Handle any size

app.py

@@ -11,22 +11,40 @@ device = "cuda" if torch.cuda.is_available() else "cpu"
 pipe = AutoPipelineForImage2Image.from_pretrained("stabilityai/sdxl-turbo", torch_dtype=torch.float16) if torch.cuda.is_available() else AutoPipelineForImage2Image.from_pretrained("stabilityai/sdxl-turbo")
 pipe = pipe.to(device)
 
-def resize(value,img):
-    img = Image.open(img)
-    img = img.resize((value,value))
-    return img
-
 def infer(source_img, prompt, steps, seed, Strength):
     generator = torch.Generator(device).manual_seed(seed)  
     if int(steps * Strength) < 1:
         steps = math.ceil(1 / max(0.10, Strength))
-    source_image = resize(512, source_img)
-    source_image.save('source.png')
-    image = pipe(prompt, image=source_image, strength=Strength, guidance_scale=0.0, num_inference_steps=steps).images[0]
-    return image
+
+    original_height, original_width, original_channel = np.array(source_img).shape
+
+    # Limited to 1 million pixels
+    if 1024 * 1024 < original_width * original_height:
+        factor = ((1024 * 1024) / (original_width * original_height))**0.5
+        process_width = math.floor(original_width * factor)
+        process_height = math.floor(original_height * factor)
+    else:
+        process_width = original_width
+        process_height = original_height
+
+    # Width and height must be multiple of 8
+    if (process_width % 8) != 0 or (process_height % 8) != 0:
+        process_width = process_width - (process_width % 8)
+        process_height = process_height - (process_height % 8)
+
+        if ((process_width + 8) * (process_height + 8)) <= (1024 * 1024):
+            process_width = process_width + 8
+            process_height = process_height + 8
+
+    source_image = source_img.resize((process_width, process_height))
+    
+    image = pipe(prompt, image=source_image, strength=Strength, guidance_scale=0.0, num_inference_steps=steps, width = process_width, height = process_height).images[0]
+
+    output_image = image.resize((original_width, original_height))
+    return output_image
 
 gr.Interface(fn=infer, inputs=[
-    gr.Image(sources=["upload", "webcam", "clipboard"], type="filepath", label="Raw Image."), 
+    gr.Image(sources=["upload", "webcam", "clipboard"], type = "pil", label="Raw Image."), 
     gr.Textbox(label = 'Prompt Input Text. 77 Token (Keyword or Symbol) Maximum'),
     gr.Slider(1, 5, value = 2, step = 1, label = 'Number of Iterations'),
     gr.Slider(label = "Seed", minimum = 0, maximum = 987654321987654321, step = 1, randomize = True),