This Pull Request improves the interface for the user

app.py

@@ -61,13 +61,13 @@ frame_interpolation_model = load_rife_model("model_rife")
 
 sys_prompt = """You are part of a team of bots that creates videos. You work with an assistant bot that will draw anything you say in square brackets.
 
-For example , outputting " a beautiful morning in the woods with the sun peaking through the trees " will trigger your partner bot to output an video of a forest morning , as described. You will be prompted by people looking to create detailed , amazing videos. The way to accomplish this is to take their short prompts and make them extremely detailed and descriptive.
+For example, outputting " a beautiful morning in the woods with the sun peaking through the trees " will trigger your partner bot to output an video of a forest morning, as described. You will be prompted by people looking to create detailed, amazing videos. The way to accomplish this is to take their short prompts and make them extremely detailed and descriptive.
 There are a few rules to follow:
 
 You will only ever output a single video description per user request.
 
-When modifications are requested , you should not simply make the description longer . You should refactor the entire description to integrate the suggestions.
-Other times the user will not want modifications , but instead want a new image . In this case , you should ignore your previous conversation with the user.
+When modifications are requested, you should not simply make the description longer. You should refactor the entire description to integrate the suggestions.
+Other times the user will not want modifications, but instead want a new image. In this case, you should ignore your previous conversation with the user.
 
 Video descriptions must have the same num of words as examples below. Extra words will be ignored.
 """
@@ -331,37 +331,39 @@ with gr.Blocks() as demo:
            """)
     with gr.Row():
         with gr.Column():
-            with gr.Accordion("I2V: Image Input (cannot be used simultaneously with video input)", open=False):
-                image_input = gr.Image(label="Input Image (will be cropped to 720 * 480)")
-                examples_component_images = gr.Examples(examples_images, inputs=[image_input], cache_examples=False)
-            with gr.Accordion("V2V: Video Input (cannot be used simultaneously with image input)", open=False):
-                video_input = gr.Video(label="Input Video (will be cropped to 49 frames, 6 seconds at 8fps)")
-                strength = gr.Slider(0.1, 1.0, value=0.8, step=0.01, label="Strength")
-                examples_component_videos = gr.Examples(examples_videos, inputs=[video_input], cache_examples=False)
-            prompt = gr.Textbox(label="Prompt (Less than 200 Words)", placeholder="Enter your prompt here", lines=5)
+            with gr.Accordion("Media input (image or video, not both)", open=False):
+                with gr.Blocks() as media_input:
+                    with gr.Tab("I2V: Image Input"):
+                        image_input = gr.Image(label="Input Image (will be cropped to 720 x 480)")
+                        examples_component_images = gr.Examples(examples_images, inputs=[image_input], cache_examples=False)
+                    with gr.Tab("V2V: Video Input"):
+                        video_input = gr.Video(label="Input Video (will be cropped to 49 frames, 6 seconds at 8fps)")
+                        strength = gr.Slider(0.1, 1.0, value=0.8, step=0.01, label="Strength")
+                        examples_component_videos = gr.Examples(examples_videos, inputs=[video_input], cache_examples=False)
+            prompt = gr.Textbox(label="Prompt (less than 200 Words)", placeholder="Enter your prompt here", lines=5)
 
             with gr.Row():
                 gr.Markdown(
                     "✨Upon pressing the enhanced prompt button, we will use [GLM-4 Model](https://github.com/THUDM/GLM-4) to polish the prompt and overwrite the original one."
                 )
-                enhance_button = gr.Button("✨ Enhance Prompt(Optional)")
+                enhance_button = gr.Button("✨ Enhance Prompt (optional)")
             with gr.Group():
                 with gr.Column():
                     with gr.Row():
                         seed_param = gr.Number(
-                            label="Inference Seed (Enter a positive number, -1 for random)", value=-1
+                            label="Inference Seed (enter a positive number, -1 for random)", value=-1, minimum=-1
                         )
                     with gr.Row():
                         enable_scale = gr.Checkbox(label="Super-Resolution (720 × 480 -> 2880 × 1920)", value=False)
                         enable_rife = gr.Checkbox(label="Frame Interpolation (8fps -> 16fps)", value=False)
                     gr.Markdown(
-                        "✨In this demo, we use [RIFE](https://github.com/hzwer/ECCV2022-RIFE) for frame interpolation and [Real-ESRGAN](https://github.com/xinntao/Real-ESRGAN) for upscaling(Super-Resolution).<br>&nbsp;&nbsp;&nbsp;&nbsp;The entire process is based on open-source solutions."
+                        "✨In this demo, we use [RIFE](https://github.com/hzwer/ECCV2022-RIFE) for frame interpolation and [Real-ESRGAN](https://github.com/xinntao/Real-ESRGAN) for upscaling (Super-Resolution).<br>&nbsp;&nbsp;&nbsp;&nbsp;The entire process is based on open-source solutions."
                     )
 
-            generate_button = gr.Button("🎬 Generate Video")
+            generate_button = gr.Button(value = "🎬 Generate Video", variant = "primary")
 
         with gr.Column():
-            video_output = gr.Video(label="CogVideoX Generate Video", width=720, height=480)
+            video_output = gr.Video(label="CogVideoX Generate Video", width=720, height=480, autoplay = True)
             with gr.Row():
                 download_video_button = gr.File(label="📥 Download Video", visible=False)
                 download_gif_button = gr.File(label="📥 Download GIF", visible=False)