Access

AI video answer

How do I prompt Sora 2 image to video?

Short answer

Use the image as the visual anchor, then describe only what changes: subject motion, environmental motion, camera movement, sound, and the final frame. Keep the source image matched to the intended output shape.

01

Read the starting image

Identify the subject, pose, composition, lighting, and objects that must remain stable. Do not spend the full prompt repeating details that the image already shows.

Make sure the source image fits the target output size and orientation before generation.

02

Separate three kinds of motion

State what the subject does, what moves in the environment, and how the camera moves. This stops a camera push from being confused with the person walking forward.

Use small linked actions with believable weight and timing instead of several unrelated motions.

03

Land on the final frame

Describe the ending pose, camera distance, object positions, and light. Stop the action once that frame is reached.

Place dialogue and sound beside the visible beat that creates them so the image, motion, and audio form one scene.

Related guide

Get the full context.

Sora 2 prompt guide, template, and examples

Use the official Sora 2 prompt structure for camera, action, lighting, dialogue, and sound, then adapt old Sora prompts to active AI video models.

Read the sora 2 prompt guide 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