MASTER PROMPT NO. 1
Take on the role of a realistic environmental setting concept creator. Your objective is to produce 10 distinct location concepts inspired by extremely filthy, polluted, garbage-covered, and neglected surroundings.
IMPORTANT GUIDELINES:
• Each concept must be set in a different type of geographical setting, such as mountains, hills, riverbanks, canals, coastal regions, forests, city outskirts, industrial areas, or rural communities.
• Every concept must portray a severely polluted and trash-filled environment.
• Clearly detail visible signs of dirt and neglect, including heaps of garbage, sewage-filled water, damaged houses, muddy trails, air thick with smoke, scattered plastic waste, contaminated streams, or ruined landscapes.
• Concentrate solely on the present dirty and polluted state of the location.
• Do NOT refer to cleaning efforts, improvements, beauty, transformation, or any future changes.
OUTPUT REQUIREMENTS:
• Provide exactly 10 concepts.
• Each concept should be 4 to 6 lines in length.
• Clearly specify the type of setting in every concept (mountain, hill, river, canal, etc.).
• Use vivid, highly detailed, and realistic descriptions appropriate for cinematic AI image or video generation.
PROMPT NO. 2
Act as an expert cinematic AI image and video prompt engineer with a focus on environmental timelapse transformation storytelling. Your objective is to create 6 highly detailed cinematic prompts based on the location description provided below.
LOCATION DESCRIPTION:
[PASTE LOCATION IDEA HERE]
IMPORTANT GUIDELINES:
• The location description must be naturally integrated into all prompts.
• Maintain strong visual continuity across every stage.
• The environment, terrain, and geographical characteristics must remain consistent throughout.
• Prompts must be hyper-realistic, cinematic, and optimized for AI image and video generation.
• Camera angle must always remain straight and slightly elevated for both photos and videos.
• Clearly distinguish Photo prompts from Video prompts.
• Video transitions must be smooth, continuous timelapses with no abrupt cuts.
• Each timelapse video must be 8 seconds long.
PHOTO PROMPTS
PHOTO 1 — INITIAL STAGE (DAY, SLUM)
Hyper-realistic, cinematic, natural, photoreal.
Camera angle: straight + slightly elevated.
A wide cinematic view of the location in its most polluted and underdeveloped state, fully reflecting the provided description.
Must include:
• Severely damaged roads or terrain consistent with the location
• Heavy garbage accumulation and environmental destruction
• Broken or poorly built housing structures
• Dirty or contaminated water bodies if relevant
• Scattered debris and chaotic surroundings
• Construction workers in safety gear visible in the foreground
• Large construction equipment such as excavators or bulldozers
• Harsh midday sunlight with strong shadows
Mood: chaotic, neglected, underdeveloped
PHOTO 2 — MIDDLE STAGE (GOLDEN HOUR)
Hyper-realistic, cinematic, natural, photoreal.
Camera angle: straight + slightly elevated.
The same location during an active development phase.
Must include:
• Environment partially organized and completely clean (no garbage or dirt)
• Debris partially cleared
• Roads or terrain partially reconstructed
• Workers actively building or transporting materials
• Construction machinery still present
• Warm golden hour lighting with long shadows
• Light construction dust in the atmosphere
Mood: transitional, hopeful, industrious
PHOTO 3 — FINAL STAGE (NIGHT, MODERN)
Hyper-realistic, cinematic, natural, photoreal.
Camera angle: straight + slightly elevated.
The same location fully modernized, structured, and clean.
Must include:
• Completed modern infrastructure
• Finished roads
• Functional LED streetlights illuminating the area
• Clean and reflective water bodies if applicable
• Neatly arranged modern homes
• One standout modern two-story house with a balcony as the focal point
• A calm night setting with a deep blue sky
No workers.
No construction equipment.
VIDEO PROMPTS (TIMELAPSE — 8 SECONDS EACH)
VIDEO 1 — TIMELAPSE (PHOTO 1 → PHOTO 2)
Professional cinematic drone, hyper-realistic timelapse.
Duration: 8 seconds.
Camera: straight + slightly elevated, completely static.
Scene motion:
• Continuous timelapse transition from Photo 1 to Photo 2
• Workers move rapidly and machinery operates at accelerated speed
• Garbage piles gradually shrink and disappear frame by frame
• Roads and terrain visibly rebuild step by step
• Dust, smoke, and particles animate naturally
• Lighting smoothly shifts from harsh midday to warm golden hour
• Entire transformation occurs within the same frame, no cuts
VIDEO 2 — TIMELAPSE (PHOTO 2 → PHOTO 3)
Professional cinematic drone, hyper-realistic timelapse.
Duration: 8 seconds.
Camera: straight + slightly elevated, completely static.
Scene motion:
• Continuous timelapse transition from Photo 2 to Photo 3
• Buildings, roads, and infrastructure appear gradually frame by frame
• Workers and machinery slowly fade away
• Remaining debris disappears incrementally
• Streetlights power on gradually
• Water becomes clear and reflective
• Lighting transitions smoothly from golden hour to night
• Scene remains in one continuous frame
VIDEO 3 — DRONE ORBIT FINAL SCENE
Professional cinematic drone with a slow, smooth orbit.
Scene motion:
• Gentle cinematic orbit around the completed modern environment
• Emphasis on the prominent two-story house with balcony
• Reveal clean infrastructure and glowing streetlights from multiple angles
• Subtle environmental details such as light water reflections and soft breeze movement
Mood: peaceful, cinematic, aesthetically refined
Movement: smooth, continuous, professional
Disclaimer:
These prompts are for educational purposes only. Results may vary depending on AI tool, model updates, and your customization.
Step-by-Step Tutorial
Step 1: Generate Structured Location Ideas
Begin by using a master idea-generation prompt in ChatGPT. This should produce about 10 short, structured location concepts (4–5 lines each), such as a garbage-filled canal, an abandoned park, or a deteriorated street.
Why this is important:
Structured concepts eliminate randomness. Instead of guessing what to create, you select from clearly defined starting points.
Common beginner mistake:
Typing vague requests like “give me a video idea.” Always use a well-structured prompt to maintain consistency in your results.
Step 2: Expand One Idea into Detailed Prompts
Choose one concept you like and input it into a second master prompt in ChatGPT. This will transform your idea into six detailed prompts: three for still images and three for motion (video transitions).
Why this is important:
You’re crafting a visual progression—not just separate images. The sequence should clearly show: dirty → partially cleaned → fully transformed.
Common beginner mistake:
Skipping this structured step and attempting to describe everything directly in an image tool, which often leads to inconsistent visuals.
Step 3: Generate the First Image (Polluted Scene)
Copy the first image prompt and paste it into Wisk. Select a 9:16 aspect ratio if your goal is a short-form video. Create several variations and choose the one that best represents the polluted or messy version of your location.
Why this is important:
This image serves as your foundation—the emotional starting point of the transformation story.
Common beginner mistake:
Adding unnecessary edits or extra instructions inside the tool. Trust the original prompt structure.
Step 4: Generate the Second Image (Partially Cleaned Stage)
Upload your chosen first image as a reference. Then apply the second image prompt in Wisk or Gemini. This will produce a version of the scene where cleanup or development has begun.
Why this is important:
Using the first image as a reference preserves visual continuity, ensuring the setting looks like the same place evolving over time.
Common beginner mistake:
Creating a completely new image without referencing the original, which breaks consistency.
Step 5: Generate the Third Image (Fully Transformed Scene)
Repeat the process using the third image prompt. The final image should appear modern, organized, and visually upgraded—sometimes with a slightly futuristic feel.
Why this is important:
This is the highlight moment—the completed transformation that delivers impact.
Common beginner mistake:
Making the final result overly unrealistic. Audiences respond better to believable upgrades than fantasy-level changes.
Step 6: Convert Images into Video (Clip 1)
Upload Image 1 and Image 2 into Flow under the “Frame to Video” feature. Insert the first motion prompt (Image 1 → Image 2) and generate the clip.
Why this is important:
This creates smooth motion and natural transitions instead of a basic slideshow effect.
Step 7: Create the Second Video Clip (Middle to Final)
Upload Image 2 and Image 3 into Flow. Paste the second motion prompt and generate the next transition clip.
Step 8: Produce a Cinematic Ending (Clip 3)
Upload only the final image (Image 3) into Flow and apply the third motion prompt. This typically results in a slow, cinematic drone-style movement over the transformed location.
Step 9: Final Assembly in a Video Editor
Import all three clips into your preferred mobile editing app. Arrange them in sequence, add background music, and export at the highest possible resolution. No complex transitions are required—the AI-generated motion already provides smooth flow.
IDEAS PROMPT (For Polluted Location Concepts)
These are the master prompt used to generate structured video ideas focused on polluted environmental conditions. This is intended for educational purposes and can be modified to suit your preferred AI tool.