Update app.py

app.py

@@ -1,154 +1,76 @@
 import gradio as gr
-import numpy as np
-import random
+import openvino.runtime as ov
+from optimum.intel.openvino import OVStableDiffusionPipeline
 
-# import spaces #[uncomment to use ZeroGPU]
-from diffusers import DiffusionPipeline
-import torch
+model_id = "HelloSun/chilloutmix_NiPrunedFp32Fix-openvino"
 
-device = "cuda" if torch.cuda.is_available() else "cpu"
-model_repo_id = "stabilityai/sdxl-turbo"  # Replace to the model you would like to use
+# 確保這些是有效的尺寸
+HIGH = 512
+WIDTH = 512
 
-if torch.cuda.is_available():
-    torch_dtype = torch.float16
-else:
-    torch_dtype = torch.float32
+pipe = OVStableDiffusionPipeline.from_pretrained(model_id)
 
-pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
-pipe = pipe.to(device)
-
-MAX_SEED = np.iinfo(np.int32).max
-MAX_IMAGE_SIZE = 1024
-
-
-# @spaces.GPU #[uncomment to use ZeroGPU]
-def infer(
-    prompt,
-    negative_prompt,
-    seed,
-    randomize_seed,
-    width,
-    height,
-    guidance_scale,
-    num_inference_steps,
-    progress=gr.Progress(track_tqdm=True),
-):
-    if randomize_seed:
-        seed = random.randint(0, MAX_SEED)
-
-    generator = torch.Generator().manual_seed(seed)
+negative_prompt = "(worst quality, low quality, lowres), zombie, interlocked fingers,"
 
+def infer(prompt, negative_prompt):
     image = pipe(
         prompt=prompt,
         negative_prompt=negative_prompt,
-        guidance_scale=guidance_scale,
-        num_inference_steps=num_inference_steps,
-        width=width,
-        height=height,
-        generator=generator,
+        width=WIDTH,  # 使用 WIDTH
+        height=HIGH,  # 使用 HIGH
+        guidance_scale=7.5,
+        num_inference_steps=30,
+        num_images_per_prompt=1,
     ).images[0]
-
-    return image, seed
-
+    return image
 
 examples = [
-    "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
-    "An astronaut riding a green horse",
-    "A delicious ceviche cheesecake slice",
+    "Sailor Chibi Moon, Katsura Masakazu style",
+    "1girl, silver hair, symbol-shaped pupils, yellow eyes, smiling, light particles, light rays, wallpaper, star guardian, serious face, red inner hair, power aura, grandmaster1, golden and white clothes",
+    "A cute kitten, Tinkle style.",
+    "(illustration, 8k CG, extremely detailed),(whimsical),catgirl,teenage girl,playing in the snow,winter wonderland,snow-covered trees,soft pastel colors,gentle lighting,sparkling snow,joyful,magical atmosphere,highly detailed,fluffy cat ears and tail,intricate winter clothing,shallow depth of field,watercolor techniques,close-up shot,slightly tilted angle,fairy tale architecture,nostalgic,playful,winter magic,(masterpiece:2),best quality,ultra highres,original,extremely detailed,perfect lighting,",
 ]
 
 css = """
 #col-container {
     margin: 0 auto;
-    max-width: 640px;
+    max-width: 520px;
 }
 """
 
+power_device = "CPU"
+
 with gr.Blocks(css=css) as demo:
     with gr.Column(elem_id="col-container"):
-        gr.Markdown(" # Text-to-Image Gradio Template")
-
+        gr.Markdown(f"""
+        # Disty0/SoteMixV3 {HIGH}x{WIDTH}
+        Currently running on {power_device}.
+        """)
+        
         with gr.Row():
-            prompt = gr.Text(
+            prompt_input = gr.Text(
                 label="Prompt",
                 show_label=False,
                 max_lines=1,
                 placeholder="Enter your prompt",
                 container=False,
-            )
-
-            run_button = gr.Button("Run", scale=0, variant="primary")
-
+            )         
+            run_button = gr.Button("Run", scale=0)
+        
         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,
-            )
-
-            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():
-                width = gr.Slider(
-                    label="Width",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,  # Replace with defaults that work for your model
-                )
+        gr.Examples(
+            examples=examples,
+            fn=infer,
+            inputs=[prompt_input],
+            outputs=[result]
+        )
 
-                height = gr.Slider(
-                    label="Height",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,  # Replace with defaults that work for your model
-                )
-
-            with gr.Row():
-                guidance_scale = gr.Slider(
-                    label="Guidance scale",
-                    minimum=0.0,
-                    maximum=10.0,
-                    step=0.1,
-                    value=0.0,  # Replace with defaults that work for your model
-                )
-
-                num_inference_steps = gr.Slider(
-                    label="Number of inference steps",
-                    minimum=1,
-                    maximum=50,
-                    step=1,
-                    value=2,  # Replace with defaults that work for your model
-                )
-
-        gr.Examples(examples=examples, inputs=[prompt])
-    gr.on(
-        triggers=[run_button.click, prompt.submit],
+    run_button.click(
         fn=infer,
-        inputs=[
-            prompt,
-            negative_prompt,
-            seed,
-            randomize_seed,
-            width,
-            height,
-            guidance_scale,
-            num_inference_steps,
-        ],
-        outputs=[result, seed],
+        inputs=[prompt_input],
+        outputs=[result]
     )
 
-if __name__ == "__main__":
-    demo.launch()
+demo.queue().launch()
+