Update app.py

app.py

@@ -1,30 +1,32 @@
 import gradio as gr
 import numpy as np
 import random
-import spaces
 import torch
 from diffusers import DiffusionPipeline
 
 dtype = torch.bfloat16
 device = "cuda" if torch.cuda.is_available() else "cpu"
 
+# Load the pipeline with no hard size restrictions
 pipe = DiffusionPipeline.from_pretrained("black-forest-labs/FLUX.1-schnell", torch_dtype=dtype).to(device)
 
 MAX_SEED = np.iinfo(np.int32).max
-MAX_IMAGE_SIZE = 2048
 
 @spaces.GPU()
 def infer(prompt, seed=42, randomize_seed=False, width=1024, height=1024, num_inference_steps=4, progress=gr.Progress(track_tqdm=True)):
+    # Remove artificial size restrictions; allow the API to handle any size within hardware capacity
     if randomize_seed:
         seed = random.randint(0, MAX_SEED)
     generator = torch.Generator().manual_seed(seed)
+    
+    # Process the image
     image = pipe(
-            prompt = prompt, 
-            width = width,
-            height = height,
-            num_inference_steps = num_inference_steps, 
-            generator = generator,
-            guidance_scale=0.0
+        prompt=prompt, 
+        width=width,
+        height=height,
+        num_inference_steps=num_inference_steps, 
+        generator=generator,
+        guidance_scale=0.0
     ).images[0] 
     return image, seed
  
@@ -50,7 +52,6 @@ with gr.Blocks(css=css) as demo:
         """)
         
         with gr.Row():
-            
             prompt = gr.Text(
                 label="Prompt",
                 show_label=False,
@@ -64,7 +65,6 @@ with gr.Blocks(css=css) as demo:
         result = gr.Image(label="Result", show_label=False)
         
         with gr.Accordion("Advanced Settings", open=False):
-            
             seed = gr.Slider(
                 label="Seed",
                 minimum=0,
@@ -76,11 +76,10 @@ with gr.Blocks(css=css) as demo:
             randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
             
             with gr.Row():
-                
                 width = gr.Slider(
                     label="Width",
                     minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
+                    maximum=2048,  # Set sliders to a large size but allow flexibility in API
                     step=32,
                     value=1024,
                 )
@@ -88,14 +87,12 @@ with gr.Blocks(css=css) as demo:
                 height = gr.Slider(
                     label="Height",
                     minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
+                    maximum=2048,
                     step=32,
                     value=1024,
                 )
             
             with gr.Row():
-                
-  
                 num_inference_steps = gr.Slider(
                     label="Number of inference steps",
                     minimum=1,
@@ -105,18 +102,18 @@ with gr.Blocks(css=css) as demo:
                 )
         
         gr.Examples(
-            examples = examples,
-            fn = infer,
-            inputs = [prompt],
-            outputs = [result, seed],
+            examples=examples,
+            fn=infer,
+            inputs=[prompt],
+            outputs=[result, seed],
             cache_examples="lazy"
         )
 
     gr.on(
         triggers=[run_button.click, prompt.submit],
-        fn = infer,
-        inputs = [prompt, seed, randomize_seed, width, height, num_inference_steps],
-        outputs = [result, seed]
+        fn=infer,
+        inputs=[prompt, seed, randomize_seed, width, height, num_inference_steps],
+        outputs=[result, seed]
     )
 
 demo.launch()