Update app.py

app.py

@@ -1,6 +1,7 @@
 import gradio as gr
 import numpy as np
 import random
+import json
 
 from PIL import Image
 
@@ -20,23 +21,24 @@ pipe = DiffusionPipeline.from_pretrained(model_name, torch_dtype=torch.bfloat16)
 pipe.to('cuda')
 
 MAX_SEED = np.iinfo(np.int32).max
-MAX_IMAGE_SIZE = 1440
+#MAX_IMAGE_SIZE = 1440
 
+examples = json.loads(open("examples.json").read())
 
 # (1664, 928), (1472, 1140), (1328, 1328)
 def get_image_size(aspect_ratio):
     if aspect_ratio == "1:1":
-        return 1328, 1328
+        return 1920, 1920
     elif aspect_ratio == "16:9":
-        return 1664, 928
+        return 1920, 1080
     elif aspect_ratio == "9:16":
-        return 928, 1664
+        return 1080, 1920
     elif aspect_ratio == "4:3":
-        return 1472, 1140
+        return 1920, 1440
     elif aspect_ratio == "3:4":
-        return 1140, 1472
+        return 1440, 1920
     else:
-        return 1328, 1328
+        return 640, 640
 
 @spaces.GPU(duration=60)
 def infer_diffusers(
@@ -71,50 +73,7 @@ def infer_diffusers(
     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 {
@@ -124,7 +83,6 @@ css = """
 """
 
 
-
 with gr.Blocks(css=css) as demo:
     with gr.Column(elem_id="col-container"):
         # gr.Markdown('<div style="text-align: center;"><a href="https://huggingface.co/Qwen/Qwen-Image"><img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-Image/qwen_image_logo.png" width="400"/></a></div>')
@@ -147,13 +105,7 @@ with gr.Blocks(css=css) as demo:
                 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,
+                visible=True,
             )
 
             seed = gr.Slider(
@@ -168,7 +120,7 @@ with gr.Blocks(css=css) as demo:
 
             with gr.Row():
                 aspect_ratio = gr.Radio(
-                    label="Aspect ratio(width:height)",
+                    label="Image size (ratio, max dim 1920)",
                     choices=["1:1", "16:9", "9:16", "4:3", "3:4"],
                     value="16:9",
                 )
@@ -187,7 +139,7 @@ with gr.Blocks(css=css) as demo:
                     minimum=1,
                     maximum=50,
                     step=1,
-                    value=50, 
+                    value=35, 
                 )
 
         gr.Examples(examples=examples, inputs=[prompt], outputs=[result, seed], fn=infer, cache_examples=False, cache_mode="lazy")