Models / Kling / Reference to video

Kling reference to video prompting guide

How to prompt Kling in reference-to-video mode. Every point links its source; community tips are marked. Your agent gets the same guide through the Atlas MCP (get_guide).

Prompt structure

element bindings→action→scene→camera→audio

• Write prompts as directions to a scene, not object lists. Multi-shot (up to 6 shots): label each shot with framing, subject and motion. source ↗

What the text should describe

• Elements (frontal + reference images, or a video) referenced as @Element1, @Element2; extra style/appearance images as @Image1, @Image2. Max 4 total (elements + reference images) when using a video. source ↗
• On Higgsfield, add characters as Elements to lock identity; chain scenes using the final frame as the next start frame. source ↗

Camera vocabulary

• Shot language: profile shot, macro close-up, tracking shot, POV, shot-reverse-shot. Moves: slow push-in, dolly left, crane up, handheld, locked-off, orbit; lens feel 35mm/85mm. community source ↗
• Describe camera behaviour over time: tracking, following, freezing when the subject pauses, panning, moving in sync. source ↗

Responds well to

• Define core subjects at the start and keep their descriptions identical across shots. source ↗

Duration and limits

• Kling V3/O3 on fal: 3–15 s, up to 1080p; aspect 16:9, 9:16, 1:1. source ↗
• Longer durations risk drift (fal skill). community source ↗

Multi-shot

• multi_prompt list or shot_type 'intelligent'/'customize'; either prompt or multi_prompt, not both. source ↗

Avoid and failure modes

• Prefer direct declarative prompts; skip prestige adjectives; when negative_prompt is exposed list specific things, not vague ones. community source ↗

Negative prompt

Supported via negative_prompt (default: “blur, distort, and low quality”). source ↗

Real prompts, credited

@Element1 and @Element2 enters the scene from two sides. Elephant starts to play with the ball

Kling 4.0 Flash Prompt
[FORMAT]

Duration: 15 seconds
Aspect Ratio: 9:16
Style: premium cinematic photorealism, live-action fashion film, neo-gothic realism
Mood: cool, elegant, mysterious, deadpan comedy, subtle supernatural atmosphere
Visual quality: high-end luxury fashion commercial, realistic skin, realistic fabric, realistic rain and weather physics

No dialogue.
No subtitles.
No text.
No logos.
No watermark.

[CHARACTER REFERENCE]

Use the attached character sheet as the ONLY appearance reference for the female character.

Preserve her exact identity throughout the entire video.

CHARACTER APPEARANCE:

- young woman
- delicate pale skin
- refined symmetrical facial structure
- warm brown eyes
- short white bob haircut
- straight blunt bangs across the forehead
- white hair forming a clean rounded bob silhouette
- soft pink underlayer visible around the lower back and sides of the

Next

Sources

• blog.fal.ai/kling-3-0-prompting-guide/
• fal.ai/models/fal-ai/kling-video/o3/pro/reference-to-video/api
• fal.ai/models/fal-ai/kling-video/v3/pro/image-to-video/api
• github.com/fal-ai-community/skills/blob/HEAD/skills/fal-prompting/references/kling.md
• higgsfield.ai/creator-hub/help-center/ai-models/how-do-i-use-kling