Update app.py

app.py

@@ -39,36 +39,50 @@ MAX_IMAGE_SIZE = 1216
 
     
 @spaces.GPU
-def infer(image: PIL.Image.Image, prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps) -> PIL.Image.Image:
+def infer(image, prompt, negative_prompt, seed, randomize_seed, width, height, guidance_scale, num_inference_steps) -> PIL.Image.Image:
+    # Check if the input image is a valid PIL Image and is not empty
+    if isinstance(image, PIL.Image.Image) and image.size != (0, 0):
+        use_image = True
+        width, height = image.size
+        ratio = np.sqrt(1024. * 1024. / (width * height))
+        new_width, new_height = int(width * ratio), int(height * ratio)
+        image = image.resize((new_width, new_height))
+        print(image)
+    else:
+        use_image = False
 
-    width, height  = image['composite'].size
-    ratio = np.sqrt(1024. * 1024. / (width * height))
-    new_width, new_height = int(width * ratio), int(height * ratio)
-    image = image['composite'].resize((new_width, new_height))
-
-    print(image)
-    
     if randomize_seed:
         seed = random.randint(0, MAX_SEED)
 
-    controlnet_img = image
-
     generator = torch.Generator().manual_seed(seed)
 
-    output_image = pipe(
-        prompt=prompt + ", masterpiece, best quality, very aesthetic, absurdres",
-        negative_prompt=negative_prompt,
-        image=image,
-        controlnet_conditioning_scale=1.0,
-        guidance_scale=guidance_scale,
-        num_inference_steps=num_inference_steps,
-        width=new_width,
-        height=new_height,
-        generator=generator
-    ).images[0]
+    if use_image:
+        output_image = pipe(
+            prompt=prompt + ", masterpiece, best quality, very aesthetic, absurdres",
+            negative_prompt=negative_prompt,
+            image=image,
+            controlnet_conditioning_scale=1.0,
+            guidance_scale=guidance_scale,
+            num_inference_steps=num_inference_steps,
+            width=new_width,
+            height=new_height,
+            generator=generator
+        ).images[0]
+    else:
+        # If no valid image is provided, generate an image based only on the text prompt
+        output_image = pipe(
+            prompt=prompt,
+            negative_prompt=negative_prompt,
+            guidance_scale=guidance_scale,
+            num_inference_steps=num_inference_steps,
+            width=width,
+            height=height,
+            generator=generator
+        ).images[0]
 
     return output_image
 
+
 css = """
 #col-container {
     margin: 0 auto;