作指引:在下载前,请先通过如下命令安装 huggingface_hub:
pip install -U huggingface_hub
命令行下载
下载完整模型库
huggingface-cli download lightx2v/Qwen-Image-Lightning
下载单个文件到指定本地文件夹(以下载 config.json 到当前路径下 ./dir 目录为例)
huggingface-cli download lightx2v/Qwen-Image-Lightning config.json --local-dir ./dir
SDK 下载
# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('lightx2v/Qwen-Image-Lightning')
Git 下载
请确保 lfs 已经被正确安装
git lfs install
git clone https://huggingface.co/lightx2v/Qwen-Image-Lightning
如果您希望跳过 lfs 大文件下载,可以使用如下命令
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/lightx2v/Qwen-Image-Lightning
模型文件托管在 Hugging Face Hub,使用 HF CLI / SDK / Git 直接下载,不经过本站。
PyTorch / Transformers 使用
安装 Transformers
pip install -U transformers torch
模型加载和推理
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained('lightx2v/Qwen-Image-Lightning')
tokenizer = AutoTokenizer.from_pretrained('lightx2v/Qwen-Image-Lightning')
模型下载
我们推荐使用命令行或者 ModelScope SDK 来进行模型的下载。
操作指引:在下载前,请先通过如下命令安装 ModelScope:
pip install modelscope
命令行下载
下载完整模型库
modelscope download --model lightx2v/Qwen-Image-Lightning
下载单个文件到指定本地文件夹(以下载 README.md 到当前路径下 dir 目录为例)
modelscope download --model lightx2v/Qwen-Image-Lightning README.md --local_dir ./dir
SDK 下载
# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('lightx2v/Qwen-Image-Lightning')
Git 下载
请确保 lfs 已经被正确安装
git lfs install
git clone https://www.modelscope.cn/lightx2v/Qwen-Image-Lightning.git
如果您希望跳过 lfs 大文件下载,可以使用如下命令
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 快速开发
下载并安装 ModelScope library
pip install "modelscope[audio,cv,nlp,multi-modal,science]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html
模型加载和推理
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
p = pipeline('text-generation', 'lightx2v/Qwen-Image-Lightning')
完整文档
---
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)
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")