Update app.py

app.py

@@ -110,7 +110,7 @@ def get_video_fps(video_path):
 def load_examples(ref_image_in, ref_video_in):
     return "./examples/mimicmotion_result1_example.mp4"
     
-def infer(ref_image_in, ref_video_in):
+def infer(ref_image_in, ref_video_in, num_inference_steps, guidance_scale, output_frames_per_second, seed, checkpoint_version):
     # check if 'outputs' dir exists and empty it if necessary
     check_outputs_folder('./outputs')
     
@@ -124,17 +124,17 @@ def infer(ref_image_in, ref_video_in):
         num_frames = 16
         resolution = 576
         frames_overlap = 6
-        num_inference_steps = 25
+        num_inference_steps = num_inference_steps # 25
         noise_aug_strength = 0
-        guidance_scale = 2.0
+        guidance_scale = guidance_scale # 2.0
         sample_stride = 2
-        fps = 16
-        seed = 42
+        fps = output_frames_per_second # 16
+        seed = seed # 42
     
         # Create the data structure
         data = {
             'base_model_path': 'stabilityai/stable-video-diffusion-img2vid-xt-1-1',
-            'ckpt_path': 'models/MimicMotion_1.pth',
+            'ckpt_path': f'models/{checkpoint_version}',
             'test_case': [
                 {
                     'ref_video_path': ref_video_path,
@@ -230,6 +230,7 @@ div#warning-ready > .gr-prose > h2, div#warning-ready > .gr-prose > p {
 with gr.Blocks(css=css) as demo:
     with gr.Column():
         gr.Markdown("# MimicMotion")
+        gr.Markdown("High-quality human motion video generation with pose-guided control")
         with gr.Row():
             with gr.Column():
                 if is_shared_ui:
@@ -250,30 +251,45 @@ with gr.Blocks(css=css) as demo:
                         </div>
                     ''', elem_id="warning-duplicate")
                 else:
-                    top_description = gr.HTML(f'''
-                            <div class="gr-prose">
+                    if(is_gpu_associated):
+                        top_description = gr.HTML(f'''
+                                <div class="gr-prose">
+                                    <h2 class="custom-color"><svg xmlns="http://www.w3.org/2000/svg" width="18px" height="18px" style="margin-right: 0px;display: inline-block;"fill="none"><path fill="#fff" d="M7 13.2a6.3 6.3 0 0 0 4.4-10.7A6.3 6.3 0 0 0 .6 6.9 6.3 6.3 0 0 0 7 13.2Z"/><path fill="#fff" fill-rule="evenodd" d="M7 0a6.9 6.9 0 0 1 4.8 11.8A6.9 6.9 0 0 1 0 7 6.9 6.9 0 0 1 7 0Zm0 0v.7V0ZM0 7h.6H0Zm7 6.8v-.6.6ZM13.7 7h-.6.6ZM9.1 1.7c-.7-.3-1.4-.4-2.2-.4a5.6 5.6 0 0 0-4 1.6 5.6 5.6 0 0 0-1.6 4 5.6 5.6 0 0 0 1.6 4 5.6 5.6 0 0 0 4 1.7 5.6 5.6 0 0 0 4-1.7 5.6 5.6 0 0 0 1.7-4 5.6 5.6 0 0 0-1.7-4c-.5-.5-1.1-.9-1.8-1.2Z" clip-rule="evenodd"/><path fill="#000" fill-rule="evenodd" d="M7 2.9a.8.8 0 1 1 0 1.5A.8.8 0 0 1 7 3ZM5.8 5.7c0-.4.3-.6.6-.6h.7c.3 0 .6.2.6.6v3.7h.5a.6.6 0 0 1 0 1.3H6a.6.6 0 0 1 0-1.3h.4v-3a.6.6 0 0 1-.6-.7Z" clip-rule="evenodd"/></svg>
+                                    You have successfully associated a {which_gpu} GPU to this Space 🎉</h2>
+                                    <p class="custom-color">
+                                        You will be billed by the minute from when you activated the GPU until when it is turned off.
+                                    </p> 
+                                </div>
+                        ''', elem_id="warning-ready")
+                    else:
+                        top_description = gr.HTML(f'''
+                                <div class="gr-prose">
                                 <h2 class="custom-color"><svg xmlns="http://www.w3.org/2000/svg" width="18px" height="18px" style="margin-right: 0px;display: inline-block;"fill="none"><path fill="#fff" d="M7 13.2a6.3 6.3 0 0 0 4.4-10.7A6.3 6.3 0 0 0 .6 6.9 6.3 6.3 0 0 0 7 13.2Z"/><path fill="#fff" fill-rule="evenodd" d="M7 0a6.9 6.9 0 0 1 4.8 11.8A6.9 6.9 0 0 1 0 7 6.9 6.9 0 0 1 7 0Zm0 0v.7V0ZM0 7h.6H0Zm7 6.8v-.6.6ZM13.7 7h-.6.6ZM9.1 1.7c-.7-.3-1.4-.4-2.2-.4a5.6 5.6 0 0 0-4 1.6 5.6 5.6 0 0 0-1.6 4 5.6 5.6 0 0 0 1.6 4 5.6 5.6 0 0 0 4 1.7 5.6 5.6 0 0 0 4-1.7 5.6 5.6 0 0 0 1.7-4 5.6 5.6 0 0 0-1.7-4c-.5-.5-1.1-.9-1.8-1.2Z" clip-rule="evenodd"/><path fill="#000" fill-rule="evenodd" d="M7 2.9a.8.8 0 1 1 0 1.5A.8.8 0 0 1 7 3ZM5.8 5.7c0-.4.3-.6.6-.6h.7c.3 0 .6.2.6.6v3.7h.5a.6.6 0 0 1 0 1.3H6a.6.6 0 0 1 0-1.3h.4v-3a.6.6 0 0 1-.6-.7Z" clip-rule="evenodd"/></svg>
-                                You have successfully associated a {which_gpu} GPU to this Space 🎉</h2>
-                                <p class="custom-color">
-                                    You will be billed by the minute from when you activated the GPU until when it is turned off.
-                                </p> 
-                            </div>
-                    ''', elem_id="warning-ready")
+                                You have successfully duplicated the MimicMotion Space 🎉</h2>
+                                <p class="custom-color">There's only one step left before you can properly play with this demo: <a href="https://huggingface.co/spaces/{os.environ['SPACE_ID']}/settings" style="text-decoration: underline" target="_blank">attribute a GPU</b> to it (via the Settings tab)</a> and run the app below.
+                                You will be billed by the minute from when you activate the GPU until when it is turned off.</p> 
+                                <p class="actions custom-color">
+                                    <a href="https://huggingface.co/spaces/{os.environ['SPACE_ID']}/settings">🔥 &nbsp; Set recommended GPU</a>
+                                </p>
+                                </div>
+                        ''', elem_id="warning-setgpu")
                 with gr.Row():
                     ref_image_in = gr.Image(label="Person Image Reference", type="filepath")
                     ref_video_in = gr.Video(label="Person Video Reference")
                 with gr.Accordion("Advanced Settings", open=False):
                     num_inference_steps = gr.Slider(label="num inference steps", minimum=12, maximum=50, value=25, step=1, interactive=available_property)
                     guidance_scale = gr.Slider(label="guidance scale", minimum=0.1, maximum=10, value=2, step=0.1, interactive=available_property)
-                    output_frames_per_second = gr.Slider(label="fps", minimum=1, maximum=60, value=16, step=1, interactive=available_property)
-                    seed = gr.Number(label="Seed", value=42, interactive=available_property)
+                    with gr.Row():
+                        output_frames_per_second = gr.Slider(label="fps", minimum=1, maximum=60, value=16, step=1, interactive=available_property)
+                        seed = gr.Number(label="Seed", value=42, interactive=available_property)
+                    checkpoint_version = gr.Dropdown(label="Checkpoint Version", choices=["MimicMotion_1.pth", "MimicMotion_1-1.pth"], value="MimicMotion_1.pth", interactive=available_property)
                 submit_btn = gr.Button("Submit", interactive=available_property)
                 gr.Examples(
                     examples = [
                         ["./examples/demo1.jpg", "./examples/preview_1.mp4"]
                     ],
                     fn = load_examples,
-                    inputs = [ref_image_in, ref_video_in],
+                    inputs = [ref_image_in, ref_video_in, num_inference_steps, guidance_scale, output_frames_per_second, seed, checkpoint_version],
                     outputs = [output_video],
                     run_on_click = True,
                     cache_examples = False