Update app.py

app.py

@@ -26,23 +26,21 @@ pipe = DiffusionPipeline.from_pretrained("runwayml/stable-diffusion-v1-5",
                                          torch_dtype=torch.float16).to(device)
 pipe.enable_xformers_memory_efficient_attention()
 
-source_image = load_image('https://huggingface.co/lllyasviel/control_v11f1e_sd15_tile/resolve/main/images/original.png')
-
-
 def super_esr(source_image,prompt,negative_prompt,strength,seed,num_inference_steps):
     condition_image = resize_for_condition_image(source_image, 1024)
-    image = pipe(prompt=prompt,#"best quality", 
-                negative_prompt="blur, lowres, bad anatomy, bad hands, cropped, worst quality", 
-                image=condition_image, 
-                controlnet_conditioning_image=condition_image, 
-                width=condition_image.size[0],
-                height=condition_image.size[1],
-                strength=1.0,
-                generator=seed,
-                num_inference_steps=num_inference_steps,
-                ).image
-    print(source_image,prompt,negative_prompt,strength,seed,num_inference_steps)
-    return source_image
+    
+    # image = pipe(prompt=prompt,#"best quality", 
+    #             negative_prompt="blur, lowres, bad anatomy, bad hands, cropped, worst quality", 
+    #             image=condition_image, 
+    #             controlnet_conditioning_image=condition_image, 
+    #             width=condition_image.size[0],
+    #             height=condition_image.size[1],
+    #             strength=1.0,
+    #             generator=seed,
+    #             num_inference_steps=num_inference_steps,
+    #             ).image
+    # print(source_image,prompt,negative_prompt,strength,seed,num_inference_steps)
+    return condition_image
 
 #define laund take input nsame as super_esr function
 
@@ -66,3 +64,4 @@ examples=[
 #create queue the rerquests
 x=gr.Interface(fn=super_esr,inputs=inputs,outputs=outputs,title=title,description=description,examples=examples)
 x.launch()
+