Is Seedance 2.5 API available on SeeGen AI?
Yes. Seedance 2.5 (sd2.5) is available through the SeeGen AI Playground and API using model ID sd2.5.
Next-generation multimodal reference · native 1080p · up to 4K
Seedance 2.5 (sd2.5) is ByteDance Seed's next-generation professional multimodal video generation model. It supports native 30-second video generation, up to 50 multimodal reference inputs, professional video editing, and multilingual video creation. Seedance 2.5 improves visual consistency, prompt understanding, camera movement, and cinematic video generation quality for professional content creation.
Available workflows:
Seedance 2.5 supports image, video, and audio references for multimodal video generation.
| Modality | Limit | Formats | Constraints |
|---|---|---|---|
| Images | Up to 30 | JPEG, PNG, WebP, BMP, TIFF, GIF, HEIC, HEIF | Up to 4K resolution, max 30 MB each |
| Videos | Up to 10 | MP4, MOV | 480p–4K, max 200 MB each; each video 2–30s; total duration ≤ 30s |
| Audio | Up to 10 | MP3, WAV | Max 15 MB each; each file 2–30s; total duration ≤ 30s |
Note: Total reference assets across all modalities must not exceed 50.
| Parameter | Type | Default | Options / Description |
|---|---|---|---|
| prompt | string | — | Text description of scenes, actions, camera movements, and creative instructions. |
| urls | array | — | Reference image URLs. Supports up to 30 images. |
| videoUrls | array | — | Reference video URLs, up to 10. Must be asset:// URIs uploaded through the asset API — external video URLs are rejected. |
| audioUrls | array | — | Up to 10 audio URLs. Audio can be used as an independent reference input. |
| videoInputMode | enum | — | "keyframe" for image / first-last frame inputs, "reference" for multi-reference, edit, and extend. |
| mode | enum | — | Omit for standard generation. "edit" edits a reference video (pass exactly one and name it in the prompt); "extend" continues 1–3 reference videos in order. |
| duration | string | "5s" | Output duration, "4s"–"30s". Ignored when mode is "edit" — the output follows the source video length. |
| outputResolution | enum | "720p" | Output resolution tier: 480p, 720p, 1080p (all native) · 2k, 4k (automatic upscale). Higher tiers bill at a higher per-second rate. |
| resolution | enum | "auto" | Aspect-ratio preset: auto, 1280x720, 720x1280, 720x720, 960x720, 720x960, 1280x540. Required in reference mode, except mode "edit" / "extend", where the output follows the source video. |
| generateAudio | boolean | true | Generate a synced audio track (speech / SFX / BGM) alongside the video. |
| bitrateMode | enum | "standard" | Bitrate tier at the same resolution: standard or high. Does not affect price. |
| seed | integer | -1 | Optional seed for reproducible generation results. -1 generates a random seed. |
Seedance 2.5 API uses a pay-as-you-go credit system on SeeGen AI. The rates below use the $500 API Pack: 125,000 credits at $0.004 per credit.
| Condition | Rate | 10-sec clip |
|---|---|---|
| SD2.5 480p, no video input | 30 credits/sec (~$0.12/sec) | ~300 credits (~$1.20) |
| SD2.5 480p, with video input | 23 credits/sec (~$0.09/sec) | Based on output + reference video duration |
| SD2.5 720p, no video input | 60 credits/sec (~$0.24/sec) | ~600 credits (~$2.40) |
| SD2.5 720p, with video input | 45 credits/sec (~$0.18/sec) | Based on output + reference video duration |
| SD2.5 1080p, no video input | 150 credits/sec (~$0.60/sec) | ~1,500 credits (~$6.00) |
| SD2.5 1080p, with video input | 113 × (output + input) (~$0.45/sec) | Based on output + reference video duration |
| SD2.5 2K, no video input | 90 credits/sec (~$0.36/sec) | ~900 credits (~$3.60) |
| SD2.5 2K, with video input | 45 × (output + input) + 30 × output | Based on output + reference video duration |
| SD2.5 4K, no video input | 100 credits/sec (~$0.40/sec) | ~1,000 credits (~$4.00) |
| SD2.5 4K, with video input | 45 × (output + input) + 40 × output | Based on output + reference video duration |
1. No video input
credits = out × rate2. With video input
credits = (out + in) × rateout = output_seconds. in = the sum of ⌈duration⌉ for each input video. Each duration is rounded up, with a minimum input duration of ceil(out × 2 / 3). 480p, 720p, and 1080p are native output; 2K and 4K use upscaling-based pricing.
Generate a video in two steps: create a generation task, then query the result using the returned taskId.
curl -X POST \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "sd2.5",
"inputs": {
"videoInputMode": "reference",
"urls": [
"https://example.com/reference-image.jpg"
],
"videoUrls": [
"asset://asset-reference-video"
],
"audioUrls": [
"asset://asset-reference-audio"
],
"prompt": "Create a cinematic scene using the provided character, motion, and audio references.",
"duration": "10s",
"resolution": "1280x720",
"outputResolution": "720p",
"generateAudio": true
}
}' \
https://seegen.ai/api/v1/jobs/createTaskUse the returned taskId to check generation status and retrieve the completed video.
curl \
-H "Authorization: Bearer $API_KEY" \
"https://seegen.ai/api/v1/jobs/queryTask?taskId=YOUR_TASK_ID"asset:// URI. See the asset upload guide.| Use Case | 30-Second Generation | Multimodal References | Video Editing | Multilingual |
|---|---|---|---|---|
| Film & Entertainment | Complete scenes, long takes, and multi-shot storytelling | Combine multiple actors, characters, props, and environments | Replace actors or props, adjust expressions, and relight scenes | Create multilingual dubbed versions with lip-sync |
| Advertising & E-commerce | Generate TV commercials, brand stories, and product videos | Maintain consistent products, brand identity, and visual style | Replace SKUs, models, labels, and localized content | Produce localized ads and product videos |
| Education & Knowledge | Explain a concept or recreate a historical scene in one video | Visualize scientific principles and maintain consistent educational assets | Replace presenters and refine demonstration steps | Create multilingual lessons and narrated content |
| Industrial & Enterprise | Demonstrate complete workflows, operations, and maintenance procedures | Keep products, equipment, and production lines visually consistent | Update labels, specifications, packaging, and product variants | Generate multilingual training and instruction videos |
| Games & Virtual Content | Create CG trailers, narrative scenes, and episodic content | Combine virtual characters, environments, and real-world references | Modify character age, expressions, styles, and themed appearances | Produce multilingual virtual hosts and interactive content |
Seedance 2.5 can support professional video production across entertainment, advertising, education, industrial training, and virtual content workflows.
Seedance 2.5 expands Seedance 2.0 with longer video generation, more multimodal references, audio-only input, enhanced editing, and broader multilingual support.
| Feature | Seedance 2.5 | Seedance 2.0 |
|---|---|---|
| Maximum video duration | Up to 30 seconds | Up to 15 seconds |
| Reference inputs | Up to 50 total: 30 images, 10 videos, and 10 audio files | Up to 12 total: 9 images, 3 videos, and 3 audio files |
| Audio-only reference | Supported | Requires an image or video reference |
| Multilingual generation | 10+ languages | 8+ languages and dialects |
| Video editing | More precise editing, extension, and local changes | Video editing and extension supported |
| Visual consistency | Improved consistency across longer and more complex scenes | Strong consistency for shorter scenes |
Yes. Seedance 2.5 (sd2.5) is available through the SeeGen AI Playground and API using model ID sd2.5.
Seedance 2.5 supports video generation up to 30 seconds in a single task.
A single generation can use up to 50 reference assets: 30 images, 10 videos, and 10 audio files.
Yes. Seedance 2.5 supports audio as an independent reference for music-driven, rhythm-matched, and sound-aware video generation.
Seedance 2.5 uses pay-as-you-go credit pricing on SeeGen AI. Final cost depends on output resolution, output duration, and the duration of any reference videos. The rates shown above use the $500 API Pack rate of $0.004 per credit.
Yes. Real human image and video assets must first pass SeeGen AI’s official asset review before they can be used as references.

High-fidelity video · up to 4k

Faster & cheaper · 480p/720p native

Cheapest tier · 50% less Pro · 480p/720p native

Native audio · 720p/1080p native

Quality tiers · up to 4K

Fast generation · up to 4K

Highest quality · up to 4K

Fast generation · 2K/4K

High fidelity · 1K/2K