Vidu Q3 Pro Image to Video API

Vidu Q3 Pro Image-to-Video

Vidu Q3 Pro Image-to-Video transforms a reference image into a generated video clip with prompt-guided motion, controllable duration, resolution options, movement amplitude settings, and optional audio generation. It is designed for cinematic image animation, commercial visuals, social content, and other image-driven video generation workflows.

Why Choose This?

• Image-guided video generation Start from a reference image and generate motion while preserving the core scene, subject, and visual identity.

• Prompt-based motion control Use a text prompt to describe the motion, atmosphere, camera feel, and overall scene progression.

• Flexible movement intensity Adjust movement_amplitude to control how subtle or dramatic the motion should be.

• Optional audio generation Enable generated audio and optional background music for a more complete output.

• Multiple resolution options Choose between 540p, 720p, and 1080p depending on your quality and cost needs.

• Production-ready API Suitable for animated keyframes, marketing content, social video, concept visualization, and cinematic motion design workflows.

Parameters

Parameter	Required	Description
image	Yes	Reference image used as the starting visual input for video generation.
prompt	Yes	Positive prompt describing the desired motion, style, and scene behavior.
resolution	No	Output resolution: 540p, 720p (default), or 1080p.
duration	No	Video duration in seconds. Range: 1–16. Default: 5.
movement_amplitude	No	Motion intensity: auto, small, medium, or large. Default: auto.
generate_audio	No	Whether to generate audio. Default: true.
bgm	No	Whether to include background music in the generated output. Default: true.
seed	No	Random seed for reproducibility. Use -1 for random generation.

How to Use

1. Upload your image — provide the reference image you want to animate.
2. Write your prompt — describe the motion, scene progression, style, and atmosphere you want.
3. Choose resolution — use 540p, 720p, or 1080p based on your quality and budget needs.
4. Set duration — choose the desired video length between 1 and 16 seconds.
5. Adjust movement amplitude (optional) — use small, medium, or large, or leave it on auto.
6. Configure audio options (optional) — enable or disable generated audio and background music.
7. Set a seed (optional) — use -1 for random output, or a fixed seed for more reproducible generations.
8. Submit — run the model and download the generated video.

Example Prompt

A cinematic travel shot of a lone figure standing on a desert road at sunset, warm natural light, subtle wind moving clothing and dust, slow camera pullback, realistic motion, stable composition

Pricing

Pricing is based on duration and resolution.

Resolution	5s Cost	Per Second
540p	$0.25	$0.05
720p	$0.625	$0.125
1080p	$0.75	$0.15

Example Costs

Resolution	1s	5s	10s	16s
540p	$0.05	$0.25	$0.50	$0.80
720p	$0.125	$0.625	$1.25	$2.00
1080p	$0.15	$0.75	$1.50	$2.40

Billing Rules

• Base price is $0.25 per 5 seconds at 540p
• 720p costs 2.5× the base rate
• 1080p costs 3× the base rate
• Pricing scales linearly with duration
• movement_amplitude, generate_audio, bgm, and seed do not affect pricing

Best Use Cases

• Image animation — Turn still images into short video clips with controlled motion.
• Marketing creatives — Create animated hero visuals, ad content, and branded motion assets.
• Social media video — Generate short-form animated clips for posts, reels, and promotional content.
• Concept visualization — Bring keyframes, illustrations, or photo concepts to life with motion.
• Atmospheric storytelling — Add subtle camera motion and scene dynamics to still images.
• Audio-enabled video generation — Produce outputs with generated audio and background music for richer presentation.

Pro Tips

• Use a clean, high-quality reference image for better stability and subject preservation.
• Be specific in your prompt about motion, camera behavior, and atmosphere.
• Start with 540p or 720p for testing, then switch to 1080p for higher-quality final outputs.
• Use small or medium movement amplitude when you want more stable and natural animation.
• Keep large movement amplitude for scenes that can tolerate stronger motion.
• Reuse the same seed when you want more consistent variations.

Notes

• Both image and prompt are required.
• duration supports 1–16 seconds.
• resolution defaults to 720p.
• movement_amplitude defaults to auto.
• generate_audio and bgm default to true.
• seed uses -1 for random generation.
• Pricing depends only on duration and resolution.

Related Models

• vidu/q3-pro/start-end-to-video - Vidu video generation models may be useful when you need different quality, speed, or workflow trade-offs.