Skip to content
Open CastalyConsole

Video

seedance-2.0-nsfw API

Use the exact seedance-2.0-nsfw model ID through Modelflare asynchronous video routing.

Use the exact model ID seedance-2.0-nsfw. The model field must match this page exactly.

Sample outputseedance-2.0-nsfwPOST /v1/videos5.1s

Parameters: duration=5resolution=1080pratio=16:9

Prompt: One continuous take, no cuts. The bow cushions of a yacht at anchor, flat blue water around. A blonde woman with a curvy full figure, in a white bikini and tortoiseshell glasses. She sits with her knees up looking out at the sea, then turns to face the camera, lifting her hair off her neck and letting it fall, and settles front on to the lens. Hard midday sun from above, white deck bouncing light back up. Low camera close to her, easing back as she turns and keeping her framed from shoulders to hips, shallow depth of field. Real weight and inertia, natural hair and fabric movement, no text.

This sample is deliberately mild. It is not the content limit of this model ID.

Request that produced this sample
{
"model": "seedance-2.0-nsfw",
"prompt": "One continuous take, no cuts. The bow cushions of a yacht at anchor, flat blue water around. A blonde woman with a curvy full figure, in a white bikini and tortoiseshell glasses. She sits with her knees up looking out at the sea, then turns to face the camera, lifting her hair off her neck and letting it fall, and settles front on to the lens. Hard midday sun from above, white deck bouncing light back up. Low camera close to her, easing back as she turns and keeping her framed from shoulders to hips, shallow depth of field. Real weight and inertia, natural hair and fabric movement, no text.",
"seconds": "5",
"duration": 5,
"resolution": "1080p",
"ratio": "16:9",
"aspect_ratio": "16:9"
}

Use a Modelflare API key with https://modelflare.dev/v1. The gateway entry point is POST /v1/videos.

HTTP
Authorization: Bearer YOUR_MODELFLARE_API_KEY
Terminal windowbash
curl https://modelflare.dev/v1/videos \
-H "Authorization: Bearer YOUR_MODELFLARE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedance-2.0-nsfw",
"content": [{"type": "text", "text": "A white cat runs through a neon-lit street in the rain, cinematic tracking shot"}],
"resolution": "720p",
"duration": 5,
"generate_audio": false
}'

Save the task ID. Poll GET /v1/videos/{task_id} and download with GET /v1/videos/{task_id}/content. Result URLs may expire, so transfer the file promptly.

Terminal windowbash
curl https://modelflare.dev/v1/videos/TASK_ID \
-H "Authorization: Bearer YOUR_MODELFLARE_API_KEY"

Seedance uses content[] for text, frames, and reference media; the separate Seedance asset management contract is documented independently.

Seedance uses one asynchronous multimodal envelope. Put text and media in content[]; media roles select first/last-frame or reference workflows.

Field Required Notes
model Yes seedance-2.0-nsfw
content[] Yes text, image_url, video_url, and audio_url; use role to identify media purpose
resolution No 480p / 720p / 1080p / 4k (default 720p)
ratio No 21:9 / 16:9 / 4:3 / 1:1 / 3:4 / 9:16 / adaptive
duration No 4–15 seconds
generate_audio No Generate synchronized dialogue, effects, and background audio
tools No Use web_search only where the official model page supports it
watermark No Whether to add a watermark

This model supports 480p, 720p, 1080p, and 4k output with a 4–15 second duration. Multimodal references allow up to nine images, three videos, and three audio clips; audio cannot be used alone. Mark media with role values in content[]; first-frame, editing, extension, and web-search workflows have their own constraints. Photorealistic people, real-person photos, and realistic faces must be uploaded to the asset library first; do not submit them as an image URL or Base64 payload.

The Seedance 2.0 series supports text-to-video, first/first-and-last frames, multimodal references, editing, extension, and web search for text-to-video. Order media as text, image, video, then audio.

Terminal windowbash
curl https://modelflare.dev/v1/videos \
-H "Authorization: Bearer YOUR_MODELFLARE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedance-2.0-nsfw",
"content": [
{"type": "text", "text": "@image1 performs the movement from @video1, paced to @audio1"},
{"type": "image_url", "image_url": {"url": "https://example.com/character.jpg"}, "role": "reference_image"},
{"type": "video_url", "video_url": {"url": "https://example.com/motion.mp4"}, "role": "reference_video"},
{"type": "audio_url", "audio_url": {"url": "https://example.com/music.mp3"}, "role": "reference_audio"}
],
"generate_audio": true, "ratio": "16:9", "duration": 11
}'
Terminal windowbash
curl https://modelflare.dev/v1/videos \
-H "Authorization: Bearer YOUR_MODELFLARE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedance-2.0-nsfw", "content": [{"type": "text", "text": "Macro shot of cherry blossoms in spring"}],
"generate_audio": true, "ratio": "16:9", "duration": 11,
"tools": [{"type": "web_search"}]
}'

Invalid model parameters return a 4xx with a request ID. An asynchronous task can also enter failed after creation succeeds; use error_code and error_message from the poll response as the final task reason. Do not retry the same request with a different JSON shape.

This page covers Modelflare model generation and editing calls. Search or map enrichment, voice management, and element-library management are resource APIs outside this public model-call surface and are not required request fields.

This model uses token-based billing. See the model pricing page for the current customer price, reference list price, and complete specification.

Model ID Difference
seedance-2.0-nsfw The model documented on this page.
seedance-2.0 The base model. Same endpoint, request contract, and billing unit; only the model ID changes — see its own page, and the pricing page for price and availability.
Media contract · v1

Contract ID: media.seedance-2-0-nsfw.v1Adapter: video.seedance.20.v1@v1Fingerprint: efb41f1aa059d28b75ad0a53b4efdee5e26d6bbef51eed15209c16b7c58212fd

Official source: ByteDance / Volcengine

Contract parameters

Intent fieldControlOptions
ratioselect16:9 / 9:16 / 1:1 / 4:3 / 3:4 / 21:9 / adaptive
resolutionselect480p / 720p / 1080p / 4k
durationselect4 / 5 / 8 / 10 / 15
audioswitch—

Supported capability

  • allowed_values · ratio · 16:9, 9:16, 1:1, 4:3, 3:4, 21:9, adaptive
  • allowed_values · resolution · 480p, 720p, 1080p, 4k
  • allowed_values · duration · 4, 5, 8, 10, 15
  • max_assets · reference_asset_ids · 15
  • prompt_optional_with_reference · prompt

Structured request example

text

Intent

{
  "audio": false,
  "duration": 4,
  "prompt": "A red paper kite over a quiet harbour at dusk.",
  "ratio": "16:9",
  "resolution": "480p"
}

Provider request

{
  "content": [
    {
      "text": "A red paper kite over a quiet harbour at dusk.",
      "type": "text"
    }
  ],
  "duration": 4,
  "generate_audio": false,
  "model": "seedance-2.0-nsfw",
  "ratio": "16:9",
  "resolution": "480p",
  "seconds": "4"
}

reference

Intent

{
  "audio": false,
  "duration": 4,
  "prompt": "A red paper kite over a quiet harbour at dusk.",
  "ratio": "16:9",
  "resolution": "480p"
}

Provider request

{
  "content": [
    {
      "text": "A red paper kite over a quiet harbour at dusk.",
      "type": "text"
    },
    {
      "image_url": {
        "url": "https://example.com/reference.png"
      },
      "role": "reference_image",
      "type": "image_url"
    }
  ],
  "duration": 4,
  "generate_audio": false,
  "model": "seedance-2.0-nsfw",
  "ratio": "16:9",
  "resolution": "480p",
  "seconds": "4"
}