Improve interface

gradio_demo.py

@@ -165,7 +165,6 @@ def stage2_process(input_image, prompt, a_prompt, n_prompt, num_samples, upscale
             Image.fromarray(result).save(f'./history/{event_id[:5]}/{event_id[5:]}/HQ_{i}.png')
     return [input_image] + results, event_id, 3, ''
 
-@spaces.GPU(duration=120)
 def load_and_reset(param_setting):
     if torch.cuda.device_count() == 0:
         gr.Warning('Set this space to GPU config to make it work.')
@@ -226,6 +225,7 @@ else:
     ⚠️SUPIR is still a research project under tested and is not yet a stable commercial product.
     
     <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>
+    <p style="background-color: orange;">For now, only the stage 2 is working (the most important one). The stage 1 and LLaVa are failing. LLaVa is disabled.</p>
     """
 
 
@@ -252,34 +252,38 @@ with gr.Blocks(title='SUPIR') as interface:
                 with gr.Column():
                     gr.Markdown("<center>Stage1 Output</center>")
                     denoise_image = gr.Image(type="numpy", elem_id="image-s1", height=400, width=400)
-            prompt = gr.Textbox(label="Prompt", value="")
+            prompt = gr.Textbox(label="Prompt", value="", placeholder="A person, walking, in a town, Summer, photorealistic")
+
             with gr.Accordion("Stage1 options", open=False):
                 gamma_correction = gr.Slider(label="Gamma Correction", minimum=0.1, maximum=2.0, value=1.0, step=0.1)
+
             with gr.Accordion("LLaVA options", open=False):
-                temperature = gr.Slider(label="Temperature", minimum=0., maximum=1.0, value=0.2, step=0.1)
-                top_p = gr.Slider(label="Top P", minimum=0., maximum=1.0, value=0.7, step=0.1)
-                qs = gr.Textbox(label="Question", value="Describe this image and its style in a very detailed manner. "
-                                                        "The image is a realistic photography, not an art painting.")
+                temperature = gr.Slider(label="Temperature", info = "lower=Always similar, higher=More creative", minimum=0., maximum=1.0, value=0.2, step=0.1)
+                top_p = gr.Slider(label="Top P", info = "Percent of tokens shortlisted", minimum=0., maximum=1.0, value=0.7, step=0.1)
+                qs = gr.Textbox(label="Question", info="Describe the image and its style in a very detailed manner", placeholder="The image is a realistic photography, not an art painting.")
+
             with gr.Accordion("Stage2 options", open=False):
-                num_samples = gr.Slider(label="Num Samples", minimum=1, maximum=4 if not args.use_image_slider else 1
+                num_samples = gr.Slider(label="Num Samples", info="Number of generated results; I discourage to increase because the process is limited to 2 min", minimum=1, maximum=4 if not args.use_image_slider else 1
                                         , value=1, step=1)
-                upscale = gr.Slider(label="Upscale", minimum=1, maximum=8, value=1, step=1)
-                edm_steps = gr.Slider(label="Steps", 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", minimum=1.0, maximum=15.0,
+                upscale = gr.Slider(label="Upscale", info="The resolution increase factor", minimum=1, maximum=8, 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)
+                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="Stage2 Guidance Strength", minimum=0., maximum=1., value=1., step=0.05)
                 s_stage1 = gr.Slider(label="Stage1 Guidance Strength", minimum=-1.0, maximum=6.0, value=-1.0, step=1.0)
-                seed = gr.Slider(label="Seed", minimum=-1, maximum=2147483647, step=1, randomize=True)
+                seed = gr.Slider(label="Seed", info="-1=Different each time, other=Reproducible", minimum=-1, 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 '
                                             'camera, hyper detailed photo - realistic maximum detail, 32k, Color '
                                             'Grading, ultra HD, extreme meticulous detailing, skin pore detailing, '
                                             'hyper sharpness, perfect without deformations.')
                 n_prompt = gr.Textbox(label="Default Negative Prompt",
-                                      value='painting, oil painting, illustration, drawing, art, sketch, oil painting, '
-                                            'cartoon, CG Style, 3D render, unreal engine, blurring, dirty, messy, '
+                                      info="List what the image does NOT represent",
+                                      value='painting, oil painting, illustration, drawing, art, sketch, anime, '
+                                            'cartoon, CG Style, 3D render, unreal engine, blurring, bokeh, ugly, dirty, messy, '
                                             'worst quality, low quality, frames, watermark, signature, jpeg artifacts, '
                                             'deformed, lowres, over-smooth')
                 with gr.Row():
@@ -313,17 +317,17 @@ with gr.Blocks(title='SUPIR') as interface:
                 result_gallery = ImageSlider(label='Output', show_label=False, elem_id="gallery1")
             with gr.Row():
                 with gr.Column():
-                    denoise_button = gr.Button(value="Stage1 Run")
+                    denoise_button = gr.Button(value="Stage1 Run (out of work)")
                 with gr.Column():
                     llave_button = gr.Button(value="LlaVa Run")
                 with gr.Column():
-                    diffusion_button = gr.Button(value="Stage2 Run")
+                    diffusion_button = gr.Button(value="Stage2 Run (actual upscaling)", variant = "primary")
             with gr.Row():
                 with gr.Column():
-                    param_setting = gr.Dropdown(["Quality", "Fidelity"], interactive=True, label="Param Setting",
-                                               value="Quality")
+                    param_setting = gr.Radio(["Quality", "Fidelity"], interactive=True, label="Param Setting", value="Quality")
                 with gr.Column():
-                    restart_button = gr.Button(value="Reset Param", scale=2)
+                    restart_button = gr.Button(value="Reset Param", scale=2, variant="stop")
+
             with gr.Accordion("Feedback", open=True):
                 fb_score = gr.Slider(label="Feedback Score", minimum=1, maximum=5, value=3, step=1,
                                      interactive=True)