.

app.py

@@ -137,10 +137,12 @@ with gr.Blocks() as demo:
             img = gr.Image()
             prompt = gr.Textbox(label="Enter the text to get a good start")
             btn = gr.Button()
-            size = gr.Slider(label="Size", minimum=256, maximum=MAX_IMAGE_SIZE, step=8, value=1024)
-            num_inference_steps = gr.Slider(label="num_inference_steps", minimum=1, maximum=100,step=1, value=20)
+            with gr.Accordion("Advanced options", open=False):
+                size = gr.Slider(label="Size", minimum=256, maximum=MAX_IMAGE_SIZE, step=8, value=1024)
+                num_inference_steps = gr.Slider(label="num_inference_steps", minimum=1, maximum=100,step=1, value=20)
+                guidance_scale=gr.Slider(label="guidance_scale", minimum=0.1, maximum=30.0, value=9.0, step=0.1)
             out_img = gr.Image()
-            btn.click(Banner.Image2Image_2, [prompt, img,size,num_inference_steps], out_img)
+            btn.click(Banner.Image2Image_2, [prompt, img,size,num_inference_steps,guidance_scale], out_img)
 
 
     with gr.Tab("Video"):

options/Banner.py

@@ -21,5 +21,5 @@ def Image2Image(
     progress=gr.Progress(track_tqdm=True)
 ):return I2I(input_image_editor,input_text,seed_slicer,randomize_seed_checkbox,strength_slider,num_inference_steps_slider)
 
-def Image2Image_2(prompt,image,size,num_inference_steps=30):
+def Image2Image_2(prompt,image,size,num_inference_steps,guidance_scale):
     return I2I_2(image, prompt,size,num_inference_steps)

options/Banner_Model/Image2Image_2.py

@@ -8,7 +8,7 @@ device= "cuda" if torch.cuda.is_available() else "cpu"
 print("Using device for I2I_2:", device)
 
 @spaces.GPU(duration=100)
-def I2I_2(image, prompt,size,num_inference_steps):
+def I2I_2(image, prompt,size,num_inference_steps,guidance_scale):
     processor = LineartDetector.from_pretrained("lllyasviel/Annotators")
 
     checkpoint = "ControlNet-1-1-preview/control_v11p_sd15_lineart"
@@ -23,5 +23,5 @@ def I2I_2(image, prompt,size,num_inference_steps):
     image.resize((size,size))
     image=processor(image)
     generator = torch.Generator(device=device).manual_seed(0)
-    image = pipe(prompt+"best quality, extremely detailed", num_inference_steps=num_inference_steps, generator=generator, image=image,negative_prompt="longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality").images[0]
+    image = pipe(prompt+"best quality, extremely detailed", num_inference_steps=num_inference_steps, generator=generator, image=image,negative_prompt="longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality",guidance_scale=guidance_scale).images[0]
     return image