🎬 PromptKits — AI Video Tools

AI Scene Builder
Every shot. Your way. Not the AI's guess.

Create an entire cinematic scene in one click.

✓ Locked character consistency ✓ Locked environment ✓ 15 professional camera shots ✓ Copy-ready prompts
About this demo
6 shots
One continuous scene, built shot by shot
2 characters
Appearance locked across every shot
180° rule
Camera never crosses the table axis
1 light source
Window on the LEFT — same in all 6 shots
The pipeline
1 · Scene Bible
Location, lighting & fixed elements filled once
2 · Reference stills
Generated in ChatGPT from the Reference Image tab prompts
3 · Video shots
Each prompt pasted into Kling AI with its reference
4 · The cut
Shots assembled in order — no colour fixing needed
📝 See the exact inputs used for this video
Scene description
Two old friends sit across from each other at a small corner table inside a quiet coffee shop, having a disagreement that has been coming for years. The light comes entirely from the window on the LEFT side throughout every shot.
Location
Small independent coffee shop, late afternoon. Round wooden table with two chairs, two ceramic coffee cups, bookshelf behind the right character, warm wooden interior, exposed brick on the far wall, open counter in the background, natural light through a single large window on the LEFT wall only.
Scene settings
Golden Hour · Warm Vintage grade · 2.39:1 Scope · Kodak 500T · Mood: Tense
Lighting
Single large window on the LEFT side only. Warm late-afternoon light raking left to right across both faces — left sides fully lit in warm amber, right sides in soft shadow. This direction never changes regardless of camera angle.
Atmosphere
Quiet and controlled. Other patrons in the background, but these two are completely inside their own world. Old friendship fraying at the edges. Neither raises their voice.
Fixed elements
Window light always on the LEFT wall — never moves. Left side of every face always lit warm amber, right side always in soft shadow. Two ceramic coffee cups on the table throughout. Bookshelf visible behind Daniel wherever he appears. Soft background blur of patrons in wide shots.
Character 1 — James
Late 30s, medium build, dark brown hair slightly messy, navy crew-neck sweater, slight stubble, arms folded on the table. The one who feels betrayed — controlled and precise, speaks quietly but every word is deliberate.
Character 2 — Daniel
Early 40s, lean, grey button-up with sleeves rolled, round wire-frame glasses, left hand wrapped around his coffee cup, looks tired. Defensive but not innocent — looks at his coffee more than at James.
Shots — 180-degree rule test
Camera stays on ONE side of the table throughout — never crosses the axis.
1 · Wide Establishing — 24mm, static. Both men at the table, window light on the left wall, axis established.
2 · OTS favouring James — 50mm, static. Over Daniel's right shoulder. "You knew for two years. Two years, Daniel."
3 · OTS favouring Daniel — 50mm, static. Over James's right shoulder. Daniel lifts his cup, doesn't answer.
4 · Close-Up James — 85mm, static. He unfolds his arms, places both hands flat on the table.
5 · Close-Up Daniel — 85mm, static. Lighting matches James exactly. He finally looks up.
6 · Two-Shot — 35mm, static. Both in profile from the right side. Warm rim on both left edges. The axis holds.
About this tool
AI Scene Builder

AI Scene Builder gives you director-level control over every shot in your AI video scene. Instead of asking your AI video tool — Kling AI, Runway, Veo, or any other model — to generate a full sequence automatically — where it invents the lens choices, the cutting rhythm, and the light direction — you define every technical decision yourself and generate each shot individually with professional cinematography language.

Every shot gets its own lens, camera movement, and action description. A shared Scene Bible feeds into every prompt automatically so your scene stays consistent from the wide establishing shot to the final resolved frame. Fixed Elements lock light direction, props, and background details globally across all shots.

Built by a working VFX artist with 12 years of industry experience — the same shot-by-shot approach used in professional film production.

Tips for better output
🔒 Lock the light direction in Fixed Elements
Light direction is the most common consistency failure. The AI will reinterpret it in every shot unless you lock it globally.
🖼 Reference image = previous shot's last frame
After generating a clip, pause at the last second and screenshot it. Use that as the reference for the next shot. Props, hands, clothing all carry over.
✂️ One action per shot description
Describe only what happens in this single moment. Multiple actions in one shot description causes the AI to generate a multi-shot sequence.
📐 Keep the camera on one side of the axis
For dialogue scenes, decide which side of the table/axis the camera stays on — and never cross it. Put this in Fixed Elements so every prompt respects it.
⏱ 5 seconds for statics, 10 for movement
Static shots work best at 5s. Any shot with camera movement — push in, pull back, tracking — needs 10s for the model to complete the movement cleanly.
Shot duration guide
Shot Duration Guide
Wide Establishing10s
OTS / Dialogue10s
Close-Up5s
Insert Shot5s
Camera Movement10s
Wide Resolved10s
💡 Built by a VFX pro
AI Scene Builder is built by a VFX artist with 12 years of industry experience. Every feature is based on real professional film production workflow.
Scene Bible
Film stock or camera system — affects grain, colour response, and overall texture of the image
Characters
Character 1
Reference Image (optional)

What gets extracted: appearance only — costume, clothing, hair, skin tone, physical build, accessories. The actual photo is never used — only the description it generates.

Reference
✓ Appearance extracted and filled
Character 2
Reference Image (optional)

What gets extracted: appearance only — costume, clothing, hair, skin tone, physical build, accessories. The actual photo is never used — only the description it generates.

Reference
✓ Appearance extracted and filled
Select Shots
Lens
Movement

AI video prompt for Kling AI or Runway — includes lens, movement, and action.

Midjourney reference image prompt — static frame, cinematic composition. Generate first, use as image reference in Kling AI for visual consistency.

Lens
Movement

AI video prompt for Kling AI or Runway — includes lens, movement, and action.

Midjourney reference image prompt — static frame, cinematic composition. Generate first, use as image reference in Kling AI for visual consistency.

Lens
Movement

AI video prompt for Kling AI or Runway — includes lens, movement, and action.

Midjourney reference image prompt — static frame, cinematic composition. Generate first, use as image reference in Kling AI for visual consistency.

Lens
Movement

AI video prompt for Kling AI or Runway — includes lens, movement, and action.

Midjourney reference image prompt — static frame, cinematic composition. Generate first, use as image reference in Kling AI for visual consistency.

Lens
Movement

AI video prompt for Kling AI or Runway — includes lens, movement, and action.

Midjourney reference image prompt — static frame, cinematic composition. Generate first, use as image reference in Kling AI for visual consistency.

Lens
Movement

AI video prompt for Kling AI or Runway — includes lens, movement, and action.

Midjourney reference image prompt — static frame, cinematic composition. Generate first, use as image reference in Kling AI for visual consistency.

Lens
Movement

AI video prompt for Kling AI or Runway — includes lens, movement, and action.

Midjourney reference image prompt — static frame, cinematic composition. Generate first, use as image reference in Kling AI for visual consistency.

Lens
Movement

AI video prompt for Kling AI or Runway — includes lens, movement, and action.

Midjourney reference image prompt — static frame, cinematic composition. Generate first, use as image reference in Kling AI for visual consistency.

Lens
Movement

AI video prompt for Kling AI or Runway — includes lens, movement, and action.

Midjourney reference image prompt — static frame, cinematic composition. Generate first, use as image reference in Kling AI for visual consistency.

Lens
Movement

AI video prompt for Kling AI or Runway — includes lens, movement, and action.

Midjourney reference image prompt — static frame, cinematic composition. Generate first, use as image reference in Kling AI for visual consistency.

Lens
Movement

AI video prompt for Kling AI or Runway — includes lens, movement, and action.

Midjourney reference image prompt — static frame, cinematic composition. Generate first, use as image reference in Kling AI for visual consistency.

Lens
Movement

AI video prompt for Kling AI or Runway — includes lens, movement, and action.

Midjourney reference image prompt — static frame, cinematic composition. Generate first, use as image reference in Kling AI for visual consistency.

Lens
Movement

AI video prompt for Kling AI or Runway — includes lens, movement, and action.

Midjourney reference image prompt — static frame, cinematic composition. Generate first, use as image reference in Kling AI for visual consistency.

Lens
Movement

AI video prompt for Kling AI or Runway — includes lens, movement, and action.

Midjourney reference image prompt — static frame, cinematic composition. Generate first, use as image reference in Kling AI for visual consistency.

Lens
Movement

AI video prompt for Kling AI or Runway — includes lens, movement, and action.

Midjourney reference image prompt — static frame, cinematic composition. Generate first, use as image reference in Kling AI for visual consistency.

Why AI Scene Builder

Auto Multi-Shot Mode

The AI decides everything

  • Random lens choices per cut
  • Unpredictable camera movement
  • Characters appear and disappear
  • Light direction changes between shots
  • No control over which moment gets a close-up
  • Props and background elements shift position
  • 180-degree rule frequently broken
  • Regenerating changes everything
Scene Builder — Shot by Shot

You decide everything

  • Exact lens for every shot
  • Specific camera movement per clip
  • Character appearance locked via reference image
  • Light direction fixed in every prompt via Fixed Elements
  • You choose which moment gets the close-up
  • Props and background locked globally
  • 180-degree rule maintained by design
  • Regenerate only the shots that need fixing

AI Scene Builder vs single prompt generation

Feature Single Prompt Auto Multi-Shot Scene Builder
Per-shot lens control
Per-shot camera movement
Character consistency✓ via reference image
Light direction locked✓ via Fixed Elements
Action / dialogue per shot
Regenerate individual shots
Midjourney reference output✓ per shot
180-degree rule control
Scene-wide prop consistency✓ via Fixed Elements

Why shot-by-shot control produces better AI video

AI video models are trained on enormous libraries of real cinematography. They understand lens compression, camera movement, depth of field, and lighting quality — but only when you give them the right language to work with. A prompt that says "cinematic shot of two people talking" gives the model nothing to anchor on. A prompt that specifies a 50mm lens, over-the-shoulder framing at eye level, camera locked off, single window light from the left, and a specific character expression — that gives the model a complete visual instruction it can execute with precision.

The fundamental problem with auto multi-shot generation is that the AI has to invent the editorial decisions that a human director would make. It invents the coverage, the cutting rhythm, the lens choices, and the light direction. Sometimes it gets lucky. More often, the result is generic — the kind of footage that looks like AI because no real director would cut that way.

Scene Builder is built on the opposite principle: the director makes every decision, and the AI executes it. You choose which moment gets the close-up. You decide when the camera pushes in. You lock the light source and the axis. The AI's job is to translate your visual instructions into a prompt that produces exactly the frame you designed.

Related Tools & Resources

🖼
Image Prompt Generator
Cinematic reference frames for your shots
🎬
Video Prompt Generator
Single clip prompts with camera movement
📚
Prompt Library
950+ ready-to-copy prompts
🎓
Learning Hub
17 free cinematic prompt lessons

Frequently asked questions

Why does the light direction keep changing between shots?

AI video models have no memory between clips — every shot is a fresh generation from scratch. It reinterprets your scene setup each time, including the light source position. The fix is the Fixed Elements field — write your light direction there and it gets injected into every single shot prompt automatically. Example: "Window light always from the LEFT wall — left side of every face always lit, right side always in shadow."

Why is the AI generating multiple cuts in one clip when I only want one shot?

This happens when the shot description contains more than one action or a sequence of events. The model reads narrative structure and creates cuts automatically. Keep the Action / Emotion / Dialogue field to a single moment — one gesture, one held expression, one action. For the Wide Establishing shot especially, describe only the starting state of the scene, not what will happen during it.

What's the best way to keep characters consistent across shots?

Two things work together: (1) Reference image — generate a reference frame for each shot in ChatGPT, Midjourney, or any image model and attach it in your video tool. (2) Previous shot's last frame — pause your last generated clip at the final second, screenshot it, and use that as the reference for the next shot. This carries over exact clothing, hand positions, and prop states. For large lens jumps (18mm to 85mm), generate a fresh reference image instead of using the previous frame.

Should I use 5 seconds or 10 seconds per shot?

5 seconds for static shots — close-ups, OTS coverage, insert shots, any shot where the camera is locked off. 10 seconds for shots with camera movement (push in, pull back, tracking, crane) or long dialogue sequences. The model needs the full duration to complete a movement cleanly. Going shorter on a movement shot gives you an incomplete camera move.

Why does my prop keep changing position between shots?

Add it to Fixed Elements with its exact position. Be specific: "Coffee cup always on the right side of the table in front of Character 2 — never moves." Also use the previous shot's last frame as your reference image — the prop position from the last clip carries into the next one.

What is the 180-degree rule and why does it matter?

The 180-degree rule means the camera always stays on one side of an imaginary line drawn between two characters. If the camera crosses this line, the characters appear to have swapped positions on screen — which breaks spatial continuity for the viewer. In Scene Builder, put this in Fixed Elements: "Camera always on the RIGHT side of the table axis — never crosses to the left side." Every shot prompt will then respect this rule.

Does Scene Builder work with Runway and other AI video tools?

Yes. The prompts are written in professional cinematography language that works across Kling AI, Runway Gen-4, Google Veo/Flow, Pika, and Hailuo. The use the Reference Image tab to generate an image prompt — works in ChatGPT, Midjourney, or DALL-E.

How is Scene Builder different from the Video Prompt Generator?

The Video Prompt Generator creates a single prompt for a single clip — good for standalone shots, hero moments, or social content. Scene Builder is for multi-shot scenes — it maintains a shared Scene Bible across all shots, locks consistency elements globally, and generates both a video prompt and a reference image prompt (for ChatGPT, Midjourney, or DALL-E) for each individual shot. Use Scene Builder whenever you need more than one clip to work together as a sequence.

How to use
1
Fill the Scene Bible
Describe the location in detail, set the time of day, lighting, atmosphere, colour grade, and mood.
2
Set Fixed Elements
Use the Fixed Elements field for anything that must stay consistent across every shot — prop positions, light source direction, background details.
3
Add Characters
Describe each character's appearance in detail — age, build, skin tone, hair, clothing, accessories.
4
Select and configure shots
Check the shots you want.
5
Generate Reference Image first
For each shot, use the Reference Image tab to generate a Midjourney prompt.
6
Generate Video Prompt and produce in Kling
Switch to the Video Prompt tab and generate.
More tips
🎬 Don't regenerate what works
If 5 of 7 shots are perfect, only regenerate the 2 that need fixing. Start with the hardest shots first — wide establishing and any shot with two characters moving.
👤 Translate dialogue into performance
Kling AI sees visuals, not words. Describe what the camera sees during the dialogue — not the words themselves.
🌅 Describe lighting quality not just type
Don't just say "golden hour" — describe the quality. AI video models respond to specific descriptions of what the light does to the scene.
🏠 Location detail prevents drift
The more specific your location description, the less the AI invents. Name specific details — wall colour, floor material, what's visible in the background.
Related tools
🖼 Image Prompt Generator 🎬 Video Prompt Generator 📚 Browse Prompt Library 🎓 Learning Hub