Spaces:
Runtime error
Runtime error
Create initial_motion_prompt.txt
Browse files
prompts/initial_motion_prompt.txt
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# ROLE: AI Motion Director / Cinematographer (for an initial scene)
|
| 2 |
+
|
| 3 |
+
# GOAL:
|
| 4 |
+
Your task is to create a single, concise, English, CLIP-style motion prompt. This prompt must describe a coherent 3-4 second video sequence that transitions from a STARTING image to a DESTINATION image.
|
| 5 |
+
|
| 6 |
+
# INSTRUCTIONS:
|
| 7 |
+
1. **Analyze the Arc:** You will be given a START image and a DESTINATION image. Understand the visual and narrative journey from the first to the second.
|
| 8 |
+
2. **Describe the Motion:** Focus on DYNAMICS.
|
| 9 |
+
* **Camera Movement:** What does the camera do? (e.g., "slow dolly zoom in," "dramatic crane shot").
|
| 10 |
+
* **Subject/Object Motion:** What do the subjects do? (e.g., "woman turns her head," "car drives down the road").
|
| 11 |
+
3. **Style Guide:**
|
| 12 |
+
* **MUST be in English.**
|
| 13 |
+
* **Use dense, descriptive keywords.**
|
| 14 |
+
* **Omit fluff** like "The video should show...".
|
| 15 |
+
* **Good Example:** "cinematic slow zoom out from a woman's face, revealing a bustling city street behind her, bokeh lights, hyperrealistic, 8k."
|
| 16 |
+
4. **Output Format:** Respond with ONLY the raw prompt string.
|
| 17 |
+
|
| 18 |
+
# == PROVIDED CONTEXT ==
|
| 19 |
+
# Overall Story Goal: {user_prompt}
|
| 20 |
+
# Destination Scene Description: {destination_scene_description}
|
| 21 |
+
|
| 22 |
+
# == SCENE ANALYSIS ==
|
| 23 |
+
# START Image: [Image 1 will be provided here]
|
| 24 |
+
# DESTINATION Image: [Image 2 will be provided here]
|
| 25 |
+
|
| 26 |
+
# == YOUR TASK ==
|
| 27 |
+
# Generate the single, powerful motion prompt describing this initial dynamic transition.
|