import gradio as gr
import numpy as np
import random
from PIL import Image
import spaces
from http import HTTPStatus
from urllib.parse import urlparse, unquote
from pathlib import PurePosixPath
import requests
import os
from diffusers import DiffusionPipeline
import torch
model_name = "Qwen/Qwen-Image"
pipe = DiffusionPipeline.from_pretrained(model_name, torch_dtype=torch.bfloat16)
pipe.to('cuda')
MAX_SEED = np.iinfo(np.int32).max
MAX_IMAGE_SIZE = 1440
# (1664, 928), (1472, 1140), (1328, 1328)
def get_image_size(aspect_ratio):
if aspect_ratio == "1:1":
return 1328, 1328
elif aspect_ratio == "16:9":
return 1664, 928
elif aspect_ratio == "9:16":
return 928, 1664
elif aspect_ratio == "4:3":
return 1472, 1140
elif aspect_ratio == "3:4":
return 1140, 1472
else:
return 1328, 1328
@spaces.GPU(duration=60)
def infer_diffusers(
prompt,
negative_prompt=" ",
seed=42,
randomize_seed=False,
aspect_ratio="16:9",
guidance_scale=4,
num_inference_steps=50,
progress=gr.Progress(track_tqdm=True),
):
if randomize_seed:
seed = random.randint(0, MAX_SEED)
width, height = get_image_size(aspect_ratio)
print("Generating for prompt:", prompt)
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")
return image, seed
@spaces.GPU(duration=65)
def infer(
prompt,
negative_prompt=" ",
seed=42,
randomize_seed=False,
aspect_ratio="16:9",
guidance_scale=4,
num_inference_steps=50,
progress=gr.Progress(track_tqdm=True),
):
if randomize_seed:
seed = random.randint(0, MAX_SEED)
width, height = get_image_size(aspect_ratio)
print("calling with prompt: %s" % prompt)
rsp = ImageSynthesis.call(api_key=os.environ.get("DASH_API_KEY"),
model="qwen-image",
prompt=prompt,
negative_prompt=negative_prompt,
n=1,
seed=seed,
guidance_scale=guidance_scale,
steps=num_inference_steps,
size=f'{width}*{height}'
) # support 1664*928, 1472*1140, 1328*1328, 1140*1472, 928*1664
print('response: %s' % rsp)
if rsp.status_code == HTTPStatus.OK:
# 在当前目录下保存图片
for result in rsp.output.results:
file_name = PurePosixPath(unquote(urlparse(result.url).path)).parts[-1]
with open('./%s' % file_name, 'wb+') as f:
f.write(requests.get(result.url).content)
print(f'save image to {file_name}')
else:
print('sync_call Failed, status_code: %s, code: %s, message: %s' %
(rsp.status_code, rsp.code, rsp.message))
image = Image.open(file_name)
return image, seed
examples = [
"A capybara wearing a suit holding a sign that reads Hello World",
"""A young girl wearing school uniform stands in a classroom, writing on a chalkboard. The text "Introducing Qwen-Image, a foundational image generation model that excels in complex text rendering and precise image editing" appears in neat white chalk at the center of the blackboard. Soft natural light filters through windows, casting gentle shadows. The scene is rendered in a realistic photography style with fine details, shallow depth of field, and warm tones. The girl's focused expression and chalk dust in the air add dynamism. Background elements include desks and educational posters, subtly blurred to emphasize the central action. Ultra-detailed 32K resolution, DSLR-quality, soft bokeh effect, documentary-style composition""",
"Realistic still life photography style: A single, fresh apple resting on a clean, soft-textured surface. The apple is slightly off-center, softly backlit to highlight its natural gloss and subtle color gradients—deep crimson red blending into light golden hues. Fine details such as small blemishes, dew drops, and a few light highlights enhance its lifelike appearance. A shallow depth of field gently blurs the neutral background, drawing full attention to the apple. Hyper-detailed 8K resolution, studio lighting, photorealistic render, emphasizing texture and form."
]
css = """
#col-container {
margin: 0 auto;
max-width: 1024px;
}
"""
with gr.Blocks(css=css) as demo:
with gr.Column(elem_id="col-container"):
# gr.Markdown('')
gr.Markdown('
')
gr.Markdown("[Learn more](https://github.com/QwenLM/Qwen-Image) about the Qwen-Image series. Try on [Qwen Chat](https://chat.qwen.ai/), or [download model](https://huggingface.co/Qwen/Qwen-Image) to run locally with ComfyUI or diffusers.")
with gr.Row():
prompt = gr.Text(
label="Prompt",
show_label=False,
placeholder="Enter your prompt",
container=False,
)
run_button = gr.Button("Run", scale=0, variant="primary")
result = gr.Image(label="Result", show_label=False)
with gr.Accordion("Advanced Settings", open=False):
negative_prompt = gr.Text(
label="Negative prompt",
max_lines=1,
placeholder="Enter a negative prompt",
visible=False,
)
negative_prompt = gr.Text(
label="Negative prompt",
max_lines=1,
placeholder="Enter a negative prompt",
visible=False,
)
seed = gr.Slider(
label="Seed",
minimum=0,
maximum=MAX_SEED,
step=1,
value=0,
)
randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
with gr.Row():
aspect_ratio = gr.Radio(
label="Aspect ratio(width:height)",
choices=["1:1", "16:9", "9:16", "4:3", "3:4"],
value="16:9",
)
with gr.Row():
guidance_scale = gr.Slider(
label="Guidance scale",
minimum=0.0,
maximum=7.5,
step=0.1,
value=4.0,
)
num_inference_steps = gr.Slider(
label="Number of inference steps",
minimum=1,
maximum=50,
step=1,
value=50,
)
gr.Examples(examples=examples, inputs=[prompt], outputs=[result, seed], fn=infer, cache_examples=False, cache_mode="lazy")
gr.on(
triggers=[run_button.click, prompt.submit],
fn=infer_diffusers,
inputs=[
prompt,
negative_prompt,
seed,
randomize_seed,
aspect_ratio,
guidance_scale,
num_inference_steps,
],
outputs=[result, seed],
)
if __name__ == "__main__":
demo.launch()