Directing note: framing words first

Before any camera move, a shot needs a size and an angle: close-up or wide, low or high. They cost nothing and change what a shot means. As of 2026-09-25.

Only a few models' docs define shot sizes, but the words turn up in about half of them.

A move written without a framing word leaves the model to choose the size.

1From the docs

To manually specify the framing of the main subject within the video, use the Shot size dropdown menu to select an option.

Adobe, Firefly help: generate videos using text prompts

Close-up : frames the subject tightly, typically focusing on the face to emphasize emotions or a specific detail.

Google Cloud, Veo video prompt guide

AI-crafted cinematic moves like crash zooms and crane shots, fully controllable.

Higgsfield, camera controls

• Camera
  Shot size and camera angle menus, each option defined, from extreme close-up to a top-down shotAdobe, Firefly help: generate videos using text prompts / recorded 2026-09-25
• Camera angles and shot types
  Shot sizes and angles are defined one by one, from extreme close-up to wide, low-angle and dutch angleGoogle Cloud, Veo video prompt guide / recorded 2026-09-25
• Camera controls
  More than fifty named motion presets, from crash zooms to crane shots and bullet timeHiggsfield, camera controls / recorded 2026-09-25
• Demo prompts
  Camera movement is written into the prompt; the demo prompts circle, tilt and zoom the cameraTencent Hunyuan, HunyuanVideo-1.5 repository / recorded 2026-09-25
• Multi-shot examples
  Camera moves are written into each shot of the prompt, as in its tracking-shot examplesKling AI, VIDEO 3.0 model user guide / recorded 2026-09-25
• Style
  Shot Type style options, such as Close Up and Overhead, chosen by style IDLeonardo.Ai API docs, Motion 2.0 from text prompts / recorded 2026-09-25
• Structuring your prompt
  Detail is matched to shot scale: close-ups need more than wide shotsLTX, prompting guide / recorded 2026-09-25
• Precision in shot design
  Shot type, camera angle and framing are set for each shot in the shot editorLTX, Shot Video Editor platform page / recorded 2026-09-25

2Camera language in a pipeline

Where “Framing words first” has to be written by hand, SceneMixer's pipeline writes the shots; its guides explain:

Paste a scene or a short script and SceneMixer gives you a storyboard — numbered shots with framing and seconds — and then a moving version of each segment, which you can join into a rough cut of the scene.

SceneMixer, Using SceneMixer for Previs and Animatics Before a Live-Action Shoot (read 2026-10-13)

SceneMixer writes dialogue into the script analysis, assigns each line to a shot with a speaker and a short delivery note, and the video model performs it — picture and audio generated together, so the mouth forms that sentence in the language you chose.

SceneMixer, AI Dialogue Generator (read 2026-10-13)

3Other notes

• Pinning the last frame
• Saying what not to show

Examples are quoted from the models' docs; no model was run.