Update app.py

app.py

@@ -17,6 +17,15 @@ MIN_IMAGE_SIZE = int(os.getenv("MIN_IMAGE_SIZE", "512"))
 MAX_IMAGE_SIZE = int(os.getenv("MAX_IMAGE_SIZE", "2048"))
 MAX_SEED = np.iinfo(np.int32).max
 
+sampler_list = [
+    "DPM++ 2M Karras",
+    "DPM++ SDE Karras",
+    "DPM++ 2M SDE Karras",
+    "Euler",
+    "Euler a",
+    "DDIM",
+]
+
 torch.backends.cudnn.deterministic = True
 torch.backends.cudnn.benchmark = False
 
@@ -101,7 +110,7 @@ def generate(
             output_type="pil",
         ).images[0]
 
-        return img
+        return img, seed
 
     except Exception as e:
         print(f"An error occurred: {e}")
@@ -112,3 +121,116 @@ if torch.cuda.is_available():
 else:
     pipe = None
 
+with gr.Blocks(
+    theme=gr.themes.Soft()
+) as demo:
+    gr.Markdown("Starry XL 5.2 Demo")
+
+    with gr.Group():
+        prompt = gr.Text(
+            label="Prompt",
+            placeholder="Enter your prompt here..."
+        )
+
+        negative_prompt = gr.Text(
+            label="Negative Prompt",
+            placeholder="(Optional) Enter your negative prompt here..."
+        )
+
+        with gr.Row():
+            width = gr.Slider(
+                label="Width",
+                minimum=256,
+                maximum=MAX_IMAGE_SIZE,
+                step=32,
+                value=1024,
+            )
+            height = gr.Slider(
+                label="Height",
+                minimum=256,
+                maximum=MAX_IMAGE_SIZE,
+                step=32,
+                value=1024,
+            )
+
+        sampler = gr.Dropdown(
+            label="Sampler",
+            choices=sampler_list,
+            interactive=True,
+            value="Euler a",
+        )        
+        
+        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():
+            guidance_scale = gr.Slider(
+                label="Guidance scale",
+                minimum=1,
+                maximum=20,
+                step=0.1,
+                value=5.0,
+            )
+            num_inference_steps = gr.Slider(
+                label="Steps",
+                minimum=10,
+                maximum=100,
+                step=1,
+                value=25,
+            )
+
+        clip_skip = gr.Slider(
+            label="Clip Skip",
+            minimum=1,
+            maximum=2,
+            step=1,
+            value=1
+        )
+
+        run_button = gr.Button("Run")
+
+        result = gr.Image(
+            label="Result",
+            show_label=False
+        )
+
+    with gr.Group():
+        used_seed = gr.Number(label="Used Seed", interactive=False)
+
+    gr.on(
+        triggers=[
+            prompt.submit,
+            negative_prompt.submit,         
+            run_button.click,
+        ],
+        fn=randomize_seed_fn,
+        inputs=[seed, randomize_seed],
+        outputs=seed,
+        queue=False,
+        api_name=False,
+    ).then(
+        fn=generate,
+        inputs=[
+            prompt,
+            negative_prompt,
+            seed,
+            width,
+            height,
+            guidance_scale,
+            num_inference_steps,
+            sampler,
+            clip_skip
+        ],
+        outputs=[result, used_seed],
+        api_name="run"
+    )
+
+if __name__ == "__main__":
+    demo.queue(max_size=20).launch(show_error=True)