Better parameter order

gradio_demo.py

@@ -117,13 +117,36 @@ def llave_process(input_image, temperature, top_p, qs=None):
     return captions[0]
 
 @spaces.GPU(duration=240)
-def stage2_process(input_image, prompt, a_prompt, n_prompt, num_samples, upscale, edm_steps, s_stage1, s_stage2,
-                   s_cfg, seed, s_churn, s_noise, color_fix_type, diff_dtype, ae_dtype, gamma_correction,
-                   linear_CFG, linear_s_stage2, spt_linear_CFG, spt_linear_s_stage2, model_select):
+def stage2_process(
+    noisy_image,
+    denoise_image,
+    prompt,
+    a_prompt,
+    n_prompt,
+    num_samples,
+    upscale,
+    edm_steps,
+    s_stage1,
+    s_stage2,
+    s_cfg,
+    seed,
+    s_churn,
+    s_noise,
+    color_fix_type,
+    diff_dtype,
+    ae_dtype,
+    gamma_correction,
+    linear_CFG,
+    linear_s_stage2,
+    spt_linear_CFG,
+    spt_linear_s_stage2,
+    model_select
+):
     print('Start stage2_process')
     if torch.cuda.device_count() == 0:
         gr.Warning('Set this space to GPU config to make it work.')
         return None, None
+    input_image = noisy_image if denoise_image is None else denoise_image
     torch.cuda.set_device(SUPIR_device)
     event_id = str(time.time_ns())
     event_dict = {'event_id': event_id, 'localtime': time.ctime(), 'prompt': prompt, 'a_prompt': a_prompt,
@@ -184,7 +207,7 @@ def load_and_reset(param_setting):
     print('Start load_and_reset')
     if torch.cuda.device_count() == 0:
         gr.Warning('Set this space to GPU config to make it work.')
-        return None, None, None, None, None, None, None, None, None, None, None, None, None
+        return None, None, None, None, None, None, None, None, None, None, None, None, None, None
     edm_steps = default_setting.edm_steps
     s_stage2 = 1.0
     s_stage1 = -1.0
@@ -203,15 +226,17 @@ def load_and_reset(param_setting):
     if param_setting == "Quality":
         s_cfg = default_setting.s_cfg_Quality
         spt_linear_CFG = default_setting.spt_linear_CFG_Quality
+        model_select = "v0-Q"
     elif param_setting == "Fidelity":
         s_cfg = default_setting.s_cfg_Fidelity
         spt_linear_CFG = default_setting.spt_linear_CFG_Fidelity
+        model_select = "v0-F"
     else:
         raise NotImplementedError
     gr.Info('The parameters are reset.')
     print('End load_and_reset')
     return edm_steps, s_cfg, s_stage2, s_stage1, s_churn, s_noise, a_prompt, n_prompt, color_fix_type, linear_CFG, \
-        linear_s_stage2, spt_linear_CFG, spt_linear_s_stage2
+        linear_s_stage2, spt_linear_CFG, spt_linear_s_stage2, model_select
 
 
 def submit_feedback(event_id, fb_score, fb_text):
@@ -229,10 +254,10 @@ def submit_feedback(event_id, fb_score, fb_text):
 
 title_html = """
     <h1><center>SUPIR</center></h1>
-    <center>Upscale your images up to x8 freely, without account, without watermark and download it</center>
+    <big><center>Upscale your images up to x8 freely, without account, without watermark and download it</center></big>
     <br/>
     
-    <p>SUPIR is a practicing model scaling for photo-realistic image restoration. It is still a research project under tested and is not yet a stable commercial product. LLaVa is not available in this demo. If you want to auto-generate the description of your image, use another <a href="https://huggingface.co/spaces/MaziyarPanahi/llava-llama-3-8b">LLaVa space</a>.
+    <p>SUPIR is a practicing model scaling for photo-realistic image restoration. It is still a research project under tested and is not yet a stable commercial product. LLaVa is not integrated in this demo. If you want to auto-generate the description of your image, use another <a href="https://huggingface.co/spaces/MaziyarPanahi/llava-llama-3-8b">LLaVa space</a>. The content added by SUPIR is imagination, not real-world information. The aim of SUPIR is the beauty and the illustration.
     
     <p><center><a href="https://arxiv.org/abs/2401.13627">Paper</a> &emsp; <a href="http://supir.xpixel.group/">Project Page</a> &emsp; <a href="https://github.com/Fanghua-Yu/SUPIR/blob/master/assets/DemoGuide.png">How to play</a> &emsp; <a href="https://huggingface.co/blog/MonsterMMORPG/supir-sota-image-upscale-better-than-magnific-ai">Local Install Guide</a></center></p>
     """
@@ -281,18 +306,7 @@ with gr.Blocks(title="SUPIR") as interface:
                 qs = gr.Textbox(label="Question", info="Ask LLaVa what description you want", value="Describe the image and its style in a very detailed manner. The image is a realistic photography, not an art painting.", lines=3)
 
             with gr.Accordion("Restoring options", open=False):
-                num_samples = gr.Slider(label="Num Samples", info="Number of generated results; I discourage to increase because the process is limited to 3 min", minimum=1, maximum=4 if not args.use_image_slider else 1
-                                        , value=1, step=1)
                 upscale = gr.Slider(label="Upscale factor", info="Resolution x1, x2, x3, x4, x5, x6, x7 or x8", minimum=1, maximum=8, value=2, step=1)
-                edm_steps = gr.Slider(label="Steps", info="lower=faster, higher=more details", minimum=1, maximum=200, value=default_setting.edm_steps if torch.cuda.device_count() > 0 else 1, step=1)
-                s_cfg = gr.Slider(label="Text Guidance Scale", info="lower=follow the image, higher=follow the prompt", minimum=1.0, maximum=15.0,
-                                  value=default_setting.s_cfg_Quality if torch.cuda.device_count() > 0 else 1.0, step=0.1)
-                s_stage2 = gr.Slider(label="Restoring Guidance Strength", minimum=0., maximum=1., value=1., step=0.05)
-                s_stage1 = gr.Slider(label="Pre-denoising Guidance Strength", minimum=-1.0, maximum=6.0, value=-1.0, step=1.0)
-                randomize_seed = gr.Checkbox(label = "\U0001F3B2 Randomize seed", value = True, info = "If checked, result is always different")
-                seed = gr.Slider(label="Seed", minimum=0, maximum=2147483647, step=1, randomize=True)
-                s_churn = gr.Slider(label="S-Churn", minimum=0, maximum=40, value=5, step=1)
-                s_noise = gr.Slider(label="S-Noise", minimum=1.0, maximum=1.1, value=1.003, step=0.001)
                 a_prompt = gr.Textbox(label="Default Positive Prompt",
                                       info="Describe what the image represents",
                                       value='Cinematic, High Contrast, highly detailed, taken using a Canon EOS R '
@@ -307,6 +321,22 @@ with gr.Blocks(title="SUPIR") as interface:
                                             'worst quality, low quality, frames, watermark, signature, jpeg artifacts, '
                                             'deformed, lowres, over-smooth',
                                       lines=3)
+                num_samples = gr.Slider(label="Num Samples", info="Number of generated results; I discourage to increase because the process is limited to 4 min", minimum=1, maximum=4 if not args.use_image_slider else 1
+                                        , value=1, step=1)
+                edm_steps = gr.Slider(label="Steps", info="lower=faster, higher=more details", minimum=1, maximum=200, value=default_setting.edm_steps if torch.cuda.device_count() > 0 else 1, step=1)
+                with gr.Row():
+                    with gr.Column():
+                        model_select = gr.Radio(["v0-Q", "v0-F"], label="Model Selection", info="Q=Quality, F=Fidelity", value="v0-Q",
+                                                interactive=True)
+                    with gr.Column():
+                        color_fix_type = gr.Radio(["None", "AdaIn", "Wavelet"], label="Color-Fix Type", info="AdaIn=Adaptive Instance Normalization, Wavelet=For JPEG artifacts", value="Wavelet",
+                                                  interactive=True)
+                s_cfg = gr.Slider(label="Text Guidance Scale", info="lower=follow the image, higher=follow the prompt", minimum=1.0, maximum=15.0,
+                                  value=default_setting.s_cfg_Quality if torch.cuda.device_count() > 0 else 1.0, step=0.1)
+                s_stage2 = gr.Slider(label="Restoring Guidance Strength", minimum=0., maximum=1., value=1., step=0.05)
+                s_stage1 = gr.Slider(label="Pre-denoising Guidance Strength", minimum=-1.0, maximum=6.0, value=-1.0, step=1.0)
+                s_churn = gr.Slider(label="S-Churn", minimum=0, maximum=40, value=5, step=1)
+                s_noise = gr.Slider(label="S-Noise", minimum=1.0, maximum=1.1, value=1.003, step=0.001)
                 with gr.Row():
                     with gr.Column():
                         linear_CFG = gr.Checkbox(label="Linear CFG", value=True)
@@ -323,12 +353,8 @@ with gr.Blocks(title="SUPIR") as interface:
                     with gr.Column():
                         ae_dtype = gr.Radio(['fp32', 'bf16'], label="Auto-Encoder Data Type", value="bf16",
                                             interactive=True)
-                    with gr.Column():
-                        color_fix_type = gr.Radio(["None", "AdaIn", "Wavelet"], label="Color-Fix Type", info="AdaIn=Adaptive Instance Normalization, Wavelet=For JPEG artifacts", value="Wavelet",
-                                                  interactive=True)
-                    with gr.Column():
-                        model_select = gr.Radio(["v0-Q", "v0-F"], label="Model Selection", info="Q=Quality, F=Fidelity", value="v0-Q",
-                                                interactive=True)
+                randomize_seed = gr.Checkbox(label = "\U0001F3B2 Randomize seed", value = True, info = "If checked, result is always different")
+                seed = gr.Slider(label="Seed", minimum=0, maximum=2147483647, step=1, randomize=True)
 
         with gr.Column():
             gr.Markdown("<center>Restoring Output</center>")
@@ -340,14 +366,14 @@ with gr.Blocks(title="SUPIR") as interface:
                 with gr.Column(visible=False):
                     llave_button = gr.Button(value="Generate description by LlaVa (disabled)")
                 with gr.Column():
-                    diffusion_button = gr.Button(value="🚀 Upscale/Restore", variant = "primary")
+                    diffusion_button = gr.Button(value="🚀 Upscale/Restore", variant = "primary", elem_id="process_button")
             with gr.Row():
                 with gr.Column():
-                    param_setting = gr.Radio(["Quality", "Fidelity"], interactive=True, label="Parameter setting", value="Quality")
+                    param_setting = gr.Radio(["Quality", "Fidelity"], interactive=True, label="Presetting", value="Quality")
                 with gr.Column():
-                    restart_button = gr.Button(value="Apply parameter setting", scale=2)
+                    restart_button = gr.Button(value="Apply presetting", scale=2)
 
-            with gr.Accordion("Feedback", open=True):
+            with gr.Accordion("Feedback", open=True, visible=False):
                 fb_score = gr.Slider(label="Feedback Score", minimum=1, maximum=5, value=3, step=1,
                                      interactive=True)
                 fb_text = gr.Textbox(label="Feedback Text", value="", placeholder='Please enter your feedback here.')
@@ -388,6 +414,7 @@ with gr.Blocks(title="SUPIR") as interface:
         fb_text
     ], queue = False, show_progress = False).success(fn=stage2_process, inputs = [
         input_image,
+        denoise_image,
         prompt,
         a_prompt,
         n_prompt,
@@ -430,7 +457,8 @@ with gr.Blocks(title="SUPIR") as interface:
         linear_CFG,
         linear_s_stage2,
         spt_linear_CFG,
-        spt_linear_s_stage2
+        spt_linear_s_stage2,
+        model_select
     ])
 
     submit_button.click(fn = submit_feedback, inputs = [