These are reusable skeletons, not finished prompts. Every [SQUARE BRACKET] is a blank you fill with your own words; delete any bracket you do not need. Copy one, swap the placeholders, and paste it straight into Kling 3.5 (or 2.5 Turbo for fast drafts).
Most text templates follow one order: Subject + one Action + Setting + Camera (shot size plus one move) + Lighting + Mood. Keep it to a single action per clip and set aspect ratio, resolution, and duration in the panel — never in the text. For the full roundup of ready-made prompts, see our best Kling prompts collection.
The master text-to-video template
Start here: the full formula as one editable skeleton. Fill every blank in order and you get a coherent single-shot clip.
1. Full-formula master template
[SUBJECT with 2-3 details], [ONE ACTION], in [SETTING]. [SHOT SIZE] shot, camera [CAMERA MOVE]. [LIGHTING]. [MOOD] mood.Fill in: [SUBJECT] = who or what, e.g. "a weathered fisherman in a yellow raincoat"; [ONE ACTION] = "hauls a net over the rail"; [SETTING] = "on a small trawler at dawn"; [SHOT SIZE] = wide / medium / close-up; [CAMERA MOVE] = one move only; [LIGHTING] and [MOOD] = tone words. (16:9, 1080p, 5s)
2. Minimal one-line template
[SUBJECT] [ACTION] in [SETTING], [SHOT SIZE] with a slow [CAMERA MOVE], [LIGHTING].Fill in: [SUBJECT] = main focus; [ACTION] = one verb phrase; [SETTING] = location; [SHOT SIZE] = framing; [CAMERA MOVE] = dolly in, pan, tilt, orbit; [LIGHTING] = light source and quality. Use this when you want fast, clean results without over-describing. (16:9, 1080p, 5s)
Cinematic & b-roll
These lean into camera language and light to produce film-look shots and cutaways. Keep the action gentle so motion stays stable.
3. Establishing wide shot
Extreme wide establishing shot of [PLACE], [ONE ELEMENT MOVING], [TIME OF DAY]. Camera slow drone ascending. [LIGHTING], [WEATHER]. Cinematic, [MOOD].Fill in: [PLACE] = "a fog-wrapped mountain village"; [ONE ELEMENT MOVING] = "smoke rising from chimneys"; [TIME OF DAY] = golden hour; [WEATHER] = light mist. Keep motion to a single element so the wide frame stays crisp. (16:9, 1080p, 10s)
4. Cinematic tracking b-roll
Medium tracking shot following [SUBJECT] as they [ACTION] through [SETTING]. Camera tracking alongside, shallow depth of field. [LIGHTING], [COLOR PALETTE] grade. [MOOD].Fill in: [SUBJECT] = "a courier on a bicycle"; [ACTION] = "weaves between market stalls"; [SETTING] = "a crowded old-town lane"; [COLOR PALETTE] = "warm amber and teal". Great for movement-driven cutaways. (16:9, 1080p, 8s)
5. Detail macro b-roll
Extreme close-up macro of [SUBJECT DETAIL], [SUBTLE ACTION]. Camera slow push-in, static background. [LIGHTING], soft focus falloff. [MOOD] mood.Fill in: [SUBJECT DETAIL] = "coffee crema swirling in a cup"; [SUBTLE ACTION] = "steam curling upward"; [LIGHTING] = "warm side light". Perfect for texture-rich inserts. (16:9, 1080p, 5s)
Product & ad
These frame a single product cleanly with controlled motion. For a full ad walkthrough, see our Kling product ad prompts.
6. Studio product turntable
[PRODUCT] centered on a [SURFACE], slowly rotating. Camera static, product turntable. Clean [BACKGROUND COLOR] studio background, soft [LIGHTING] with gentle reflections. Premium, minimal.Fill in: [PRODUCT] = "a matte-black wireless headphone"; [SURFACE] = "a polished stone slab"; [BACKGROUND COLOR] = "off-white"; [LIGHTING] = "soft key from upper left". (1:1, 1080p, 5s)
7. Product hero reveal
[PRODUCT] on [SURFACE], [SUBTLE PROP MOTION] around it. Camera slow dolly in toward the label. [LIGHTING], [COLOR ACCENT] rim light. Sleek, aspirational.Fill in: [PRODUCT] = "a glass perfume bottle"; [SUBTLE PROP MOTION] = "petals drifting down"; [COLOR ACCENT] = "gold"; [LIGHTING] = "dark moody key light". The push-in builds toward the brand. (16:9, 1080p, 8s)
8. Product in-use lifestyle
Close-up of [HANDS/PERSON] using [PRODUCT] to [ACTION] in [SETTING]. Camera handheld, shallow focus on the product. [LIGHTING], natural [MOOD].Fill in: [HANDS/PERSON] = "a woman's hands"; [PRODUCT] = "a ceramic pour-over kettle"; [ACTION] = "pour water in a slow spiral"; [SETTING] = "a sunlit kitchen". Handheld reads authentic for lifestyle. (9:16, 1080p, 6s)
Character & people
People need clear framing and one readable action. Add a Negative prompt for hands and warping. For consistent faces, keep a reference image in Elements.
9. Character portrait with emotion
Close-up portrait of [PERSON with 2-3 details], [ONE FACIAL ACTION], looking [DIRECTION]. Camera slow push-in, static. [LIGHTING]. [EMOTION] mood.Fill in: [PERSON] = "an older man with a grey beard and wool cap"; [ONE FACIAL ACTION] = "a slow, warm smile forming"; [DIRECTION] = "off-camera left"; [EMOTION] = "quiet, reflective". Negative prompt: extra fingers, warped face. (16:9, 1080p, 5s)
10. Character in action
Medium shot of [CHARACTER] [ONE ACTION] in [SETTING], wearing [WARDROBE]. Camera [CAMERA MOVE] to follow. [LIGHTING], [MOOD].Fill in: [CHARACTER] = "a young dancer"; [ONE ACTION] = "spins once and holds a pose"; [SETTING] = "an empty warehouse"; [WARDROBE] = "a flowing red dress"; [CAMERA MOVE] = "arc". One action keeps limbs stable. (16:9, 1080p, 6s)
11. Two-shot dialogue setup (silent base)
Medium two-shot of [PERSON A] and [PERSON B] in [SETTING], [PERSON A] [SUBTLE ACTION] while [PERSON B] listens. Camera static, shallow depth. [LIGHTING], [MOOD].Fill in: [PERSON A]/[PERSON B] = the two figures; [SUBTLE ACTION] = "leans in slightly". The base video is silent — add speech later with Lip Sync as a separate step. (16:9, 1080p, 8s)
Image-to-video & cinemagraph
With image-to-video the still already supplies the scene, so these skeletons are motion-only. Describe camera and movement, nothing else.
12. Image-to-video, gentle camera
Camera slowly [CAMERA MOVE]. [ONE SUBJECT] [SUBTLE MOTION]. Everything else stays still.Fill in: [CAMERA MOVE] = "dollies in" or "pans right"; [ONE SUBJECT] = "the woman's hair"; [SUBTLE MOTION] = "drifts in the breeze". Pairs with an uploaded still — see image-to-video prompts. (matches source, 1080p, 5s)
13. Image-to-video, subject enters motion
[SUBJECT] begins to [ACTION]. Camera [CAMERA MOVE]. Keep the background static.Fill in: [SUBJECT] = "the car"; [ACTION] = "drive forward slowly"; [CAMERA MOVE] = "tracks alongside". Motion-only keeps the source scene intact. (matches source, 1080p, 5s)
14. Cinemagraph (Motion Brush)
Only [MASKED AREA] moves: [SUBTLE LOOPING MOTION]. Everything else frozen. Camera static.Fill in: [MASKED AREA] = the region you paint with Motion Brush, e.g. "the waterfall"; [SUBTLE LOOPING MOTION] = "water flowing downward". Brush only that area for a clean cinemagraph loop. (matches source, 1080p, 5s)
15. Start & End Frame transition
Smooth transition from the first frame to the last: [WHAT CHANGES]. Camera [CAMERA MOVE], steady pacing.Fill in: [WHAT CHANGES] = "closed flower bud opens into full bloom"; [CAMERA MOVE] = "slow push-in". Upload both a start and end image so Kling interpolates between them. (matches source, 1080p, 5s)
Vertical social 9:16
Vertical clips need the subject centered and one punchy action for the first second. Keep camera moves short. For quick reference on framing, see the Kling cheat sheet.
16. Vertical hook shot
Vertical framing. [SUBJECT] centered, [BOLD ACTION] immediately. Camera fast push-in then settle. [LIGHTING], [HIGH-ENERGY MOOD].Fill in: [SUBJECT] = "a chef"; [BOLD ACTION] = "flips a pan of flaming vegetables"; [LIGHTING] = "warm kitchen glow"; [MOOD] = "energetic". Front-load the action to stop the scroll. (9:16, 1080p, 5s)
17. Vertical talking-head b-roll (silent)
Vertical medium close-up of [PERSON] [SUBTLE ACTION] in [SETTING]. Camera static, slight handheld sway. [LIGHTING], [MOOD].Fill in: [PERSON] = "a young creator"; [SUBTLE ACTION] = "nodding and gesturing lightly"; [SETTING] = "a plant-filled room". Add voice with Lip Sync afterward. (9:16, 1080p, 6s)
18. Vertical product flatlay motion
Vertical top-down of [PRODUCT] on [SURFACE], [PROPS] arranged around it, [SUBTLE MOTION]. Camera slow tilt down. [LIGHTING], clean and bright.Fill in: [PRODUCT] = "a skincare jar"; [SURFACE] = "marble"; [PROPS] = "eucalyptus sprigs"; [SUBTLE MOTION] = "a hand placing the jar down". Ideal for social product teasers. (9:16, 1080p, 6s)
19. Vertical POV walk-through
Vertical POV moving forward through [ENVIRONMENT], [ONE ELEMENT REACTING]. Camera handheld push-in, steady pace. [LIGHTING], [MOOD].Fill in: [ENVIRONMENT] = "a neon-lit night market"; [ONE ELEMENT REACTING] = "steam rising from food stalls"; [LIGHTING] = "colorful neon reflections". POV reads immersive on mobile. (9:16, 1080p, 8s)
Frequently Asked Questions
How do I use these Kling templates?
Copy a template, replace every [BRACKET] with your own words, delete any bracket you do not need, and paste the finished sentence into Kling. Set aspect ratio, resolution, and duration in the interface, not in the text.
What is the base Kling prompt formula?
Subject + one Action + Setting + Camera (shot size plus one move) + Lighting + Mood. Most text-to-video templates follow this order so Kling 3.5 has a clear scene and a single motion to render.
Should I put aspect ratio or duration in the prompt?
No. Aspect ratio, resolution, and clip length are settings you pick in the Kling panel. Writing --ar flags or 16:9 in the text does nothing and can confuse the model.
Why do image-to-video templates look so short?
With image-to-video the uploaded still already supplies the subject, setting, and lighting. Your prompt only needs to describe motion and camera, so those templates stay to one or two clauses.
How many actions should one template describe?
One clear action per clip. Kling 3.5 renders a single motion cleanly; stacking two or three actions causes warping. Chain multiple actions with Video Extension instead.
Do these work on Kling 2.5 Turbo?
Yes. The structure is identical. Turbo is the faster tier for drafts, while Kling 3.5 gives the best coherence and detail for final renders, so test cheaply on Turbo then finalize on 3.5.
What is a Negative prompt used for here?
The Negative prompt field lists what to avoid, such as extra fingers, warping, text, or watermark. It is separate from the main prompt and helps clean up common artifacts.