# ShotPlan: Cinematic Video Generation with Learnable Planning Token > Source: > Published: 2026-07-21 04:37:58+00:00 1Institute of Artificial Intelligence (TeleAI), China Telecom 2Harbin Institute of Technology *Equal contribution ShotPlan is built on Wan2.1-T2V-14B and changes nothing about the backbone's treatment of video tokens — planning happens entirely through a handful of extra tokens. Latents are patchified as usual; for a request like **hard cuts at frames 21, 46, 64**, three copies of the learnable planning embedding are appended with fractional temporal positions **6.00, 12.25, 16.75**. They attend jointly with visual tokens through every DiT block and are removed before unpatchify. Each transition type (hard cut, fade-in begin, fade-in end, camera move) owns a single learnable embedding `F` . It is replicated once per requested event and concatenated with the visual token sequence — no attention masks, no architectural surgery. The 3D VAE compresses time 4×, so integer latent positions can't express arbitrary frames. FRoPE gives each planning token a *fractional* temporal coordinate, letting it point between latent frames while video tokens keep standard RoPE. After the final DiT block the planning tokens are sliced off; only visual tokens are unpatchified and decoded. The tokens exist purely to steer denoising — the output video has the exact same shape as the base model's. `tu` maps to fractional latent time with temporal stride `st = 4` — e.g. frame 21 → position 6.00, frame 46 → 12.25, frame 64 → 16.75. All videos are generated at 832×480, 81 frames, from a single prompt with per-shot captions. Gold markers on each timeline show where each cut happens. Hover to play with sound off; videos loop. Timeline legend — **▮ gold ticks**: cut frames · ● teal dot: playback position · all clips are 81 frames. Two planning tokens — fade-in begin and fade-in end — bracket the transition window, producing a smooth dissolve between shots instead of a hard cut. A camera-movement planning token triggers a specific motion — circle, zoom, dolly, truck — at an exact frame inside one continuous take. The gold tick marks where the movement is scheduled to begin. For easier viewing, a blue box is drawn around the outer border of the video at the frame where the camera movement starts. On the multi-shot generation benchmark, ShotPlan cuts transition deviation to well under one frame while also leading on consistency and narrative coherence. | Method | Trans. Dev ↓ | Text Align ↑ | Char. Cons ↑ | Scene Cons ↑ | Narrative ↑ | |---|---|---|---|---|---| | CineTrans | 4.73 | 0.25 | 0.32 | 0.21 | 0.48 | | EchoShot | 6.95 | 0.26 | 0.31 | 0.23 | 0.51 | | HoloCine | 2.71 | 0.28 | 0.39 | 0.32 | 0.85 | | MultiShotMaster | 1.12 | 0.27 | 0.36 | 0.28 | 0.83 | | ShotPlan (Ours) | 0.64 | 0.26 | 0.46 | 0.37 | 0.88 |