Update app.py

app.py

@@ -5,6 +5,9 @@ import spaces
 import gradio as gr
 import numpy as np
 import torch
+import tempfile
+import os
+import uuid
 from PIL import Image
 from diffusers import StableDiffusionXLImg2ImgPipeline, StableDiffusionXLPipeline, EDMEulerScheduler, StableDiffusionXLInstructPix2PixPipeline, AutoencoderKL, DPMSolverMultistepScheduler
 from huggingface_hub import hf_hub_download, InferenceClient
@@ -29,6 +32,11 @@ To optimize image results:
 - **Increase the number of steps** for enhanced edits.
 """
 
+def save_image(img):
+    unique_name = str(uuid.uuid4()) + ".png"
+    img.save(unique_name)
+    return unique_name
+
 def set_timesteps_patched(self, num_inference_steps: int, device = None):
     self.num_inference_steps = num_inference_steps
     
@@ -91,8 +99,9 @@ def king(type ,
             num_inference_steps=steps,
             image=output_image,
             generator=generator,
-        ).images[0]  
-        return seed, refine
+        ).images
+        image_paths = [save_image(img) for img in refine][0]
+        return seed, image_paths
     else :
         if randomize_seed:
             seed = random.randint(0, 999999)
@@ -108,7 +117,7 @@ def king(type ,
             num_inference_steps = int(steps/2.5),
             width = width, height = height,
             generator = generator,
-            ).images[0]
+            ).images
         else:            
             image = pipe_fast( prompt = instruction,
             negative_prompt=negative_prompt,
@@ -123,8 +132,9 @@ def king(type ,
                     guidance_scale = 7.5,
                     num_inference_steps=  steps,
                     image=image, generator=generator,
-            ).images[0]        
-        return seed, refine
+            ).images
+        image_paths = [save_image(img) for img in refine][0]
+        return seed, image_paths
 
 client = InferenceClient()
 # Prompt classifier