How to Prompt a Push-In (Dolly In) Shot in AI Video
Last updated: October 12, 2026
The push-in is the most useful camera move in filmmaking. The camera travels slowly toward the subject, and the audience leans in with it. It signals that something matters: a decision, an emotion, a detail you should not miss.
It is also one of the easiest moves for AI video to get right, as long as you ask for a physical camera move rather than a zoom. A zoom flattens the image; a dolly push creates parallax, with the background and foreground separating as the camera travels.
When to use it
- Emotional beats, like a character realizing something or making a choice.
- Building tension before a reveal or a cut.
- Product hero shots that move toward the logo or a key detail.
- Opening shots that pull the viewer into a scene.
How to write the prompt
1. Ask for a dolly, not a zoom. Write "camera dollies forward toward the subject on a locked track". The word zoom often produces a flat digital crop instead of real camera movement.
2. Mention parallax. Add that foreground and background separate as the camera moves. Parallax is what makes the push feel physical and three-dimensional.
3. Keep it slow. Slow pushes feel cinematic and are much less likely to warp. Fast pushes read as a crash zoom and often distort faces.
4. Give the camera a destination. Say where the push ends, such as a close-up on the eyes or the watch face. A clear endpoint keeps the framing intentional.
5. Hold the subject steady. Let the camera do the moving. A still or nearly still subject keeps identity and proportions stable across the clip.
Copy-ready example
Subject: A young chess player staring at the board, one move from winning. Generate the keyframe image first, then use it as the start frame for your video with the motion layer as the video prompt. Add the negative block wherever your tool accepts one.
A young chess player staring at the board, one move from winning. medium hero shot, subject framed from mid-torso up, heroic and commanding presence, shot on a 50mm prime lens, natural human-eye perspective with clean, undistorted rendering, moody film-noir chiaroscuro, hard directional key light, deep crushed shadows and high-contrast modeling, 16:9 landscape aspect ratio. Photorealistic, cinematic color grade, high dynamic range, sharp focus.
Camera move: steady forward dolly push-in along the Z-axis, camera translating toward the subject on a locked track, slow, tense creeping pace, deliberate and suspenseful timing. foreground and background planes separate with dynamic parallax, depth compression building as distance closes. strict frame-to-frame identity lock, subject features, wardrobe and proportions held perfectly consistent. Animate only the camera and environment, not the subject's core features.
Negative: blurry, low quality, distorted, deformed, extra limbs, disfigured, watermark, signature, jpeg artifacts, text errors, bad anatomy, flickering, temporal inconsistency, morphing artifacts, warping, ghosting. Style: cinematic film grain, anamorphic character, high dynamic range, professional color grade.
Common mistakes
- Writing "zoom in" and getting a flat crop instead of a camera move.
- Pushing too fast, which warps faces and fine detail.
- No endpoint, so the camera drifts aimlessly.
- A busy subject moving in the opposite direction of the camera.
Try it with your own scene
CineCue builds every prompt layer for you. Open it with this setup, describe your own subject, adjust the options, and copy the result into your AI tool.