Consistency Examples
Educational Close-up
Steady framing with low variance.
- Pick your model's tab — the JSON re-shapes itself to that model's block order and limits.
- Click any green value to edit it in place — swap the subject, setting, or style for your own.
- Copy and paste the JSON as your prompt in the tool — links below.
{
"scene": "Bright classroom, neutral wall",
"subject": "Teacher at whiteboard, marker in hand",
"action": "Points to formula, nods once",
"camera": {
"lens_mm": 85,
"movement": "static",
"movement_speed": "normal"
},
"style": "Clean instructional, soft contrast",
"audio": "Light ambient classroom tone",
"technical": {
"aspect_ratio": "1:1",
"seed": 90214,
"lock_identity": true,
"lock_style": true,
"negative_prompt": "crowd, background text, decorative posters",
"duration_seconds": 8,
"fps": 24,
"creativity": 0.25
}
}- Veo 3.1 follows structured prompts unusually well — lock camera, lighting and audio as separate JSON fields and it respects each one.
- Native audio: describe dialogue, ambient sound and music directly in the audio field.
{
"subject": "Teacher at whiteboard, marker in hand",
"action": "Points to formula, nods once",
"scene": "Bright classroom, neutral wall",
"camera": {
"lens_mm": 85,
"movement": "static",
"movement_speed": "normal"
},
"style": "Clean instructional, soft contrast",
"audio": "Light ambient classroom tone",
"technical": {
"aspect_ratio": "1:1",
"seed": 90214,
"lock_identity": true,
"lock_style": true,
"negative_prompt": "crowd, background text, decorative posters",
"duration_seconds": 8,
"fps": 24,
"creativity": 0.25
}
}- Kling 3.0 reasons about the scene like a director — write the action field as a shot note, not a keyword list.
- Multi-shot is the signature feature: split the action into "Shot 1: … Shot 2: …" inside the action field for cuts within one generation.
{
"camera": {
"lens_mm": 85,
"movement": "static",
"movement_speed": "normal"
},
"subject": "Teacher at whiteboard, marker in hand",
"action": "Points to formula, nods once",
"scene": "Bright classroom, neutral wall",
"style": "Clean instructional, soft contrast",
"audio": "Light ambient classroom tone",
"technical": {
"aspect_ratio": "1:1",
"seed": 90214,
"lock_identity": true,
"lock_style": true,
"negative_prompt": "crowd, background text, decorative posters",
"duration_seconds": 8,
"fps": 24,
"creativity": 0.25
}
}- Seedance responds best to a strict block order: CAMERA → SUBJECT → ACTION → ENVIRONMENT → LIGHTING → STYLE. The JSON below is ordered to match.
- Keep the camera block to a shot type plus one movement — stacking movements degrades output.
{
"subject": "Teacher at whiteboard, marker in hand",
"action": "Points to formula, nods once",
"scene": "Bright classroom, neutral wall",
"camera": {
"lens_mm": 85,
"movement": "static",
"movement_speed": "normal"
},
"style": "Clean instructional, soft contrast",
"technical": {
"aspect_ratio": "1:1",
"seed": 90214,
"lock_identity": true,
"lock_style": true,
"negative_prompt": "crowd, background text, decorative posters",
"duration_seconds": 8,
"fps": 24,
"creativity": 0.25
}
}- Wan 2.2 is the latest version with genuinely open, downloadable weights. "Wan 2.5/2.6/2.7" are hosted API-only versions on commercial platforms.
- Open-weights Wan 2.2 has no audio track — drop the audio field or move sound design to post.
{
"subject": "Teacher at whiteboard, marker in hand",
"action": "Points to formula, nods once",
"camera": {
"lens_mm": 85,
"movement": "static",
"movement_speed": "normal"
},
"scene": "Bright classroom, neutral wall",
"style": "Clean instructional, soft contrast",
"technical": {
"aspect_ratio": "1:1",
"seed": 90214,
"lock_identity": true,
"lock_style": true,
"negative_prompt": "crowd, background text, decorative posters",
"duration_seconds": 8,
"fps": 24,
"creativity": 0.25
}
}- Runway exposes camera controls in the UI — use the camera block here as your settings checklist rather than prompt text.
- Gen-4.5 excels with reference images: the subject field doubles as your reference-tagging description.
Run this prompt
Copy the JSON above, then paste it as your prompt in any of these tools. Veo 3.1 is free to try inside Gemini (daily limit applies).
What each block does
| Block | Purpose |
|---|---|
| scene | Where it happens: location, time of day, weather, mood of the space. |
| subject | Who or what the shot is about. Keep it to one clear subject — models blur focus when given several. |
| action | What visibly happens during the clip. Describe motion the camera can see, not internal states. |
| camera | Shot framing and movement. One movement per clip reads best on every current model. |
| style | Aesthetic direction: film stock, color palette, references, tone. |
| audio | Dialogue, ambient sound and music. Only Veo 3.1, Kling 3.0 and Seedance 2.0 render audio natively. |
| technical | Render settings: aspect ratio, duration, fps, seed for reproducibility, negative prompt. |