{
 "slug": "framing-label",
 "name": "Framing label",
 "category": "composition",
 "group": "Rules",
 "media": [
  "image",
  "video"
 ],
 "checked": "2026-10-13",
 "effect": "One short line fixes the frame: how big, from which side, from which height, with which lens.",
 "use_when": "The opening line of any shot prompt; a shared language between the brief and the prompt.",
 "phrase": "medium shot, front three-quarter left, eye level, 35mm",
 "pitfalls": [
  {
   "text": "Sizes: close-up, medium, medium-wide, wide. Sides: front, front three-quarter, profile, rear three-quarter, back. Heights: ground level, eye level, high angle. Keep this order every time.",
   "evidence": "film-craft",
   "source": "Camera Control (aicameracontrol.com), its framing label read on 13 Oct 2026 by placing the subject in the 3D stage"
  },
  {
   "text": "Put the framing first in the prompt; without it a full figure is cropped to a portrait.",
   "evidence": "measured",
   "source": "Director Chair field notes on image prompting"
  }
 ],
 "per_model": [],
 "external_refs": [
  {
   "site": "aicameracontrol",
   "url": "https://aicameracontrol.com/",
   "what": "a free 3D stage to place the person and set the lens before you generate"
  },
  {
   "site": "shotdeck",
   "url": "https://shotdeck.com/",
   "what": "real film frames tagged by colour, lighting, time of day and composition (paid, link only)"
  },
  {
   "site": "flim",
   "url": "https://flim.ai/",
   "what": "film, ad and music-video stills to search by text or image (free tier, link only)"
  }
 ],
 "licensed": [],
 "site_names": [],
 "related": [
  "framing-first",
  "three-quarter-view",
  "rear-three-quarter-view",
  "ground-level"
 ],
 "rights": "own-work",
 "evidence": "film-craft",
 "source": {
  "url": null,
  "note": "Label structure from Camera Control (aicameracontrol.com), its framing label read on 13 Oct 2026 by placing the subject in the 3D stage"
 },
 "body": "## Values the Camera Control stage uses\n\nThe stage reads the framing off the 3D scene and writes it into its prompt. Its values, in our words:\n\n- **Size**, from how much of the frame the person fills: extreme close-up, close-up, medium close-up, medium, medium-wide, wide, extreme wide. Tighter sizes are paired with more skin detail and shallower focus, wider ones with deep focus.\n- **Side**: front, front three-quarter (left or right), profile (left or right), rear three-quarter (left or right), back.\n- **Height**: ground level, knee level, hip level, chest level, eye level, high angle, overhead.\n- **Lens**: a vertical field of view from 14 to 90 degrees, written as the nearest of 14, 18, 24, 28, 35, 50, 85, 100 or 135mm.\n- **Presets**: medium, wide, close-up, low angle, high angle, over the shoulder, two shot.\n- **Moves** (video): static, push in, pull out, pan, tilt, tracking, orbit, crane, handheld, crash zoom, dolly zoom, whip pan, aerial, or your own.\n- **Staging**: one or two people, each placed left or right, nearer or further, and turned; a pose per person; a rule-of-thirds overlay; a shot view and a plan view from above.\n- **Sheets**: a character sheet or an environment sheet can stand in for the written subject and place.",
 "shown_with": null,
 "url": "https://directorchair.ai/composition/framing-label",
 "markdown": "https://directorchair.ai/composition/framing-label.md",
 "prompts": {
  "nano-banana-pro": "[your subject] in [your setting]. Medium shot, front three-quarter left, eye level, 35mm.",
  "nano-banana-2": "[your subject] in [your setting]. Medium shot, front three-quarter left, eye level, 35mm.",
  "gpt-image": "A photograph of [your subject] in [your setting].\nPeople and framing: medium shot, front three-quarter left, eye level, 35mm\nExclusions: no extra text, no watermark, no logo.",
  "seedream-5": "[your subject] in [your setting]. Medium shot, front three-quarter left, eye level, 35mm.",
  "seedance-2.5": "Scene: [your subject] in [your setting].\nFirst frame: medium shot, front three-quarter left, eye level, 35mm\nShot 1 (0:00 to 0:05): one continuous shot",
  "seedance-2.0": "Scene: [your subject] in [your setting].\nFirst frame: medium shot, front three-quarter left, eye level, 35mm\nShot 1: one continuous shot",
  "kling-3": "[your subject]. The scene is [your setting]. Medium shot, front three-quarter left, eye level, 35mm.",
  "veo-3.1": "Medium shot, front three-quarter left, eye level, 35mm. [your subject] in [your setting]. Framing and subject stay as in the start image."
 },
 "licence": {
  "code": "MIT",
  "text": "CC BY 4.0",
  "third_party": "Clips and card texts inside a \"licensed\" block belong to their makers and are shown with permission and credit."
 }
}