> ## Documentation Index
> Fetch the complete documentation index at: https://veniceai-tombystrican-api-103-update-and-re-enable-public-s.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.
# Seedance 2.0 e 2.5
> Gere, edite, estenda e una vídeos com Seedance 2.0 e 2.5 na Venice - fluxos texto/imagem/referência, API faces-off e limites multimodais por família.
Seedance is a flagship multimodal video family on Venice for text-, image-, and reference-driven video generation. **Seedance 2.0** (plus Fast) and **Seedance 2.5** share the same R2V prompt-routing model: a single reference-to-video endpoint handles **four distinct workflows** (Reference, Edit, Extend, Stitch) — the workflow is inferred from the **shape of your prompt**.
This guide covers variants, the four workflows, **faces-off public API behavior**, **family-specific multimodal limits**, pricing, and `curl` examples.
**Rostos não são suportados na API pública do Seedance.** A Venice não executa provisionamento de face assets nem atestação de consentimento facial (`consents.seedance` / `needs_consent`) para modelos Seedance públicos. Entradas com rostos podem ser rejeitadas upstream como erro de política de conteúdo / provedor. Para geração com likeness / face assets, use o app ou o Studio da Venice.
## Variants
| Model ID | Variant | Output resolutions | Notes |
| ------------------------------------------ | -------- | ---------------------------- | ------------------------------------------------------------------------------------------------------------------- |
| `seedance-2-0-text-to-video-api` | T2V | 480p / 720p / 1080p / **4k** | Text prompt only |
| `seedance-2-0-image-to-video-api` | I2V | 480p / 720p / 1080p / **4k** | First-frame (and optionally last-frame) image grounding |
| `seedance-2-0-reference-to-video-api` | R2V | 480p / 720p / 1080p / **4k** | Up to 9 reference images + 3 reference videos + 3 reference audio donors. Powers Reference / Edit / Extend / Stitch |
| `seedance-2-0-fast-text-to-video-api` | Fast T2V | 480p / 720p | Faster, lower-fidelity tier (no 1080p / 4k) |
| `seedance-2-0-fast-image-to-video-api` | Fast I2V | 480p / 720p | Faster, lower-fidelity tier (no 1080p / 4k) |
| `seedance-2-0-fast-reference-to-video-api` | Fast R2V | 480p / 720p | Faster, lower-fidelity tier (no 1080p / 4k); same workflow set |
| `seedance-2-5-text-to-video-api` | T2V | 480p / 720p | Up to 30s output; native audio |
| `seedance-2-5-image-to-video-api` | I2V | 480p / 720p | Up to 30s output; first-frame (and optionally last-frame) grounding |
| `seedance-2-5-reference-to-video-api` | R2V | 480p / 720p | Up to 30 images + 10 videos + 10 audio donors; same Reference / Edit / Extend / Stitch workflows |
All variants are async. Submit via `POST /api/v1/video/queue`, then poll `POST /api/v1/video/retrieve` until the response body is `video/mp4`. See [Video Generation](/guides/media/video-generation) for the general queue flow.
Pass `resolution` as one of: `480p`, `720p`, `1080p`, or `4k` (lowercase). Seedance **2.0** (non-Fast) accepts all four; **2.0 Fast** and **2.5** accept `480p` / `720p` only. Discover live model IDs and capabilities with `GET /models?type=video` — do not hardcode availability.
## The "one model, four workflows" model
The reference-to-video variants (`seedance-2-0-reference-to-video-api`, its Fast sibling, and `seedance-2-5-reference-to-video-api`) use the same prompt-routing pattern. **The model infers the task from the prompt prefix and the shape of your inputs.** There is no `task` or `workflow` field — the prompt syntax is the routing.
| Workflow | What it does | Prompt prefix | Inputs |
| ------------- | -------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------- |
| **Reference** | Generate a new video using uploaded reference files as donors for subject / motion / style / audio | `Refer to ... in to generate ...` | Text + ≥1 image OR video reference, plus optional audio donors (counts differ by family — see limits) |
| **Edit** | Modify a single input video while preserving the rest | `Strictly edit , changing its ...` | 1 input video + text (images optional grounding) |
| **Extend** | Forward / backward extension of one clip | `Extend , generate ...` | 1 input video + text |
| **Stitch** | Stitch input clips with auto-generated transitions | ` + + followed by + ...` | Multiple input videos + text (clip count / duration caps differ by family) |
The **prompt syntax is canonical and case-sensitive**: angle brackets, capital first letter, single space before the number — ``, ``, ``.
***
## Workflow patterns
### Reference workflow
Use the uploaded reference files as **donors** — subject, scene, motion, style, vocal timbre — to generate a brand-new video.
**Canonical prompt patterns**:
```
Refer to in to generate ...
Refer to the [action | camera scene | style | sound effect] in to generate ...
Refer to the [tone | timbre] in to generate ...
```
**Examples**:
* `Refer to in to generate a 5-second clip of the same character riding a horse through snow.`
* `Refer to the camera scene in to generate a similar establishing shot of a futuristic city at dawn.`
* `Refer to in and use the timbre in for the narrator describing the scene.` (audio donors must be paired with at least one image or video reference — audio alone is rejected)
### Edit workflow
Modify a single input video. **Anything not explicitly named in the prompt is preserved.** Use this when you want a localized change (subject swap, weather/color change, element add/remove) rather than a wholly new video.
**Canonical prompt pattern**:
```
Strictly edit , changing its [original feature] to [new feature] ...
```
**Sub-patterns for finer control**:
```
Add Elements:
At [timestamp / timing] and [spatial location] of , add [description of intended element].
Remove Elements:
Remove [element to be deleted] from , keeping the rest of the video content unchanged.
Modify Elements:
Replace [description of element to be changed] in with [description of intended element].
```
**Examples**:
* `Strictly edit , changing its weather from sunny to a heavy rainstorm.`
* `Add snacks such as fried chicken and pizza to the countertop in .`
* `Remove the red car from , keeping the rest of the video content unchanged.`
* `Replace the perfume featured in with the face cream from , with all original motions and camera work preserved.`
The last example combines Edit with an image reference — perfectly legal, the model uses `` as a visual donor for the replacement.
### Extend workflow
Continue a single clip forward or backward in time. **By default Seedance returns only the new content** — not the original input concatenated with the extension. This is by design, for transition continuity; if you want the input clip preserved alongside the extension, say so explicitly:
```
Extend , generate [description of extended content]
Extend backward, [description of extended content]
Extend , start with , then [description of extended content] ← preserves input at start
Extend backward, [description], and then end with ← preserves input at end
```
Transition handling: the model automatically extracts the transition frames for seamless blending, and the original segments of the input video are not re-generated.
**Examples**:
* `Extend , generate a dramatic chase scene through narrow alleys at dusk.`
* `Extend backward, the same character walking toward the camera before the original shot begins.`
* `Extend , start with , then the camera pulls back to reveal a vast landscape.`
### Stitch workflow (Track Completion)
Connect input clips with AI-generated transitions. Respect the **family-specific** combined-duration and clip-count caps in [Multimodal input limits](#multimodal-input-limits) (Seedance 2.0: ≤3 clips / ≤15 s combined; Seedance 2.5: higher video caps).
**Canonical prompt pattern**:
```
+ [transition description] + followed by [+ [transition description] + followed by ]
```
**Examples**:
* ` + a smooth seamless cut + followed by `
* `. The moment a leaf falls to the ground, it sets off a special effect of golden particles. A gust of wind blows by, leading into .`
* ` + a wisp of smoke transforms into a flock of birds + followed by + a slow dolly-in + followed by `
The model auto-trims connecting segments at the join points for continuity.
***
## Universal prompt formula
Across all four workflows, the recommended authoring formula is:
```
Subject + Motion + Environment (Optional)
+ Camera Movement / Cut (Optional)
+ Aesthetic Description (Optional)
+ Audio (Optional)
```
* **Subject + Motion**: the logical foundation — define "Who" is performing "What action"
* **Environment + Aesthetics**: spatial background, lighting, visual style
* **Camera**: explicit shot type or movement
* **Audio**: ambient sound effects or vocal direction for immersive output
Layering this on top of a workflow prefix (e.g., `Strictly edit , changing its `) produces the highest-quality outputs.
***
## Multimodal input limits
Values below are what the Venice API accepts. Requests outside these ranges are rejected at the schema layer with a 400 before reaching inference.
**Seedance 2.0 and Seedance 2.5 use different caps.** Always check the column for the model family you are calling.
### Shared media floors
| Constraint | Value |
| ----------------------------------- | ------------------------------------------------------------------- |
| Image / video / audio input methods | URL (`http://`, `https://`) or Base64 data URL |
| Image formats | `.jpeg`, `.png`, `.webp`, `.bmp`, `.tiff`, `.gif`, `.heic`, `.heif` |
| Image aspect ratio (W / H) | exclusive `(0.4, 2.5)` |
| Image minimum side | ≥ 300 px |
| Video formats | `.mp4`, `.mov` |
| Video codecs | H.264 / AVC, H.265 / HEVC |
| Audio codecs (in container) | AAC, MP3 |
| Audio formats (reference audio) | `.wav`, `.mp3` |
| Per-clip video size | ≤ 50 MB |
| Per-clip audio size | ≤ 15 MB |
| I2V first-frame images | 1 |
| I2V first + last frame | 2 |
### Family comparison
| Constraint | Seedance 2.0 (+ Fast) | Seedance 2.5 |
| --------------------------------- | ----------------------------------------------------- | ------------------- |
| Output duration | 4–15 s | 4–30 s (default 10) |
| Output resolutions | 480p / 720p / 1080p / **4k** (Fast: 480p / 720p only) | 480p / 720p only |
| R2V reference images | 1–9 | 1–30 |
| Max R2V reference image bytes | (shared request limits) | ≤ 30 MB per image |
| R2V reference videos | ≤ 3 | ≤ 10 |
| Duration per reference video | `[2, 15]` s | `[2, 30]` s |
| Combined reference video duration | ≤ 15 s | ≤ 30 s |
| R2V reference audio clips | ≤ 3 | ≤ 10 |
| Duration per reference audio | `[2, 15]` s | `[2, 30]` s |
| Combined reference audio duration | ≤ 15 s | ≤ 30 s |
Reference audio is supported on the R2V variants only. Each entry is forwarded to the model as a `role: "reference_audio"` content item that the prompt addresses as ``, ``, … — the model uses each clip for vocal timbre, sound effects, or background music depending on how the prompt frames it. The legacy singular `audio_url` field maps to the same content shape and is now equivalent to passing a one-element `reference_audio_urls`.
**`reference_audio_urls` cannot be the only reference input.** The model requires at least one image or video reference alongside any audio donor. Pair `reference_audio_urls` with `reference_image_urls`, `reference_video_urls`, `image_url`, or `video_url` — audio-only submissions are rejected.
### Request size
The queue endpoint accepts JSON bodies up to **35 MB**. Inline data URLs for large videos can push past this — for multi-clip Stitch in particular, prefer URLs over inline base64.
***
## Pricing
Call `POST /api/v1/video/quote` to get a quote for a given request shape before submitting it to `/video/queue`. The quote endpoint is the only authoritative source; pricing details may change and shouldn't be cached or duplicated client-side.
When reference video(s) are part of the request, also pass `reference_video_total_duration` (the sum of all reference clip durations in seconds) so the quote matches what `/video/queue` will charge:
```bash theme={"system"}
curl -X POST https://api.venice.ai/api/v1/video/quote \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedance-2-0-reference-to-video-api",
"duration": "5s",
"resolution": "1080p",
"aspect_ratio": "16:9",
"reference_video_total_duration": 5
}'
```
***
## Complete examples
All examples assume `VENICE_API_KEY` is set in the environment.
### Text-to-video
```bash theme={"system"}
curl -X POST https://api.venice.ai/api/v1/video/queue \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedance-2-0-text-to-video-api",
"prompt": "A golden retriever frolicking through a sunlit meadow at sunset, slow camera dolly-in, shallow depth of field, warm cinematic lighting.",
"duration": "5s",
"aspect_ratio": "16:9",
"resolution": "1080p"
}'
```
### Seedance 2.0 text-to-video (4K)
```bash theme={"system"}
curl -X POST https://api.venice.ai/api/v1/video/queue \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedance-2-0-text-to-video-api",
"prompt": "Ultra-detailed aerial glide over a sunlit alpine lake, crystal water, distant peaks, cinematic color grade.",
"duration": "5s",
"aspect_ratio": "16:9",
"resolution": "4k"
}'
```
### Seedance 2.5 text-to-video (longer duration)
```bash theme={"system"}
curl -X POST https://api.venice.ai/api/v1/video/queue \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedance-2-5-text-to-video-api",
"prompt": "A slow aerial push over misty mountains at sunrise, clouds parting, soft orchestral ambience, cinematic widescreen framing.",
"duration": "20s",
"aspect_ratio": "16:9",
"resolution": "720p"
}'
```
### Image-to-video (first frame)
```bash theme={"system"}
curl -X POST https://api.venice.ai/api/v1/video/queue \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedance-2-0-image-to-video-api",
"prompt": "The lighthouse keeper turns toward the storm, lantern raised, waves crashing against the rocks.",
"image_url": "https://example.com/lighthouse.jpg",
"duration": "5s",
"resolution": "720p"
}'
```
Seedance I2V models (`seedance-2-0-image-to-video-api`, its Fast variant, and `seedance-2-5-image-to-video-api`) **do not accept `aspect_ratio`** — the output aspect ratio is auto-derived from the input image's dimensions. Passing the field returns a 400 with *"This model does not support aspect\_ratio"*. Use the T2V or R2V variants if you need explicit aspect-ratio control.
### Reference workflow — subject donor
```bash theme={"system"}
curl -X POST https://api.venice.ai/api/v1/video/queue \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedance-2-0-reference-to-video-api",
"prompt": "Refer to in to generate a 5-second clip of the same character walking through a neon-lit Tokyo street at night.",
"reference_image_urls": ["https://example.com/character.png"],
"duration": "5s",
"aspect_ratio": "9:16",
"resolution": "1080p"
}'
```
### Seedance 2.5 reference workflow — multi-image
```bash theme={"system"}
curl -X POST https://api.venice.ai/api/v1/video/queue \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedance-2-5-reference-to-video-api",
"prompt": "Refer to in and the style in to generate a 12-second clip of the same character exploring a rainy cyberpunk alley.",
"reference_image_urls": [
"https://example.com/character.png",
"https://example.com/style-board.png"
],
"duration": "12s",
"aspect_ratio": "9:16",
"resolution": "720p"
}'
```
### Reference workflow — subject + audio donor
```bash theme={"system"}
curl -X POST https://api.venice.ai/api/v1/video/queue \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedance-2-0-reference-to-video-api",
"prompt": "Refer to in to generate a 5-second clip of the same character walking through a neon-lit Tokyo street at night. Refer to the timbre in for a soft female voiceover describing the scene.",
"reference_image_urls": ["https://example.com/character.png"],
"reference_audio_urls": ["https://example.com/voice-sample.mp3"],
"duration": "5s",
"aspect_ratio": "9:16",
"resolution": "1080p"
}'
```
### Edit workflow
```bash theme={"system"}
curl -X POST https://api.venice.ai/api/v1/video/queue \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedance-2-0-reference-to-video-api",
"prompt": "Strictly edit , changing its weather from sunny to a heavy rainstorm, with all original motions and camera work preserved.",
"reference_video_urls": ["https://example.com/sunny-scene.mp4"],
"reference_video_total_duration": 5,
"duration": "5s",
"aspect_ratio": "16:9",
"resolution": "1080p"
}'
```
### Edit workflow with image grounding
```bash theme={"system"}
curl -X POST https://api.venice.ai/api/v1/video/queue \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedance-2-0-reference-to-video-api",
"prompt": "Replace the perfume featured in with the face cream from , with all original motions and camera work preserved.",
"reference_video_urls": ["https://example.com/perfume-ad.mp4"],
"reference_image_urls": ["https://example.com/face-cream.png"],
"reference_video_total_duration": 4,
"duration": "5s",
"aspect_ratio": "16:9",
"resolution": "1080p"
}'
```
### Extend forward
```bash theme={"system"}
curl -X POST https://api.venice.ai/api/v1/video/queue \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedance-2-0-reference-to-video-api",
"prompt": "Extend , generate a dramatic chase scene through narrow alleys at dusk, with neon signs flickering and rain on the pavement.",
"reference_video_urls": ["https://example.com/alley-intro.mp4"],
"reference_video_total_duration": 4,
"duration": "5s",
"aspect_ratio": "16:9",
"resolution": "1080p"
}'
```
### Stitch (3 clips)
```bash theme={"system"}
curl -X POST https://api.venice.ai/api/v1/video/queue \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedance-2-0-reference-to-video-api",
"prompt": " + a wisp of smoke transforms into a flock of birds + followed by + a slow dolly-in + followed by ",
"reference_video_urls": [
"https://example.com/clip-1.mp4",
"https://example.com/clip-2.mp4",
"https://example.com/clip-3.mp4"
],
"reference_video_total_duration": 12,
"duration": "5s",
"aspect_ratio": "16:9",
"resolution": "1080p"
}'
```
### Polling for completion
After every queue submission, save the returned `queue_id` and poll `/video/retrieve` until the response body is `video/mp4`:
```bash theme={"system"}
curl -X POST https://api.venice.ai/api/v1/video/retrieve \
-H "Authorization: Bearer $VENICE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedance-2-0-reference-to-video-api",
"queue_id": "123e4567-e89b-12d3-a456-426614174000"
}' \
-o output.mp4
```
The response is JSON (`{ "status": "queued" | "running" | "failed", ... }`) until the job completes, at which point the response body switches to `video/mp4` bytes. See [Video Generation](/guides/media/video-generation) for the full polling pattern.
***
## Troubleshooting
### `At least one reference is required for this model`
Reference-to-video submissions must include at least one of `reference_image_urls`, `reference_video_urls`, `image_references`, or `video_references`. Pure text-only generation isn't a valid R2V workflow — use a text-to-video model ID instead. `reference_audio_urls` alone is not sufficient (see the Audio section above).
### Too many reference videos / images
Seedance **2.0** caps R2V at **9 images** and **3 videos**. Seedance **2.5** raises those caps to **30 images** and **10 videos**. If you exceed the family limit, trim inputs or stitch offline first.
### Duration / aggregate duration errors
* **2.0:** per-clip reference video/audio `[2, 15]` s; combined video/audio ≤ 15 s; output 4–15 s.
* **2.5:** per-clip reference video/audio `[2, 30]` s; combined video/audio ≤ 30 s; output 4–30 s.
Trim clips client-side before submission.
### Prompt routes to the wrong workflow
Workflow is inferred from prompt syntax. Common misroutings:
* Wanting to **Extend** but writing `Refer to ...` → model treats your video as a *donor*, not a canvas to continue
* Wanting to **Stitch** but writing `Refer to ...` → model picks one as the donor, ignores the others
* Wanting to **Edit** but writing `Generate a video based on ` → ambiguous; model may default to Reference
Use the canonical prefixes exactly as written: `Strictly edit , ...`, `Extend , ...`, ` + ... + followed by `.
### Face / likeness inputs rejected
Public Seedance API models are **faces-off**. Do not expect a consent attestation flow. Face-bearing media may fail with a content-policy / provider error. Use the Venice app or Studio for likeness workflows.
### Quote doesn't match the queued amount
If you included a reference video but didn't pass `reference_video_total_duration` to `/video/quote`, the quote and the queued amount may differ. Always pass `reference_video_total_duration` (sum of all reference clip durations, in seconds) when reference videos are present.
***
## References
* Venice video queue endpoint: [`POST /api/v1/video/queue`](/api-reference/endpoint/video/queue)
* Venice quote endpoint: [`POST /api/v1/video/quote`](/api-reference/endpoint/video/quote)
* Companion guide: [Reference to Video](/guides/media/reference-to-video) (covers Kling O3 + Grok Imagine R2V)
* Companion guide: [Video Generation](/guides/media/video-generation) (queue / polling overview)