In a softly lit kitchen, a man folds a paper crane with both hands, looks to his sister, and says, "I will be there this time." She takes the crane, smiles through tears, and replies, "Then we start again." Natural lip-sync, expressive fingers, steady medium two-shot.

Characters & Dialogue · default settings, one run, 5 s, 720p, 16:9 · Updated September 14, 2026

Not run yet
MiniMax FastH3 V2
P-Video 2 Pro
3.9videomodels.ai score
  • Prompt adherence4.0
  • Motion & consistency3.5
  • Camera & framing3.0
  • Quality & detail4.5
  • Look & lighting4.0
  • Realism & physics4.0
  • Text rendering—
  • Audio5.0

Accurate spoken exchange and crane work, but framing is tighter than the requested medium two-shot.

Wan 3.0
3.8videomodels.ai score
  • Prompt adherence3.5
  • Motion & consistency3.5
  • Camera & framing4.0
  • Quality & detail4.0
  • Look & lighting4.0
  • Realism & physics4.0
  • Text rendering—
  • Audio—

The paper crane and emotional kitchen scene are clear, with dialogue unverified.

Wan 3.0 Prime
4.0videomodels.ai score
  • Prompt adherence4.0
  • Motion & consistency4.0
  • Camera & framing4.0
  • Quality & detail4.0
  • Look & lighting4.0
  • Realism & physics4.0
  • Text rendering—
  • Audio—

Strong emotional two-shot with clean composition.

FastH3 V2
4.7videomodels.ai score
  • Prompt adherence5.0
  • Motion & consistency4.5
  • Camera & framing5.0
  • Quality & detail4.5
  • Look & lighting4.5
  • Realism & physics4.5
  • Text rendering—
  • Audio5.0

The complete emotional crane handoff and exact dialogue are delivered in a clean, steady two-shot.

Seedance 2.5
4.5videomodels.ai score
  • Prompt adherence4.5
  • Motion & consistency4.5
  • Camera & framing4.5
  • Quality & detail4.5
  • Look & lighting4.5
  • Realism & physics4.0
  • Text rendering—
  • Audio4.5

Excellent steady emotional handoff with only slight hand and crane softness.

Seedance 2.0
3.8videomodels.ai score
  • Prompt adherence4.0
  • Motion & consistency4.0
  • Camera & framing4.0
  • Quality & detail4.0
  • Look & lighting4.0
  • Realism & physics4.0
  • Text rendering—
  • Audio2.0

The warm crane exchange is clear, though the handoff has mild motion softness.

Seedance 2.0 Fast
3.8videomodels.ai score
  • Prompt adherence4.0
  • Motion & consistency4.0
  • Camera & framing4.5
  • Quality & detail4.5
  • Look & lighting4.5
  • Realism & physics4.0
  • Text rendering—
  • Audio1.0

A clear emotional crane handoff, though folding is mostly implied.

Kling 3.0 Turbo
4.6videomodels.ai score
  • Prompt adherence4.5
  • Motion & consistency4.5
  • Camera & framing5.0
  • Quality & detail4.5
  • Look & lighting4.5
  • Realism & physics4.5
  • Text rendering—
  • Audio5.0

A convincing complete handoff with matching dialogue and only minor hand blur.

Veo 3.1
4.0videomodels.ai score
  • Prompt adherence4.0
  • Motion & consistency3.5
  • Camera & framing4.0
  • Quality & detail4.0
  • Look & lighting4.0
  • Realism & physics3.5
  • Text rendering—
  • Audio5.0

Tender crane handoff is clear, but the origami and fingers shift during transfer.

Veo 3.1 Fast
4.3videomodels.ai score
  • Prompt adherence4.0
  • Motion & consistency4.0
  • Camera & framing4.5
  • Quality & detail4.5
  • Look & lighting4.5
  • Realism & physics4.0
  • Text rendering—
  • Audio5.0

Sharp, natural handoff and exact speech, with small crane geometry shifts.

Happy Horse 1.1
4.0videomodels.ai score
  • Prompt adherence4.0
  • Motion & consistency3.5
  • Camera & framing4.5
  • Quality & detail4.0
  • Look & lighting4.0
  • Realism & physics3.5
  • Text rendering—
  • Audio5.0

The complete spoken exchange lands, but tears and crane geometry are weak.

MiniMax H3
4.3videomodels.ai score
  • Prompt adherence4.0
  • Motion & consistency4.0
  • Camera & framing4.5
  • Quality & detail4.5
  • Look & lighting4.5
  • Realism & physics4.0
  • Text rendering—
  • Audio5.0

Strong stable two-shot and readable handoff; the crane transfer snaps slightly.

Gemini Omni Flash
4.0videomodels.ai score
  • Prompt adherence4.0
  • Motion & consistency3.5
  • Camera & framing4.0
  • Quality & detail4.0
  • Look & lighting4.0
  • Realism & physics3.5
  • Text rendering—
  • Audio5.0

The handoff and emotion read well, with shifting crane geometry and soft hands.

Wan 2.7
4.1videomodels.ai score
  • Prompt adherence4.0
  • Motion & consistency4.0
  • Camera & framing4.0
  • Quality & detail4.0
  • Look & lighting4.0
  • Realism & physics3.5
  • Text rendering—
  • Audio5.0

A coherent warm handoff, slightly weakened by changing origami and hand contact.

Grok Imagine Video
4.3videomodels.ai score
  • Prompt adherence4.0
  • Motion & consistency4.0
  • Camera & framing4.5
  • Quality & detail4.5
  • Look & lighting4.5
  • Realism & physics4.0
  • Text rendering—
  • Audio5.0

Warm, stable two-shot with only minor hand and crane inconsistencies.

P-Video 2
3.9videomodels.ai score
  • Prompt adherence3.5
  • Motion & consistency3.5
  • Camera & framing4.5
  • Quality & detail4.0
  • Look & lighting4.0
  • Realism & physics3.5
  • Text rendering—
  • Audio5.0

The dialogue and handoff work, but the woman reads older than a sister.

Runway Gen-4.5
3.7videomodels.ai score
  • Prompt adherence3.0
  • Motion & consistency4.0
  • Camera & framing4.0
  • Quality & detail4.0
  • Look & lighting4.0
  • Realism & physics4.0
  • Text rendering—
  • Audio—

The visual handoff is clear, but required spoken dialogue is entirely absent.

Hailuo 2.3
3.6videomodels.ai score
  • Prompt adherence3.0
  • Motion & consistency3.5
  • Camera & framing4.5
  • Quality & detail4.0
  • Look & lighting4.0
  • Realism & physics3.5
  • Text rendering—
  • Audio—

The handoff is readable, but the required dialogue and tears do not arrive.

Kling 2.6
3.7videomodels.ai score
  • Prompt adherence3.0
  • Motion & consistency3.0
  • Camera & framing4.5
  • Quality & detail4.0
  • Look & lighting4.0
  • Realism & physics3.5
  • Text rendering—
  • Audio5.0

The dialogue is exact, but folding is never clearly performed and motion is limited.

FLUX 3
4.0videomodels.ai score
  • Prompt adherence4.0
  • Motion & consistency3.5
  • Camera & framing4.5
  • Quality & detail3.5
  • Look & lighting4.0
  • Realism & physics3.5
  • Text rendering—
  • Audio5.0

It delivers the full exchange, though the darker image softens hand detail.

PixVerse V5
3.9videomodels.ai score
  • Prompt adherence3.0
  • Motion & consistency4.0
  • Camera & framing4.5
  • Quality & detail4.5
  • Look & lighting4.5
  • Realism & physics4.0
  • Text rendering—
  • Audio—

The handoff is clear, but folding and visible tears are weak or absent.

Seedance 1.5 Pro
3.9videomodels.ai score
  • Prompt adherence3.5
  • Motion & consistency3.5
  • Camera & framing4.5
  • Quality & detail4.0
  • Look & lighting4.0
  • Realism & physics3.5
  • Text rendering—
  • Audio5.0

The paper crane reads as a stylized pinwheel and tears are not visible.

FastH3
4.1videomodels.ai score
  • Prompt adherence3.5
  • Motion & consistency4.0
  • Camera & framing4.5
  • Quality & detail4.5
  • Look & lighting4.5
  • Realism & physics3.5
  • Text rendering—
  • Audio5.0

The dialogue matches exactly, though the folding is only lightly shown.

Cosmos 3 Super
3.5videomodels.ai score
  • Prompt adherence3.0
  • Motion & consistency3.5
  • Camera & framing4.0
  • Quality & detail3.5
  • Look & lighting4.0
  • Realism & physics3.0
  • Text rendering—
  • Audio—

The emotional crane offer is clear, but the woman never visibly takes it.

Lance
2.7videomodels.ai score
  • Prompt adherence1.0
  • Motion & consistency3.0
  • Camera & framing4.0
  • Quality & detail3.5
  • Look & lighting3.5
  • Realism & physics2.5
  • Text rendering—
  • Audio—

It substitutes two girls and an unclear paper object for the requested adult sibling exchange.

Wan T2V
3.8videomodels.ai score
  • Prompt adherence3.5
  • Motion & consistency3.5
  • Camera & framing4.5
  • Quality & detail4.0
  • Look & lighting4.0
  • Realism & physics3.5
  • Text rendering—
  • Audio—

The handoff is clear, but the crane folding and tears are not convincingly shown.

HunyuanVideo 1.5
3.5videomodels.ai score
  • Prompt adherence3.0
  • Motion & consistency4.0
  • Camera & framing2.5
  • Quality & detail4.0
  • Look & lighting4.0
  • Realism & physics3.5
  • Text rendering—
  • Audio—

The crane is never visibly handed over, and the shot begins as a close-up rather than a steady medium two-shot.

Happy Horse 1.0
4.7videomodels.ai score
  • Prompt adherence5.0
  • Motion & consistency4.5
  • Camera & framing5.0
  • Quality & detail4.5
  • Look & lighting4.5
  • Realism & physics4.5
  • Text rendering—
  • Audio5.0

The full crane handoff and tearful reconciliation play out cleanly in a steady two-shot.

Helios 14B
3.2videomodels.ai score
  • Prompt adherence1.5
  • Motion & consistency3.5
  • Camera & framing4.0
  • Quality & detail4.0
  • Look & lighting4.0
  • Realism & physics3.5
  • Text rendering—
  • Audio—

A convincing warm exchange, but it changes the sister to a child and skips folding.

Seedance 1.0 Pro Fast
4.2videomodels.ai score
  • Prompt adherence4.0
  • Motion & consistency4.0
  • Camera & framing4.5
  • Quality & detail4.5
  • Look & lighting4.5
  • Realism & physics4.0
  • Text rendering—
  • Audio—

A coherent crane exchange with stable framing; tears remain indistinct.

Wan 2.6
3.8videomodels.ai score
  • Prompt adherence3.5
  • Motion & consistency3.5
  • Camera & framing4.5
  • Quality & detail4.0
  • Look & lighting4.0
  • Realism & physics3.5
  • Text rendering—
  • Audio—

The warm handoff works, but folding and visible tears are largely absent.

Kling 3.0 Omni
4.2videomodels.ai score
  • Prompt adherence3.5
  • Motion & consistency4.0
  • Camera & framing4.5
  • Quality & detail4.5
  • Look & lighting4.5
  • Realism & physics4.0
  • Text rendering—
  • Audio5.0

The spoken lines match exactly, while folding and tears are only implied.

P-Video
3.6videomodels.ai score
  • Prompt adherence3.5
  • Motion & consistency3.5
  • Camera & framing3.5
  • Quality & detail4.0
  • Look & lighting4.0
  • Realism & physics3.5
  • Text rendering—
  • Audio—

Warm crane handoff, but the sister never visibly tears up.

Kling 2.5 Turbo
3.4videomodels.ai score
  • Prompt adherence2.0
  • Motion & consistency3.5
  • Camera & framing4.0
  • Quality & detail4.5
  • Look & lighting4.5
  • Realism & physics3.5
  • Text rendering—
  • Audio—

A polished handoff, but the crane is already made rather than folded on-screen.

Seedance 1.0 Pro
4.2videomodels.ai score
  • Prompt adherence4.0
  • Motion & consistency4.0
  • Camera & framing4.5
  • Quality & detail4.5
  • Look & lighting4.5
  • Realism & physics4.0
  • Text rendering—
  • Audio—

The crane transfer is elegant and coherent, but tears are not visible.

PixVerse V4.5
3.6videomodels.ai score
  • Prompt adherence3.0
  • Motion & consistency3.5
  • Camera & framing4.5
  • Quality & detail4.0
  • Look & lighting4.0
  • Realism & physics3.5
  • Text rendering—
  • Audio—

The exchange is clear, but captions conflict with and garble the requested dialogue.

PixVerse V4
3.7videomodels.ai score
  • Prompt adherence2.5
  • Motion & consistency3.5
  • Camera & framing5.0
  • Quality & detail4.5
  • Look & lighting4.5
  • Realism & physics3.5
  • Text rendering—
  • Audio—

Lovely stable staging, but folding is largely replaced by an already-made crane.

Hailuo 02
3.6videomodels.ai score
  • Prompt adherence3.5
  • Motion & consistency3.0
  • Camera & framing4.5
  • Quality & detail4.0
  • Look & lighting4.0
  • Realism & physics3.0
  • Text rendering—
  • Audio—

It completes the fold and transfer, but the paper shape jumps between folds.

Hailuo 01 Director
3.2videomodels.ai score
  • Prompt adherence1.5
  • Motion & consistency3.5
  • Camera & framing4.5
  • Quality & detail4.0
  • Look & lighting4.0
  • Realism & physics3.0
  • Text rendering—
  • Audio—

It substitutes a child and never completes the requested crane handoff.