Seedance 2.5 Omni Reference: AI Image-to-Video Generator
Blend images, video, and audio into one video with Seedance 2.5 Omni Reference. 720p, 30-second clips. Try free — pay per generation, no subscription.
Blend images, video, and audio into one video with Seedance 2.5 Omni Reference. 720p, 30-second clips. Try free — pay per generation, no subscription.
About this model
Seedance 2.5 Omni Reference is the early-access multi-reference endpoint in the Seedance 2.5 family, blending up to 20 reference images, 6 video clips, and 6 audio files into a single guided video generation. Use the images to steer environment and style, the videos for camera motion and rhythm, and the audio as a mood reference — all combined via one text prompt. Supports clips up to 30 seconds at 720p.
Cost analysis
| Provider | Cost | Notes |
|---|---|---|
| muapiapp | $0.72/sec (720p) or $0.36/sec (480p) | Pay-per-generation pricing with no subscription. |
| Fal.ai | Not available | Seedance 2.5 is not listed on Fal.ai. |
| Replicate | Not available | Seedance 2.5 is not listed on Replicate. |
Pay-per-generation pricing with no subscription.
Seedance 2.5 is not listed on Fal.ai.
Seedance 2.5 is not listed on Replicate.
* Competitor pricing is estimated based on similar model architectures and usage tiers.
Configuration schema
| Parameter | Type | Description | Default |
|---|---|---|---|
| Prompt | string | Text prompt describing the desired video, referencing the provided images, video clips, and audio as environment, motion, and mood cues. | Create a calm cinematic park sequence. Use the images for environment style, the video clips for camera motion and street rhythm, and the audio as mood reference. |
| Reference Images | array | Reference image URLs. Up to 20 images. | undefined |
| Reference Videos | array | Reference video URLs. Up to 6 clips. | undefined |
| Reference Audio | array | Reference audio URLs. Up to 6 files. | undefined |
| Duration | int | The duration of the generated video in seconds. | 5 |
| Aspect Ratio | Enum (7 options) | Aspect ratio of the output video. | 16:9 |
| Seed | int | Random seed for reproducible generation. Use -1 for random. | 42 |
Text prompt describing the desired video, referencing the provided images, video clips, and audio as environment, motion, and mood cues.
Create a calm cinematic park sequence. Use the images for environment style, the video clips for camera motion and street rhythm, and the audio as mood reference.Reference image URLs. Up to 20 images.
undefinedReference video URLs. Up to 6 clips.
undefinedReference audio URLs. Up to 6 files.
undefinedThe duration of the generated video in seconds.
5Aspect ratio of the output video.
16:9Random seed for reproducible generation. Use -1 for random.
42Developer documentation
Gather Your References
images_list, 6 videos via videos_list, 6 audio files via audios_list. At least one reference is recommended.Write a Guiding Prompt
Configure Output
duration (4–30s), aspect_ratio, and optionally seed.Submit via the API
curl -X POST https://api.muapi.ai/api/v1/seedance-2.5-omni-reference \
-H "x-api-key: YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"prompt": "Create a calm cinematic park sequence using the references for style, motion, and mood.",
"images_list": ["https://example.com/ref1.jpg", "https://example.com/ref2.jpg"],
"videos_list": ["https://example.com/ref.mp4"],
"duration": 10
}'
GET /api/v1/predictions/{request_id}/result until status is completed, then retrieve the video URL from output.Frequently asked
It generates video guided by a combination of reference images, video clips, and audio files, blending their style, motion, and mood cues into one output.
Up to 20 images, 6 video clips, and 6 audio files, via `images_list`, `videos_list`, and `audios_list` respectively.
Processing multiple reference modalities together adds computational overhead, so Omni Reference is priced at 1.2x the base rate: $0.72/sec at 720p or $0.36/sec at 480p.
720p by default. A cheaper 480p variant is available separately.
Between 4 and 30 seconds, configurable via the `duration` parameter.
No — provide any combination of images, videos, and audio. A text prompt alone still works, but references help steer style, motion, and mood more precisely.