JUN 26, 2026

Seedance 2.0 omni on PixVerse: real faces, driven by a reference video and audio

June 26, 2026

Seedance 2.0 keeps real human faces photoreal where many video models distort them, and PixVerse’s omni (Reference) mode now combines an image, a video, and an audio clip in one request. POST /videos/create-fusion accepts up to 9 reference images, 3 reference videos (@video1…@video3), and 3 reference audios (@audio1…@audio3), each addressed by an @-tag in the prompt.

Here we drop one person into another’s footage: take a studio portrait (@image1), replace the woman in a soccer-pitch clip (@video1) with her, and make her speak from an audio clip (@audio1). The same request runs on all three Seedance 2.0 tiers — seedance-2.0-mini, seedance-2.0-fast, and seedance-2.0 (Standard) — so you can compare the face fidelity directly.

The three references

A photo, a video, and an audio clip go in together:

@image1 — the face and identity to drop in.

@video1 — the scene, pose, ball, and motion to keep.

@audio1 — the speech to drive (about 2 seconds).

The prompt

Replace the woman in @video1 with @image1, keeping the exact same scene, soccer ball and movements, and make her say @audio1

First upload each file with POST /files to get its upload/… path, then pass those paths as frame_1_path, video_1_path, and audio_1_path. Only the model and quality change between the three runs below.

seedance-2.0-mini — 720p

curl — seedance-2.0-mini, 720p, omni image + video + audio

curl --location 'https://api.useapi.net/v2/pixverse/videos/create-fusion' \
--header 'Authorization: Bearer user:12345-…' \
--form 'model="seedance-2.0-mini"' \
--form 'prompt="Replace the woman in @video1 with @image1, keeping the exact same scene, soccer ball and movements, and make her say @audio1"' \
--form 'frame_1_path="upload/your-image.jpg"' \
--form 'video_1_path="upload/your-video.mp4"' \
--form 'audio_1_path="upload/your-audio.mp3"' \
--form 'quality="720p"' \
--form 'duration="4"' \
--form 'aspect_ratio="9:16"'

seedance-2.0-fast — 720p

curl — seedance-2.0-fast, 720p, omni image + video + audio

curl --location 'https://api.useapi.net/v2/pixverse/videos/create-fusion' \
--header 'Authorization: Bearer user:12345-…' \
--form 'model="seedance-2.0-fast"' \
--form 'prompt="Replace the woman in @video1 with @image1, keeping the exact same scene, soccer ball and movements, and make her say @audio1"' \
--form 'frame_1_path="upload/your-image.jpg"' \
--form 'video_1_path="upload/your-video.mp4"' \
--form 'audio_1_path="upload/your-audio.mp3"' \
--form 'quality="720p"' \
--form 'duration="4"' \
--form 'aspect_ratio="9:16"'

seedance-2.0 (Standard) — 1080p

Standard adds 1080p and 4K (2160p). Same omni request, higher resolution.

curl — seedance-2.0 (Standard), 1080p, omni image + video + audio

curl --location 'https://api.useapi.net/v2/pixverse/videos/create-fusion' \
--header 'Authorization: Bearer user:12345-…' \
--form 'model="seedance-2.0"' \
--form 'prompt="Replace the woman in @video1 with @image1, keeping the exact same scene, soccer ball and movements, and make her say @audio1"' \
--form 'frame_1_path="upload/your-image.jpg"' \
--form 'video_1_path="upload/your-video.mp4"' \
--form 'audio_1_path="upload/your-audio.mp3"' \
--form 'quality="1080p"' \
--form 'duration="4"' \
--form 'aspect_ratio="9:16"'

What it costs

Omni runs on the same credit model as the rest of PixVerse video — base × quality × seconds. On a Premium plan ($60/month → 15,000 credits at $0.004 each) this 4-second 9:16 clip costs:

Model	Quality	Credits	Cost (Premium)
seedance-2.0-mini	720p	56	~$0.22
seedance-2.0-fast	720p	80	~$0.32
seedance-2.0	1080p	240	~$0.96

Mini delivers the same omni capability — real faces, plus video and audio references — at roughly a quarter of the Standard-1080p credit cost, which makes it the natural default for iterating. Move up to Standard when you need 1080p or 4K. See the interactive cost calculator and Model Capabilities for the full per-model breakdown.

---

See the POST /videos/create-fusion reference for every @image / @video / @audio tag, the reference-media limits, and a live Try-It console.