seedinteger
Random seed for reproducible results. Omit or use -1 for a random seed.
Minimum: -1
Maximum: 4294967295
Seedance 2.0 Mini Reference to Video
bytedance/seedance/2.0/mini/reference-to-videoSeedance 2.0 Mini by Bytedance - animate still images into dynamic videos with AI. Transform photos into cinematic clips with natural motion, camera movement, and optional audio generation.
Try the model
Playground
Input
The text prompt used to generate the video.
Additional Settings More
Customize your input with more control.
PNG, JPEG, WebP, or GIF · 20 MiB maximum each
Reference images to guide video generation. Refer to them in the prompt as @Image1, @Image2, etc. Supported formats: JPEG, PNG, WebP. Max 30 MB per image. Up to 9 images. Total files across all modalities must not exceed 12.
Reference videos to guide video generation. Refer to them in the prompt as @Video1, @Video2, etc. Supported formats: MP4, MOV. Up to 3 videos, combined duration must be between 2 and 15 seconds, total size under 50 MB. Each video must be between ~480p (640x640) and ~720p (834x1112) in resolution.
Video resolution - 480p for faster generation, 720p for balance. Allowed values: 480p, 720p.
Output duration in seconds (4-15), or `auto` to let the model pick a length from the prompt and inputs. `auto` is pre-authorized at 15 seconds and billed on the actual output length. When a reference video is edited or extended, use `auto` with `adaptive` aspect ratio so the output follows the source clip. Allowed values: auto, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15.
Whether to generate synchronized audio for the video, including sound effects, ambient sounds, and lip-synced speech. The cost of video generation is the same regardless of whether audio is generated or not.
Output aspect ratio. Omit to let the model choose from the prompt and reference inputs. Allowed values: 21:9, 16:9, 3:2, 4:3, 5:4, 1:1, 4:5, 3:4, 2:3, 9:16.
Reference audio URLs (voice or music) for the generated video.
Random seed for reproducible results. Omit or use -1 for a random seed. Range: -1 to 4294967295.
ResultExample
What would you like to do next?
Examples
Select an example to load its inputs and result into the playground.
- Open result ↗
Input
{ "prompt": "An octopus finds a football in the ocean and excitedly calls its octopus friends to come and play. Cut scene to an octopus football game under the sea." }
Seedance 2.0 Mini Reference to Video
Seedance 2.0 Mini reference-to-video: combine reference images, up to 3 reference videos, and reference audio to lock a character, set, motion, or voice in a new clip.
Fields
| Field | Type | Default | Notes |
|---|---|---|---|
prompt | string, required | — | Text instruction. |
images | image URL[] | — | Reference images, Image 1, Image 2, … |
videos | video URL[] | — | Reference clips (up to 3), Video 1, Video 2, … |
resolution | 480p / 720p | 720p | Sets the per-second rate. |
duration | auto / 4 / 5 / 6 / 7 / 8 / 9 / 10 / 11 / 12 / 13 / 14 / 15 | 5 | Output length in seconds (4–15), or auto to let the model choose. |
generate_audio | boolean | true | Native dialogue, music, and effects. Same price on or off. |
aspect_ratio | 21:9 / 16:9 / 3:2 / 4:3 / 5:4 / 1:1 / 4:5 / 3:4 / 2:3 / 9:16 | — | Output frame shape. |
audios | audio URL[] | — | Reference audio, Audio 1, Audio 2, … |
seed | integer -1–4294967295 | random | Fix it to compare prompt changes; -1 is random. |
Billing
Without reference videos you pay for output seconds: $0.06 at 480p, $0.12 at 720p. With reference videos, the input video seconds (at least 2) are added to the output length and billed at a lower rate: $0.0375 at 480p, $0.075 at 720p. With duration: "auto" the quote assumes 15 seconds and the final charge uses the generated length.
| Output | 480p | 720p |
|---|---|---|
| 5s, images only | $0.30 | $0.60 |
| 10s, images only | $0.60 | $1.20 |
| 5s + 5s reference video | $0.375 | $0.75 |
| 10s + 10s reference video | $0.75 | $1.50 |
Failed runs are not charged.
Prompting
- Give each reference a role: “Image 1 is the dancer, Video 1 sets the choreography, Audio 1 is the music”.
- Numbering follows array order within each type.
Limits
- Reference video seconds count toward billing (minimum 2, up to 15).
Also on SandBase
Other Seedance 2.0 Mini endpoints and tiers: bytedance/seedance/2.0/mini/text-to-video, bytedance/seedance/2.0/mini/image-to-video, bytedance/seedance/2.5/reference-to-video, bytedance/seedance/2.0/reference-to-video, bytedance/seedance/2.0/fast/reference-to-video.
Start building
Send your first request
Submit this model through the SandBase Unified Run API.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/run" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "bytedance/seedance/2.0/mini/reference-to-video",
"images": [
"https://v3b.fal.media/files/b/0a8eba37/Cqg-4Uwzyz4DELfceT1CF_a17e588773ec45b1a9e6f100a787b80b.jpg"
],
"prompt": "An octopus finds a football in the ocean and excitedly calls its octopus friends to come and play. Cut scene to an octopus football game under the sea.",
"duration": 5,
"resolution": "720p",
"generate_audio": true
}
SANDBASE_JSON
)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
status=$(printf '%s' "$result" | jq -r .status)
case "$status" in completed|failed|timeout) break ;; esac
sleep 2
result=$(curl --fail-with-body --silent \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
"https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"2. Authentication
Create a SandBase API key and set it in your server environment. All requests use Bearer authentication.
export SANDBASE_API_KEY="YOUR_API_KEY"Keep the key on your server. Do not expose it in browser code or commit it to a repository.
3. Queue
Submit a request
POST to /v1/run with this model ID and its inputs. The request example above includes submission and polling.
Fetch request status and result
Use the returned run ID to poll until the status is completed, failed or timeout. Read output only after completed.
curl "https://api.sandbase.ai/v1/run/$RUN_ID" \
-H "Authorization: Bearer $SANDBASE_API_KEY"4. Files
Hosted files
Pass a publicly accessible file URL in the model’s image, video or audio field. Supported formats and limits are shown beside each Playground input.
Uploading images
Use the upload or replace control on supported image fields in the Playground. Video URL fields accept a hosted driving video; they do not imply video-upload support.
5. Schema
Input
audiosarray
Reference audio URLs (voice or music) for the generated video.
imagesarray
Reference images to guide video generation. Refer to them in the prompt as @Image1, @Image2, etc. Supported formats: JPEG, PNG, WebP. Max 30 MB per image. Up to 9 images. Total files across all modalities must not exceed 12.
promptstringrequired
The text prompt used to generate the video.
videosarray
Reference videos to guide video generation. Refer to them in the prompt as @Video1, @Video2, etc. Supported formats: MP4, MOV. Up to 3 videos, combined duration must be between 2 and 15 seconds, total size under 50 MB. Each video must be between ~480p (640x640) and ~720p (834x1112) in resolution.
durationvalue
Output duration in seconds (4-15), or `auto` to let the model pick a length from the prompt and inputs. `auto` is pre-authorized at 15 seconds and billed on the actual output length. When a reference video is edited or extended, use `auto` with `adaptive` aspect ratio so the output follows the source clip.
Default: 5
Possible values: "auto", 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15
resolutionstring
Video resolution - 480p for faster generation, 720p for balance.
Default: "720p"
Possible values: "480p", "720p"
aspect_ratiostring
Output aspect ratio. Omit to let the model choose from the prompt and reference inputs.
Possible values: "21:9", "16:9", "3:2", "4:3", "5:4", "1:1", "4:5", "3:4", "2:3", "9:16"
generate_audioboolean
Whether to generate synchronized audio for the video, including sound effects, ambient sounds, and lip-synced speech. The cost of video generation is the same regardless of whether audio is generated or not.
Default: true
{
"model": "bytedance/seedance/2.0/mini/reference-to-video",
"images": [
"https://v3b.fal.media/files/b/0a8eba37/Cqg-4Uwzyz4DELfceT1CF_a17e588773ec45b1a9e6f100a787b80b.jpg"
],
"prompt": "An octopus finds a football in the ocean and excitedly calls its octopus friends to come and play. Cut scene to an octopus football game under the sea.",
"duration": 5,
"resolution": "720p",
"generate_audio": true
}Output
A completed run exposes its result in output. The following is the model’s saved example, not a new generation.
[
{
"poster": "https://static.sandbase.ai/examples/posters/8c713e156c30b55f062e.jpg",
"source": "ByteDance/Volcengine schema mirror",
"source_url": "https://docs.volcengine.com/docs/ark/seedance-2-0",
"url": "https://static.sandbase.ai/examples/c47e64e5-ff3d-42aa-b2d6-a6168c64775f/output/c83506bb-01c5-4433-88e7-f8f4c86ae3f6.mp4"
}
]