Vidu Q2 Reference-to-Video API by Vidu

Vidu Q2 Reference-to-Video

Vidu Q2 Reference-to-Video is a capable AI video generation model that generates video featuring specific subjects. Provide subject images alongside a motion prompt, and the model produces smooth, natural video that faithfully preserves each subject's appearance and identity — offering a strong balance of quality and cost for subject-driven workflows.

Why Choose This?

• Balanced quality and speed Solid visual consistency and motion quality at a mid-tier price point.

• Subject-driven generation Feature specific characters or objects with consistent appearance throughout the video.

• High resolution output Generate videos in 540p, 720p, or 1080p quality.

• Flexible duration Create videos from 1 to 10 seconds in length.

• Audio generation Optional audio with configurable type: full audio, speech only, or sound effects only.

• Prompt Enhancer Built-in tool to automatically improve your motion descriptions.

Parameters

How to Use

1. Upload your subject images — provide one or more images of the subjects to feature in the video.
2. Write your prompt — describe the motion, camera movement, and desired action.
3. Set resolution — higher resolution for better quality, lower for faster processing.
4. Adjust duration — set video length up to 10 seconds.
5. Configure audio (optional) — enable audio and select the audio type: all, speech_only, or sound_effect_only.
6. Set motion intensity (optional) — adjust movement_amplitude for subtle or dynamic animations.
7. Run — submit and download your video.

Pricing

Best Use Cases

• Character Consistency — Generate video featuring a specific character or subject across multiple scenes.
• Product Videos — Animate product imagery while maintaining accurate brand appearance.
• Style-Consistent Content — Produce video that matches the visual aesthetic of existing creative assets.
• Social Media Content — Create animated clips grounded in your existing image library.
• Concept Development — Explore reference-guided motion ideas quickly and affordably.

Pro Tips

• Use the Prompt Enhancer to refine your motion descriptions.
• Provide clear, well-lit subject images for the most consistent visual output.
• Be specific about movement direction, speed, and camera angles in your prompt.
• Use multiple subject images when the scene involves more than one character or object.
• Set audio_type to speech_only when the scene involves dialogue, or sound_effect_only for purely ambient audio.
• Start with 540p for previews and switch to 720p or 1080p for final output.

Notes

• Both prompt and subjects are required fields.
• Maximum video duration is 10 seconds.
• When generate_audio is true, audio_type controls what is generated: all includes speech and sound effects, speech_only generates voice audio, sound_effect_only generates ambient and environmental sounds.
• Ensure uploaded subject image URLs are publicly accessible.

Related Models

• Vidu Q2 Text-to-Video — Generate video directly from text descriptions without a reference image.
• Vidu Q2-Pro Reference-to-Video — Higher quality reference-guided video with 1080p support and extended duration.
• Vidu Q2-Pro-Fast Reference-to-Video — Pro quality reference-to-video with faster generation speed.