Vidu Q1 Reference-to-video
مرجع إلى فيديو

Vidu Q1 Reference-to-Video API by Vidu

vidu/q1/reference-to-video
Reference-to-video

Vidu Q1 Reference-to-Video is an advanced AI video generation model that brings static images to life. Upload a reference image and describe the motion you want — the model generates high-quality video with smooth animation, optional audio, and cinematic quality up to 1080p.

Vidu Q1 Reference-to-Video

Vidu Q1 Reference-to-Video is an efficient AI video generation model that generates video featuring specific subjects. Provide subject images alongside a motion prompt, and the model generates a 5-second 1080p video that faithfully preserves each subject's appearance, style, and identity — fast and at an accessible price point.

Why Choose This?

  • Fast generation Optimized for quick turnaround with minimal wait time.

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

  • 1080p output Generate videos in full 1080p high definition quality.

  • 5-second videos Produces crisp, fixed-length 5-second videos ready to share.

  • 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

ParameterRequiredDescription
promptYesText description of the desired motion and action
subjectsYesOne or more subject images to feature in the video (URL or upload)
resolutionNoOutput quality: 1080p
durationNoFixed video length of 5 seconds
aspect_ratioNoAspect ratio of the output: 16:9 (default), 9:16, 1:1, 4:3, 3:4
movement_amplitudeNoMotion intensity: auto (default), small, medium, large
generate_audioNoWhether to generate audio for the video (default: true)
audio_typeNoAudio type when generate_audio is true: all (default), speech_only, sound_effect_only
seedNoSeed for generation (default: 0); use -1 for a random seed

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. Configure audio (optional) — enable audio and select the audio type: all, speech_only, or sound_effect_only.
  4. Set motion intensity (optional) — adjust movement_amplitude for subtle or dynamic animations.
  5. Run — submit and download your video.

Pricing

ResolutionCost
1080p$0.4

Best Use Cases

  • Character Consistency — Generate video featuring a specific character or subject across scenes.
  • Product Videos — Animate product photos while preserving brand appearance.
  • Style-Consistent Content — Produce video that matches the visual aesthetic of existing assets.
  • Social Media Content — Create engaging animated clips based on your existing image library.
  • Rapid Prototyping — Quickly explore reference-guided video concepts before committing to higher-quality generation.

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.
  • Describe environmental elements (lighting, background) in the prompt to guide the scene composition.

Notes

  • Both prompt and subjects are required fields.
  • Video duration is fixed at 5 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.

استكشف نماذج مماثلة

واجهة برمجية واحدة لكل وسائط الذكاء الاصطناعي.

استكشف جميع النماذج

Join our Discord community

Join the Discord community for the latest model updates, prompts, and support.