Models / Kling / Image to video

Kling image to video prompting guide

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

Prompt structure

evolution from image→subject motion→camera→environment change→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

• Treat the input image as the anchor; prompt only how the scene evolves (subtle movement, camera, environment). Identity, layout and on-image text are preserved. source ↗
• I2V template: '[MOTION — what moves, not what exists]. [STATIC ELEMENTS: what must remain fixed]. Camera: [MOVE].' Add an endpoint like 'then settles' / 'returns to starting position'. community source ↗

What not to describe

• Don't re-describe the image's contents. 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

The craftsman slowly examines the bowl, turning it gently in his weathered hands. His eyes reflect years of wisdom. Subtle smile forms on his face. Dust particles drift in warm light. Breathing motion, blinking eyes.

Same first frame, two models. Neither does both.  

Seedance hits harder and keeps her face. Kling moves her body more naturally. I went with force.  

Prompt tip: show the force, don't name it. Describe what each hit does, not how hard it is.  

Seedance 2.5 · 2 renders · ~$1.60 
Kling 3.0 · 1 render

Prompt 👇
One continuous 5-second shot. The first frame is the uploaded image: keep its framing, camera angle, her face, hair, outfit, the wooden mortar and the old wagashi shop as they are.
Camera: a phone held steady above and in front of her, looking down, the same framing as the first frame the whole time. The large wooden mortar fills the bottom of the frame and covers her below the waist throughout.
She is pounding mochi the traditional way, alone in the shop, and she hits it hard. Three heavy strikes in the five seconds. For each one she hauls the long straight wooden pole up with bo

Next

Sources

• blog.fal.ai/kling-3-0-prompting-guide/
• fal.ai/kling-3
• 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
• github.com/maciejdzierzek/kling-ai-prompt-generator/blob/main/README.md