By attribute · 9 models · 105 documented failure modes
Which AI video model gets hands right in close-up?
Hand-anatomy failure is documented across every model. Frame hands away from camera or expect to re-roll; no model has solved close-up finger topology.
Short answer
No AI video model reliably renders correct hands in close-up — hand-anatomy failure is documented across every covered model. Frame hands away from the camera, keep them moving, or expect to re-roll. As of 2026 no model has solved close-up finger topology, so it is a shot-design problem, not a model choice.
Hands are hard for the same reason text is: fingers have high articulation and the model has no skeleton, so close-ups expose extra or fused digits. Every covered model documents a hand-artifact failure. The practical fixes are compositional — keep hands in motion, partially occluded, or out of the focal plane — rather than hunting for a model that has solved it, because none has.
See the documented evidence: the failure in the catalogue, the full failure catalogue, or the overall consistency ranking.
Full context
Documented failure profile, every model
| Model | Documented modes | Holds best on | Documented weak spot |
|---|---|---|---|
| VeoGoogle Veo 3 | 13 | native audio, single-shot photoreal, lighting | long-prompt instruction drop, camera-motion-ignored on locked-off shots |
| RunwayRunway Gen-4 | 13 | character identity across cuts (Scenes mode) | hand anatomy on close-ups, prompt-ignored on dense prompts |
| SoraOpenAI Sora 2 | 12 | stylized motion (historically) | camera-control failures, multi-character interaction |
| SeedanceByteDance Seedance | 12 | short stylized clips | style-preset drift, motion drift over long clips |
| LumaLuma Dream Machine Ray-2 | 12 | lighting realism, atmospheric single takes | identity drift past ~3 cuts, camera-path drift |
| ViduVidu | 11 | reference-to-video character carry | motion plausibility, color drift |
| PikaPika 2.0 | 11 | stylized short-form, the closest Sora-style substitute | face distortion on long clips, motion failures |
| KlingKling 1.6 | 11 | human motion on simple single-subject shots | motion-blur overload, prompt adherence on complex scenes |
| HailuoHailuo MiniMax | 10 | expressive faces on close-ups | camera-shake artifacts, physics collapse |
Which model holds…
Pick by the thing that has to stay consistent
Holds a consistent face across cuts
Runway Gen-4
Runway Gen-4 Scenes mode is the only documented model built specifically to hold a character across multiple cuts; others drift after a few cuts.
Holds readable on-screen text
No model reliably does
Text rendering is a documented failure mode for every covered model — all garble past roughly six characters. Add text in post instead of relying on the model.
Holds cinematic lighting in a single take
Luma Ray-2
Luma Ray-2 documents the fewest lighting-related failures and leads on photoreal cinematic light for mood-led single-shot work.
Holds native audio with the video
Veo (Google Veo 3)
Veo is the only covered model with native audio generation; the rest produce silent video that needs separate audio.
Holds long, multi-instruction prompts
No model reliably does
Every model documents an instruction-drop / prompt-adherence failure that worsens as prompt length grows. Front-load must-haves and keep prompts short.