improvements

app.py

@@ -1,7 +1,9 @@
 import cv2
 import torch
 import random
+import tempfile
 import numpy as np
+from pathlib import Path
 from PIL import Image
 from diffusers import (
     ControlNetModel,
@@ -43,6 +45,7 @@ pipe = StableDiffusionXLControlNetPipeline.from_pretrained(
     variant="fp16",
     add_watermarker=False,
 ).to(device)
+pipe.set_progress_bar_config(disable=True)
 pipe.scheduler = EulerDiscreteScheduler.from_config(
     pipe.scheduler.config, timestep_spacing="trailing", prediction_type="epsilon"
 )
@@ -222,6 +225,8 @@ def create_image(
             controlnet_conditioning_scale=float(control_scale),
             neg_content_prompt=neg_content_prompt,
             neg_content_scale=neg_content_scale,
+            width=512,
+            height=512,
         )
     else:
         images = ip_model.generate(
@@ -235,8 +240,13 @@ def create_image(
             seed=seed,
             image=canny_map,
             controlnet_conditioning_scale=float(control_scale),
+            width=512,
+            height=512,
         )
-    return images[0]
+    image = images[0]
+    with tempfile.NamedTemporaryFile(suffix=".jpg", delete=False) as tmpfile:
+        image.save(tmpfile, "JPEG", quality=80, optimize=True, progressive=True)
+        return Path(tmpfile.name)
 
 
 def pil_to_cv2(image_pil):
@@ -251,7 +261,7 @@ title = r"""
 """
 
 description = r"""
-<b>Forked from <a href='https://github.com/InstantStyle/InstantStyle' target='_blank'><b>InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation</b></a>.<br>
+<b>Forked from <a href='https://github.com/InstantStyle/InstantStyle' target='_blank'>InstantStyle: Free Lunch towards Style-Preserving in Text-to-Image Generation</a>.<br>
 <b>Model by <a href='https://huggingface.co/ByteDance/SDXL-Lightning' target='_blank'>SDXL Lightning</a> and <a href='https://huggingface.co/h94/IP-Adapter' target='_blank'>IP-Adapter</a>.</b><br>
 """