Access

AI video answer

How do I write an image-to-video API prompt?

Short answer

Keep the opening image facts, then write the subject motion, scene reactions, one camera path, timing, sound, and final frame. Put duration, resolution, model, and budget in API fields.

01

Protect the facts that cannot drift

Repeat only the identity, product, wardrobe, composition, or lighting facts that must remain stable. The image already carries most of the appearance.

Use direct language such as keep the label readable, preserve the red jacket, or maintain the centered composition.

02

Write motion in physical order

Describe the subject action first, then how cloth, hair, dust, water, light, or nearby objects react. Choose one camera move with a speed and relation to the subject.

The motion should fit the selected clip length and end in a pose the model can clearly stage.

03

Define the landing frame and sound

Name the final pose, framing, object positions, lighting, and camera stop. Add dialogue, ambience, effects, or music only when the selected route supports audio.

Keep duration, output size, seed, model, callback, and maximum cost in structured fields rather than prompt prose.

Related guide

Get the full context.

Image to video API for first frames, motion, and model routing

Compare image-to-video API routes, input rules, motion prompts, first and last frames, audio, prices, jobs, and output controls across five models.

Read the image to video API guide

Current prices

Compare each video route.

Open full pricing →
ModelCompared rateCre8vid price5 sec10 secSavings
MiniMax H3MiniMax$0.065$0.029$0.145$0.2955% less
Wan 3.0Alibaba$0.050$0.025$0.125$0.2550% less
Kling 3.0Kuaishou$0.084$0.039$0.195$0.3954% less
Seedance 2.5ByteDance$0.144$0.069$0.35$0.6952% less
Veo 3.1 Fast + audioGoogle$0.100$0.049$0.24$0.4951% less