Davinci Magihuman Image To Video

Davinci Magihuman Image To Video

Playground

daVinci MagiHuman Image-to-Video API — a 15B parameter omni video generation model, the new open-source king on par with WAN 2.5. Generates high-quality AI videos from reference images with optional audio input. Supports digital humans, talking heads, and general video generation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Features

DaVinci MagiHuman Image-to-Video

DaVinci MagiHuman Image-to-Video animates a reference image into a cinematic, human-centered video clip. Upload a photo, describe the motion and scene, and optionally provide an audio track to synchronize — the model generates natural human movement, expressive storytelling, and a cinematic atmosphere across multiple resolution and duration options.

• Need to generate from text only? Try DaVinci MagiHuman Text-to-Video

Why Choose This?

• Image-grounded generation Start from a reference photo for precise visual control over character appearance, environment, and composition.

• Human-focused motion Optimized for realistic human motion, expressions, and interactions — ideal for portrait-style and character-driven video content.

• Audio input support Upload an audio track to guide the rhythm, mood, and pacing of the generated video for synchronized results.

• Multiple resolution tiers Generate at 256p, 720p, or 1080p to match your delivery requirements and budget.

• Flexible aspect ratio Supports 16:9 landscape and 9:16 portrait orientations for both cinematic and social media formats.

• Adjustable duration Generate clips from 5 to 10 seconds with per-second granularity.

• Reproducible results Use the seed parameter to lock in a specific output for exact reproduction.

Parameters

How to Use

1. Upload your image — provide the reference photo to animate via URL or drag-and-drop.
2. Write your prompt — describe the motion, camera movement, and scene atmosphere. Use the Prompt Enhancer for better results.
3. Upload audio (optional) — provide an audio file or URL to synchronize the video to a specific track.
4. Select aspect ratio — 16:9 for landscape/cinematic, 9:16 for portrait/social.
5. Select resolution — 256p for drafts, 720p for standard output, 1080p for final production.
6. Set duration — choose between 5 and 10 seconds.
7. Set seed (optional) — fix the seed to reproduce a specific result in future runs.
8. Submit — generate, preview, and download your video.

Pricing

Billing Rules

• 256p: $0.02 per second
• 720p: $0.03 per second
• 1080p: $0.04 per second
• Duration options: 5–10 seconds

Best Use Cases

• Photo Animation — Bring portraits and human-centered photos to life with natural, cinematic motion.
• Social Media Content — Produce portrait-format clips from reference photos for Reels, TikTok, and Shorts.
• Music Video & Audio-Visual — Synchronize animated portraits to a music track or voiceover.
• Marketing & Brand Video — Animate spokesperson or product model images for promotional content.
• Concept Visualization — Turn still reference images into moving scene previews for pitching and storyboarding.

Pro Tips

• Use a high-quality, well-lit reference image with a clearly visible subject for the most natural animation.
• Include specific camera style references in your prompt (handheld, dolly, cinematic lighting) for more expressive results.
• Use 256p at shorter durations to rapidly test prompts before committing to a 1080p final render.
• Providing an audio track significantly improves rhythm and pacing alignment in the output.
• Fix the seed once you find a result you like to iterate on it consistently.

Notes

• Both image and prompt are required fields; all other parameters are optional.
• Duration is selectable in 1-second increments from 5 to 10 seconds.
• Ensure image and audio URLs are publicly accessible if using links rather than direct uploads.

Related Models

• DaVinci MagiHuman Text-to-Video — Generate human-centered video from text prompts without a reference image.

# Submit the task
curl --location --request POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/davinci-magihuman/image-to-video" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}" \
--data-raw '{
    "aspect_ratio": "16:9",
    "resolution": "720p",
    "duration": 5,
    "seed": -1
}'

# Get the result
curl --location --request GET "https://api.wavespeed.ai/api/v3/predictions/${requestId}/result" \
--header "Authorization: Bearer ${WAVESPEED_API_KEY}"