Video · guidance updated 22 Nov 2026

Luma (Dream Machine / Ray) prompt guide

Ray 3.2: V2V production workhorse, 20s max source duration. Multi-keyframe i2v up to 64 keyframes at arbitrary frame indexes. Supports HDR, EXR export, Adherence (Motion/Structure 1–9), Character controls (Faces/Bodies/Poses). Start_frame/end_frame limited to 5s, no HDR.

Free. We don't store what you type.

How to prompt Luma (Dream Machine / Ray)

  1. Confirm goal, deliverable, usage, and priorities with agent before generating—have it summarize understanding and ask clarifying questions.
  2. Choose input strategy based on available assets: pure T2V, I2V with start/end anchors (5s only), V2V from source video, or multi-keyframe i2v for strongest control across arbitrary moments.
  3. For V2V, describe only target end-state look; Ray 3.2 preserves source motion and timing exactly, output duration matches source (up to 20s).
  4. Pin keyframes at exact source frame indexes before motion generation to lock style and consistency; use 1+ guide frames for each distinct moment.
  5. Create keyframes by exporting source frames, art-directing in Photoshop/Nuke or Luma's image tools, then feeding back at same indexes for production restyles.
  6. Use Adherence controls (Motion 1–9, Structure 1–9) to protect critical elements; increase Motion if movement drifts, increase Structure if layout changes too much.
  7. Toggle Character controls (Faces, Bodies, Poses) only for attributes that must survive; disable what you want freed to transform.
  8. Break longer content into 4–6 discrete moments; generate each with dedicated keyframes and focused prompt for consistency.
  9. Write prompts as declarative end-state descriptions ('brushed steel', not 'change to metal'); specify concrete camera, lighting, materials, and palette.
  10. Use positive phrasing only; remove negation ('no', 'not', 'without') from all prompts.
  11. Diagnose issues when iterating—classify into motion, camera, style drift, character drift, pacing—and fix highest-impact problems first.
  12. Generate multiple options in batches, compare side-by-side, and provide focused feedback citing what works, what doesn't, and specific adjustments needed.
  13. Export, art-direct, and iterate keyframes using external tools, then re-feed at same source indexes; use Enhance and inference modes (Speed vs Quality) to refine results.

The shape of a good prompt

V2V: [Source video (up to 20s) + keyframes at frame indexes] → prompt [target look: materials/palette/light/style]. Adherence: [Motion 1–9] [Structure 1–9]. Characters: [toggle Faces/Bodies/Poses on/off]. Multi-keyframe i2v: [keyframes[] + keyframe_indexes[]] + prompt [camera] of [subject] [action] in [environment]. I2V (5s only): [start_frame/end_frame] + prompt. T2V: [prompt describing camera, subject, materials, action, environment, light, palette].

Avoid

  • Imperative edit commands ('make', 'turn', 'change', 'fix') in V2V prompts.
  • Describing sequence of changes or story progression in V2V; prompt must express end-state only.
  • Negation ('no', 'not', 'without', 'avoid') anywhere in prompts.
  • Generic adjectives ('cinematic', 'dreamy', 'high quality', 'perfect') instead of concrete visual specifications.
  • Generating full 60–90s or long-form content in one pass; break into 4–6 moments with individual keyframes.
  • Skipping keyframes when consistency across moments matters; always pin guide frames at critical beats.
  • Using start_frame/end_frame (legacy path, 5s max, no HDR) when multi-keyframe i2v or V2V would provide stronger control.
  • Treating agent as vending machine; always define goal, confirm understanding, provide structured feedback, and iterate diagnostically.

Example

Request a runner in Tokyo at night

Slow tracking shot alongside a female runner in a black windbreaker on a quiet Tokyo backstreet at night. Wet asphalt mirrors soft pink and cyan neon signs; light rain falls through the glow of a single streetlamp. Shallow depth of field, anamorphic lens flares, teal-and-magenta palette, cinematic 35mm film grain.

The Weekly Tally

Useful updates, insights and no-hype advice. Read this week's digest.

One email a week. Unsubscribe in one click.