Get the verdict
Same-prompt test 8 · video · October 2026

Origami crane unfolding and flying away: which AI does it best?

Kling 3.0 wins with 7.5/10. Behind it: Veo 3.1 Fast (6.8), PixVerse V6 (6.8), Runway Gen-4.5 (6.3). One 4-second clip per model, unedited, with whatever audio the model made.

The promptPaper origami crane unfolding itself and flying away, stop-motion style.
#ModelOveralladherencemotionqualityartifactsCostRender
1Kling 3.07.58787$0.52172s
2Veo 3.1 Fast6.85688$0.6047s
3PixVerse V66.85688$0.2144s
4Runway Gen-4.56.37666$0.4868s

Best per category: adherence Kling (8) · motion Kling (7) · quality Kling & Veo & PixVerse (8) · artifacts Veo & PixVerse (8)

Every output, ranked

#1 Kling 3.0

Kling 3.0 7.5
4s · audio · ~52 cr ($0.52) · 172s render

adherence 8motion 7quality 8artifacts 7
Unfolds from flat into a crane and takes off; stop-motion feel.

#2 Veo 3.1 Fast

Veo 3.1 Fast 6.8
4s · audio · ~60 cr ($0.60) · 47s render

adherence 5motion 6quality 8artifacts 8
Clean finished crane that lifts off; no unfolding, no stop-motion look.

#3 PixVerse V6

PixVerse V6 6.8
4s · audio · 48 PixVerse cr ($0.21) · 44s render

adherence 5motion 6quality 8artifacts 8
Clean finished crane that lifts off; no unfolding, no stop-motion look.

#4 Runway Gen-4.5

Runway Gen-4.5 6.3
4s · ~48 cr ($0.48) · 68s render

adherence 7motion 6quality 6artifacts 6
Paper rises and flies but folds look odd; grainy.

Try Kling ↗

⚖️
Outputs are shown exactly as the API returned them (4s, 720p, default settings). Scores are editorial judgments on a fixed rubric, given without knowing which model made each output. One run is a snapshot, not a guarantee. Methodology

FAQ

Which AI is best for "AI stop-motion origami video"?

In our October 2026 test of this exact prompt, Kling 3.0 wins with 7.5/10, ahead of Veo 3.1 Fast (6.8), PixVerse V6 (6.8), Runway Gen-4.5 (6.3). Kling 3.0's output: Unfolds from flat into a crane and takes off; stop-motion feel.

What exact prompt was used?

“Paper origami crane unfolding itself and flying away, stop-motion style.” Every model got the same prompt with default settings, 4 seconds at 720p, and one best-effort retry only if a generation failed.

How were the outputs scored?

Each output was scored without knowing which model made it, from 1 to 10 on adherence, motion, quality, artifacts. The overall score is the average of those.