choose in arena if to use same settings for both models

app.py

@@ -84,15 +84,21 @@ def generate_single_image(
 @spaces.GPU(duration=80)
 def generate_arena_images(
     prompt,
-    negative_prompt,
-    num_inference_steps,
-    height,
-    width,
-    guidance_scale,
+    negative_prompt_A,
+    negative_prompt_B,
+    num_inference_steps_A,
+    num_inference_steps_B,
+    height_A,
+    height_B,
+    width_A,
+    width_B,
+    guidance_scale_A,
+    guidance_scale_B,
     seed,
     num_images_per_prompt,
-    model_choice_1,
-    model_choice_2,
+    model_choice_A,
+    model_choice_B,
+    use_same_settings,
     progress=gr.Progress(track_tqdm=True),
 ):
     if seed == 0:
@@ -100,33 +106,41 @@ def generate_arena_images(
 
     generator = torch.Generator().manual_seed(seed)
 
+    # Apply settings based on use_same_settings
+    if use_same_settings:
+        num_inference_steps_B = num_inference_steps_A
+        height_B = height_A
+        width_B = width_A
+        guidance_scale_B = guidance_scale_A
+        negative_prompt_B = negative_prompt_A
+
     # Generate images for both models
-    images_1 = generate_single_image(
+    images_A = generate_single_image(
         prompt,
-        negative_prompt,
-        num_inference_steps,
-        height,
-        width,
-        guidance_scale,
+        negative_prompt_A,
+        num_inference_steps_A,
+        height_A,
+        width_A,
+        guidance_scale_A,
         seed,
         num_images_per_prompt,
-        model_choice_1,
+        model_choice_A,
         generator,
     )
-    images_2 = generate_single_image(
+    images_B = generate_single_image(
         prompt,
-        negative_prompt,
-        num_inference_steps,
-        height,
-        width,
-        guidance_scale,
+        negative_prompt_B,
+        num_inference_steps_B,
+        height_B,
+        width_B,
+        guidance_scale_B,
         seed,
         num_images_per_prompt,
-        model_choice_2,
+        model_choice_B,
         generator,
     )
 
-    return images_1, images_2
+    return images_A, images_B
 
 # Define the image generation function for the Individual tab
 @spaces.GPU(duration=80)
@@ -199,61 +213,102 @@ with gr.Blocks(css=css) as demo:
                         info="Describe the image you want",
                         placeholder="A cat...",
                     )
-                    model_choice_1 = gr.Dropdown(
-                        label="Stable Diffusion Model 1",
+                    model_choice_A = gr.Dropdown(
+                        label="Stable Diffusion Model A",
                         choices=["sd3 medium", "sd2.1", "sdxl", "sdxl flash"],
                         value="sd3 medium",
                     )
-                    model_choice_2 = gr.Dropdown(
-                        label="Stable Diffusion Model 2",
+                    model_choice_B = gr.Dropdown(
+                        label="Stable Diffusion Model B",
                         choices=["sd3 medium", "sd2.1", "sdxl", "sdxl flash"],
                         value="sdxl",
                     )
                     run_button = gr.Button("Run")
-                result_1 = gr.Gallery(label="Generated Images (Model 1)", elem_id="gallery_1")
-                result_2 = gr.Gallery(label="Generated Images (Model 2)", elem_id="gallery_2")
+                result_A = gr.Gallery(label="Generated Images (Model A)", elem_id="gallery_A")
+                result_B = gr.Gallery(label="Generated Images (Model B)", elem_id="gallery_B")
             with gr.Accordion("Advanced options", open=False):
+                use_same_settings = gr.Checkbox(label='Use same settings for both models', value=True)
                 with gr.Row():
-                    negative_prompt = gr.Textbox(
-                        label="Negative Prompt",
+                    negative_prompt_A = gr.Textbox(
+                        label="Negative Prompt (Model A)",
+                        info="Describe what you don't want in the image",
+                        value="deformed, distorted, disfigured, poorly drawn, bad anatomy, incorrect anatomy, extra limb, missing limb, floating limbs, mutated hands and fingers, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation",
+                        placeholder="Ugly, bad anatomy...",
+                    )
+                    negative_prompt_B = gr.Textbox(
+                        label="Negative Prompt (Model B)",
                         info="Describe what you don't want in the image",
                         value="deformed, distorted, disfigured, poorly drawn, bad anatomy, incorrect anatomy, extra limb, missing limb, floating limbs, mutated hands and fingers, disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation",
                         placeholder="Ugly, bad anatomy...",
                     )
                 with gr.Row():
-                    num_inference_steps = gr.Slider(
-                        label="Number of Inference Steps",
+                    num_inference_steps_A = gr.Slider(
+                        label="Number of Inference Steps (Model A)",
                         info="The number of denoising steps of the image. More denoising steps usually lead to a higher quality image at the cost of slower inference",
                         minimum=1,
                         maximum=50,
                         value=25,
                         step=1,
                     )
-                    guidance_scale = gr.Slider(
-                        label="Guidance Scale",
-                        info="Controls how much the image generation process follows the text prompt. Higher values make the image stick more closely to the input text.",
-                        minimum=0.0,
-                        maximum=10.0,
-                        value=7.5,
-                        step=0.1,
+                    num_inference_steps_B = gr.Slider(
+                        label="Number of Inference Steps (Model B)",
+                        info="The number of denoising steps of the image. More denoising steps usually lead to a higher quality image at the cost of slower inference",
+                        minimum=1,
+                        maximum=50,
+                        value=25,
+                        step=1,
                     )
                 with gr.Row():
-                    width = gr.Slider(
-                        label="Width",
+                    width_A = gr.Slider(
+                        label="Width (Model A)",
                         info="Width of the Image",
                         minimum=256,
                         maximum=1344,
                         step=32,
                         value=1024,
                     )
-                    height = gr.Slider(
-                        label="Height",
+                    width_B = gr.Slider(
+                        label="Width (Model B)",
+                        info="Width of the Image",
+                        minimum=256,
+                        maximum=1344,
+                        step=32,
+                        value=1024,
+                    )
+                with gr.Row():
+                    height_A = gr.Slider(
+                        label="Height (Model A)",
+                        info="Height of the Image",
+                        minimum=256,
+                        maximum=1344,
+                        step=32,
+                        value=1024,
+                    )
+                    height_B = gr.Slider(
+                        label="Height (Model B)",
                         info="Height of the Image",
                         minimum=256,
                         maximum=1344,
                         step=32,
                         value=1024,
                     )
+                with gr.Row():
+                    guidance_scale_A = gr.Slider(
+                        label="Guidance Scale (Model A)",
+                        info="Controls how much the image generation process follows the text prompt. Higher values make the image stick more closely to the input text.",
+                        minimum=0.0,
+                        maximum=10.0,
+                        value=7.5,
+                        step=0.1,
+                    )
+                    guidance_scale_B = gr.Slider(
+                        label="Guidance Scale (Model B)",
+                        info="Controls how much the image generation process follows the text prompt. Higher values make the image stick more closely to the input text.",
+                        minimum=0.0,
+                        maximum=10.0,
+                        value=7.5,
+                        step=0.1,
+                    )
                 with gr.Row():
                     seed = gr.Slider(
                         value=42,
@@ -275,7 +330,7 @@ with gr.Blocks(css=css) as demo:
             gr.Examples(
                 examples=examples,
                 inputs=[prompt],
-                outputs=[result_1, result_2],
+                outputs=[result_A, result_B],
                 fn=generate_arena_images,
             )
 
@@ -287,17 +342,23 @@ with gr.Blocks(css=css) as demo:
                 fn=generate_arena_images,
                 inputs=[
                     prompt,
-                    negative_prompt,
-                    num_inference_steps,
-                    width,
-                    height,
-                    guidance_scale,
+                    negative_prompt_A,
+                    negative_prompt_B,
+                    num_inference_steps_A,
+                    num_inference_steps_B,
+                    height_A,
+                    height_B,
+                    width_A,
+                    width_B,
+                    guidance_scale_A,
+                    guidance_scale_B,
                     seed,
                     num_images_per_prompt,
-                    model_choice_1,
-                    model_choice_2,
+                    model_choice_A,
+                    model_choice_B,
+                    use_same_settings
                 ],
-                outputs=[result_1, result_2],
+                outputs=[result_A, result_B],
             )
 
         with gr.TabItem("Individual"):