Seedance

Seedance is ByteDance’s video generation model family, developed by the team behind Doubao and the Seedream image models. It is built for fast, prompt-faithful video generation: a short prompt produces a coherent clip, with resolution and duration limits depending on the model, with strong adherence to camera-direction language (“dolly in”, “tracking shot”, “static”) and good motion stability across frames.

Architecture

Seedance is a Diffusion Transformer (DiT) trained jointly on text-to-video and image-to-video objectives. Two design choices stand out for API users:

• Decoupled spatial and temporal layers — the model alternates spatial-attention blocks (per-frame composition) with temporal-attention blocks (cross-frame motion). This split lets it learn fine-grained appearance and physics independently, which produces fewer flicker artifacts on textures like fur, fabric, and water than single-stream architectures.
• Multi-shot training — Seedance is trained on multi-shot sequences, so a single prompt that describes a brief sequence of actions (“the dog runs to the camera, then leaps over the puddle”) tends to produce a continuous shot that follows the described beats rather than a single static motion.

Variant comparison

The older Seedance 1.0 jobs on Prodia include Pro and Pro Turbo. Pro Turbo is the default starting point for almost all use cases; Pro exists for cases where you need maximum quality and are willing to pay more for it.

Feature	Pro Turbo	Pro
Job type prefix	inference.seedance.proturbo.*	inference.seedance.pro.*
Resolutions	480p, 1080p	480p, 1080p
Aspect ratios (txt2vid)	16:9, 9:16, 1:1, 4:3, 3:4, 21:9	16:9, 9:16, 1:1, 4:3, 3:4, 21:9
Duration	5s or 10s	5s or 10s
Generation time	~45s	~60s
Cost (1080p, 5s)	lower (around half of Pro)	higher

Pro Turbo — the recommended default. A distillation/optimization tier with the same API surface as Pro and ~25% faster generation. The quality difference for typical prompts is small enough that Pro Turbo is the right choice unless you have a specific reason to pay more.

Pro — full-quality variant. Useful when you have a finished prompt that didn’t quite render the way you wanted on Pro Turbo and you want one more pass with the higher-quality model before iterating on the prompt.

Note

A lite variant (inference.seedance.lite.*) is also exposed, but it reached end of life on 2026-04-30. Migrate to a supported Pro or Pro Turbo job type and use its documented parameters.

When to use Seedance

Use case	Job type	Why Seedance
Short cinematic clip from a prompt	proturbo.txt2vid	~45s generation at 1080p, strong camera-direction prompting
Animating a hero image / product shot	proturbo.img2vid	Faithful starting frame + natural motion in 5s
Loopable social content	proturbo.txt2vid with aspect_ratio: 9:16	Native portrait support for TikTok/Reels
Final-pass quality on a locked prompt	pro.txt2vid / pro.img2vid	Slightly higher fidelity than Pro Turbo at higher cost

Seedance 2.0, Fast, Mini, and 2.5 support first/last frame inputs through img2vid and image/video/audio references through ref2vid. The older Pro and Pro Turbo jobs accept a first-frame image. See the model-specific limits and job types below.

Job types

Job type	Description	ETA
inference.seedance.proturbo.txt2vid.v1	Text-to-video, Pro Turbo	~45s
inference.seedance.proturbo.img2vid.v1	Image-to-video from a starting frame, Pro Turbo	~45s
inference.seedance.pro.txt2vid.v1	Text-to-video, Pro	~60s
inference.seedance.pro.img2vid.v1	Image-to-video from a starting frame, Pro	~60s

Note

For asynchronous video generation, submit to POST /v2/job/async and poll GET /v2/job/async/:id/job.state.current until it returns processed, then download output/video.mp4. See the async reference and the polling async jobs guide for the full flow.

Parameters

Common to the Pro and Pro Turbo job types listed above:

• prompt (required) — text description of the desired clip, 3–4,096 characters
• resolution — "480p" or "1080p" (default: "1080p"). Exact width/height varies with aspect ratio.
• duration — 5 or 10 seconds (default: 5)
• camera_fixed — true to discourage camera motion (default: false, not guaranteed)
• watermark — true to add an “AI-generated” watermark (default: false)
• seed — integer for reproducible results

Text-to-video only:

• aspect_ratio — "16:9" (default), "9:16", "1:1", "4:3", "3:4", or "21:9"

Image-to-video only:

• first_frame — filename of the starting frame, supplied as a multipart form file. Aspect ratio of the output follows the input image.

Prompting tips

• Describe the motion, not just the scene — Seedance is trained to follow camera and subject-motion language. A prompt like "slow dolly in on the puppy, shallow depth of field" produces noticeably more intentional motion than "a puppy".
• Use camera_fixed on Pro and Pro Turbo for product shots — when you want the subject to move but the camera held still (e.g. a rotating product on a tabletop), set camera_fixed: true and describe the subject motion in the prompt.
• Match aspect ratio to platform — 9:16 for TikTok/Reels/Shorts, 16:9 for YouTube/landing pages, 1:1 for Instagram feed, 21:9 for cinematic banners.
• 480p is genuinely useful for iteration — 480p costs roughly a fifth of 1080p and finishes in the same wall time. Iterate on prompts at 480p, then switch the same prompt to 1080p for the final render.
• Short, declarative prompts beat long ones — Seedance handles 1–2 sentence prompts well. Very long prompts tend to get partially ignored; if you need to describe a sequence of actions, separate beats with commas rather than long subordinate clauses.

Examples

Text-to-video at 1080p, 16:9, 5 seconds:

{
  "type": "inference.seedance.proturbo.txt2vid.v1",
  "config": {
    "prompt": "a golden retriever puppy running through a field of wildflowers in slow motion, cinematic lighting, hyperrealistic",
    "resolution": "1080p",
    "aspect_ratio": "16:9",
    "duration": 5
  }
}

Sample frame from the generated clip (480p preview shown for size):

Vertical 9:16 clip for TikTok/Reels with a fixed camera:

{
  "type": "inference.seedance.proturbo.txt2vid.v1",
  "config": {
    "prompt": "a barista pouring latte art into a cup, steam rising, warm morning light",
    "resolution": "1080p",
    "aspect_ratio": "9:16",
    "duration": 5,
    "camera_fixed": true
  }
}

Image-to-video — animate a still frame with a described camera move. The first_frame field names the file, which is uploaded alongside the job as multipart form-data:

job.json

{
  "type": "inference.seedance.proturbo.img2vid.v1",
  "config": {
    "first_frame": "cyberpunk-input.jpg",
    "prompt": "the camera slowly pushes forward through the cyberpunk market, neon signs flicker, people walk by",
    "resolution": "1080p",
    "duration": 5
  }
}

Input frame:

Sample frame from the generated clip — the camera has pushed forward through the same scene:

Guides

Generating VideosStep-by-step tutorial covering text-to-video and image-to-video against the v2 inference API.

Polling Async JobsThe submit → poll → download flow used by all Seedance job types.

Async API ReferenceEndpoint reference for /v2/job/async.

Seedance 2.x controls and references

Seedance 2.5 exposes text-to-video and image-to-video jobs: inference.partner.seedance-2-5.txt2vid.v2 and inference.partner.seedance-2-5.img2vid.v2. Multimodal references use inference.partner.seedance-2-5.ref2vid.v2, with a required references filename array. Upload each reference file with its corresponding image, video, or audio Content-Type. Its controls include resolution (480p, 720p, 1080p), aspect ratio, duration (4–30 seconds or -1 for automatic), seed (-1 for random or 0–2147483647), watermark, audio generation, and returning the last frame. Use aspect_ratio: "adaptive" with Seedance 2.5 first-frame inputs; this is the only allowed value for that mode.

Seedance 2.0 Mini adds inference.partner.seedance-2.mini.txt2vid.v1 and inference.partner.seedance-2.mini.img2vid.v1, supporting 480p/720p and 4–15 second outputs or automatic duration. Standard 2.0 also exposes 4K resolution.

For Seedance 2.x image-to-video, upload a first-frame image and name it with first_frame; last_frame is optional and requires first_frame. An unnamed first image upload is also accepted. Seedance 2.5 additionally accepts image as an alternative to first_frame. For reference-to-video, use references. Frame and reference roles cannot be combined. Audio-only references are supported in 2.5. Its input limits are 30 images, 10 videos, and 10 audio clips, with 30 seconds total each of video and audio.

{
  "type": "inference.partner.seedance-2-5.ref2vid.v2",
  "config": {
    "prompt": "Continue the camera movement from the reference",
    "references": ["reference.mp4"],
    "duration": 8,
    "resolution": "720p",
    "seed": 0
  }
}

See the official Seedance 2.5 guide.

Seedance 2.5 defaults to resolution: "720p" and automatic duration (-1). Standard 2.0 defaults to resolution: "1080p"; Fast and Mini default to "720p". Those three variants default to duration: 5. All 2.x variants default to aspect_ratio: "adaptive", watermark: false, generate_audio: true, and return_last_frame: false. Set return_last_frame: true to receive the final frame alongside the video. Seed is optional; use -1 for random or an integer from 0 to 2147483647. Use Accept: video/mp4 (default) or Accept: video/quicktime for MOV. In ref2vid, omni_reference_task_type accepts auto/reference/edit/extend; edit requires a reference video, adaptive aspect ratio, and automatic duration, while extend requires a reference video and adaptive aspect ratio.

All Seedance 2.x variants have separate text, frame, and reference generation types:

Variant	Text	First/last frames	References	Output resolutions
Standard 2.0	inference.partner.seedance-2.txt2vid.v2	inference.partner.seedance-2.img2vid.v2	inference.partner.seedance-2.ref2vid.v2	480p, 720p, 1080p, 4k
Fast	inference.partner.seedance-2.fast.txt2vid.v2	inference.partner.seedance-2.fast.img2vid.v2	inference.partner.seedance-2.fast.ref2vid.v2	480p, 720p
Mini	inference.partner.seedance-2.mini.txt2vid.v1	inference.partner.seedance-2.mini.img2vid.v1	inference.partner.seedance-2.mini.ref2vid.v1	480p, 720p
2.5	inference.partner.seedance-2-5.txt2vid.v2	inference.partner.seedance-2-5.img2vid.v2	inference.partner.seedance-2-5.ref2vid.v2	480p, 720p, 1080p

Use references filename arrays for reference generation. Standard 2.0, Fast, and Mini accept up to 9 images, 3 videos, and 3 audio clips, with 15 seconds total each of video and audio. Audio must accompany an image or video. First/last frame inputs use img2vid and cannot be combined with reference inputs.

Set duration to -1 for automatic duration. Automatic duration is determined from the prompt and reference content, within the selected model’s supported duration range.

The expanded controls for existing models use partner-only .v2 job types. Published .v1 schemas remain unchanged. Newly introduced models use partner-only .v1 job types.