QwenLM/Qwen-Image

1. Make sure your transformers>=4.51.3 (Supporting Qwen2.5-VL)

2. Install the latest version of diffusers

pip install git+https://github.com/huggingface/diffusers

Qwen-Image-2512 (for Text to Image generation, better character realism/texture quality)

We recommand use the latest prompt enhancing tools for Qwen-Image-2512, please check src/examples/tools/prompt_utils_2512.py

from diffusers import QwenImagePipeline
import torch
# Load the pipeline
if torch.cuda.is_available():
    torch_dtype = torch.bfloat16
    device = "cuda"
else:
    torch_dtype = torch.float32
    device = "cpu"

pipe = QwenImagePipeline.from_pretrained("Qwen/Qwen-Image-2512", torch_dtype=torch_dtype).to(device)

# Generate image
prompt = '''A 20-year-old East Asian girl with delicate, charming features and large, bright brown eyes—expressive and lively, with a cheerful or subtly smiling expression. Her naturally wavy long hair is either loose or tied in twin ponytails. She has fair skin and light makeup accentuating her youthful freshness. She wears a modern, cute dress or relaxed outfit in bright, soft colors—lightweight fabric, minimalist cut. She stands indoors at an anime convention, surrounded by banners, posters, or stalls. Lighting is typical indoor illumination—no staged lighting—and the image resembles a casual iPhone snapshot: unpretentious composition, yet brimming with vivid, fresh, youthful charm.'''

negative_prompt = "低分辨率，低画质，肢体畸形，手指畸形，画面过饱和，蜡像感，人脸无细节，过度光滑，画面具有AI感。构图混乱。文字模糊，扭曲。"


# Generate with different aspect ratios
aspect_ratios = {
    "1:1": (1328, 1328),
    "16:9": (1664, 928),
    "9:16": (928, 1664),
    "4:3": (1472, 1104),
    "3:4": (1104, 1472),
    "3:2": (1584, 1056),
    "2:3": (1056, 1584),
}

width, height = aspect_ratios["16:9"]

image = pipe(
    prompt=prompt,
    negative_prompt=negative_prompt,
    width=width,
    height=height,
    num_inference_steps=50,
    true_cfg_scale=4.0,
    generator=torch.Generator(device="cuda").manual_seed(42)
).images[0]

image.save("example.png")

Qwen-Image-Edit-2511 (for Image Editing, Multiple Image Support and Improved Consistency)

import os
import torch
from PIL import Image
from diffusers import QwenImageEditPlusPipeline
from io import BytesIO
import requests

pipeline = QwenImageEditPlusPipeline.from_pretrained("Qwen/Qwen-Image-Edit-2511", torch_dtype=torch.bfloat16)
print("pipeline loaded")

pipeline.to('cuda')
pipeline.set_progress_bar_config(disable=None)
image1 = Image.open(BytesIO(requests.get("https://qianwen-res.oss-accelerate-overseas.aliyuncs.com/Qwen-Image/edit2511/edit2511input.png").content))
prompt = "这个女生看着面前的电视屏幕，屏幕上面写着“阿里巴巴”"
inputs = {
    "image": [image1],
    "prompt": prompt,
    "generator": torch.manual_seed(0),
    "true_cfg_scale": 4.0,
    "negative_prompt": " ",
    "num_inference_steps": 40,
    "guidance_scale": 1.0,
    "num_images_per_prompt": 1,
}
with torch.inference_mode():
    output = pipeline(**inputs)
    output_image = output.images[0]
    output_image.save("output_image_edit_2511.png")
    print("image saved at", os.path.abspath("output_image_edit_2511.png"))

<details> <summary> Previous Version </summary>

Qwen-Image (for Text-to-Image)

The following contains a code snippet illustrating how to use the model to generate images based on text prompts:

from diffusers import DiffusionPipeline
import torch

model_name = "Qwen/Qwen-Image"

# Load the pipeline
if torch.cuda.is_available():
    torch_dtype = torch.bfloat16
    device = "cuda"
else:
    torch_dtype = torch.float32
    device = "cpu"

pipe = DiffusionPipeline.from_pretrained(model_name, torch_dtype=torch_dtype).to(device)

positive_magic = {
    "en": ", Ultra HD, 4K, cinematic composition.", # for english prompt
    "zh": ", 超清，4K，电影级构图." # for chinese prompt
}

# Generate image
prompt = '''A coffee shop entrance features a chalkboard sign reading "Qwen Coffee 😊 $2 per cup," with a neon light beside it displaying "通义千问". Next to it hangs a poster showing a beautiful Chinese woman, and beneath the poster is written "π≈3.1415926-53589793-23846264-33832795-02384197".'''

negative_prompt = " " # Recommended if you don't use a negative prompt.


# Generate with different aspect ratios
aspect_ratios = {
    "1:1": (1328, 1328),
    "16:9": (1664, 928),
    "9:16": (928, 1664),
    "4:3": (1472, 1104),
    "3:4": (1104, 1472),
    "3:2": (1584, 1056),
    "2:3": (1056, 1584),
}

width, height = aspect_ratios["16:9"]

image = pipe(
    prompt=prompt + positive_magic["en"],
    negative_prompt=negative_prompt,
    width=width,
    height=height,
    num_inference_steps=50,
    true_cfg_scale=4.0,
    generator=torch.Generator(device="cuda").manual_seed(42)
).images[0]

image.save("example.png")

Qwen-Image-Edit (for Image Editing, Only Suppo

…