Add prompt prefix handling and update example generation parameters

app.py

@@ -14,6 +14,31 @@ TRANSFORMER_MODELS = [
     "finetrainers/cakeify-v0"
 ]
 
+# Model prefix mapping
+MODEL_PREFIXES = {
+    "sayakpaul/pika-dissolve-v0": "PIKA_DISSOLVE",
+    "finetrainers/crush-smol-v0": "DIFF_crush",
+    "finetrainers/3dgs-v0": "3D_dissolve",
+    "finetrainers/cakeify-v0": "PIKA_CAKEIFY"
+}
+
+def check_and_fix_prompt(transformer_model, prompt):
+    """Check and fix prompt according to model requirements"""
+    required_prefix = MODEL_PREFIXES.get(transformer_model)
+    if not required_prefix:
+        print(f"No required prefix found for model: {transformer_model}")
+        return prompt
+        
+    # Remove leading/trailing whitespace
+    prompt = prompt.strip()
+    
+    # Check if prompt already starts with the required prefix
+    if not prompt.startswith(required_prefix):
+        print(f"Adding required prefix '{required_prefix}' to prompt")
+        prompt = f"{required_prefix} {prompt}"
+    
+    return prompt
+
 def load_models(transformer_model):
     """Load transformer and pipeline models"""
     # Load the selected transformer model
@@ -40,7 +65,7 @@ def save_video(video_frames, fps=25):
         export_to_video(video_frames, tmp_file.name, fps=fps)
         return tmp_file.name
 
-@spaces.GPU
+@spaces.GPU(duration=1000)
 def generate_video_pipeline(pipeline, prompt, negative_prompt, num_frames, height, width, num_inference_steps):
     """Generate video using the pipeline"""
     # Move to appropriate device
@@ -64,6 +89,11 @@ def generate_video_pipeline(pipeline, prompt, negative_prompt, num_frames, heigh
 
 def generate_video(transformer_model, prompt, negative_prompt, num_frames, height, width, num_inference_steps):
     """Main function to handle the video generation process"""
+    # Check and fix prompt
+    print(f"Original prompt: {prompt}")
+    prompt = check_and_fix_prompt(transformer_model, prompt)
+    print(f"Final prompt: {prompt}")
+    
     # Load models
     pipeline = load_models(transformer_model)
     
@@ -153,25 +183,25 @@ def create_interface():
                     "sayakpaul/pika-dissolve-v0",
                     "PIKA_DISSOLVE A slender glass vase, brimming with tiny white pebbles, stands centered on a polished ebony dais. Without warning, the glass begins to dissolve from the edges inward. Wisps of translucent dust swirl upward in an elegant spiral, illuminating each pebble as they drop onto the dais. The gently drifting dust eventually settles, leaving only the scattered stones and faint traces of shimmering powder on the stage.",
                     "inconsistent motion, blurry motion, worse quality, degenerate outputs, deformed outputs",
-                    8, 32, 32, 10
+                    50, 224, 224, 50
                 ],
                 [
                     "finetrainers/crush-smol-v0",
                     "DIFF_crush A thick burger is placed on a dining table, and a large metal cylinder descends from above, crushing the burger as if it were under a hydraulic press. The bulb is crushed, leaving a pile of debris around it.",
                     "inconsistent motion, blurry motion, worse quality, degenerate outputs, deformed outputs",
-                    8, 32, 32, 10
+                    50, 224, 224, 50
                 ],
                 [
                     "finetrainers/3dgs-v0",
                     "3D_dissolve In a 3D appearance, a bookshelf filled with books is surrounded by a burst of red sparks, creating a dramatic and explosive effect against a black background.",
                     "inconsistent motion, blurry motion, worse quality, degenerate outputs, deformed outputs",
-                    8, 32, 32, 10
+                    50, 224, 224, 50
                 ],
                 [
                     "finetrainers/cakeify-v0",
                     "PIKA_CAKEIFY On a gleaming glass display stand, a sleek black purse quietly commands attention. Suddenly, a knife appears and slices through the shoe, revealing a fluffy vanilla sponge at its core. Immediately, it turns into a hyper-realistic prop cake, delighting the senses with its playful juxtaposition of the everyday and the extraordinary.",
                     "inconsistent motion, blurry motion, worse quality, degenerate outputs, deformed outputs",
-                    8, 32, 32, 10
+                    50, 224, 224, 50
                 ]
             ],
             inputs=[