seedinteger
Random seed for reproducible results. Omit or use -1 for a random seed.
Minimum: -1
Maximum: 4294967295
bytedance/seedance/2.0/fast/reference-to-videoByteDance's most advanced reference-to-video model in its fast tier delivering lower latency and cost without compromising on cinematic output, native audio, multi-shot editing, and director-level camera control for professional-grade video creation.
Try the model
Customize your input with more control.
PNG, JPEG, WebP, or GIF · 20 MiB maximum each
What would you like to do next?
Select an example to load its inputs and result into the playground.
{
"duration": 5,
"images": [
"https://static.sandbase.ai/examples/79689fb0-69ec-46be-aec5-bd3e552c32e9/input/29d43a66-db4e-46d7-998b-3e10e7b88cd1.jpg"
],
"prompt": "A hyper-realistic UGC-style medium close-up of a woman in her late 20s standing in her sunlit bedroom in front of a slightly messy bed with white linen sheets, filmed vertically as if she's holding her phone at arm's length for a TikTok or Instagram Reel; she has shoulder-length honey blonde waves, light freckles, natural glowy skin with minimal makeup, wearing a cream ribbed tank top and high-waisted jeans, holding up a compact mirrorless camera on [Image1] in one hand close to the lens so it's clearly visible, her expression bright and genuine — not overly polished — as she says directly to the camera: \"Okay I never do this, but I genuinely have to talk about this camera — I've had it for three weeks and it has not left my bag, the photos look like film straight out of it, no editing, and it literally fits in my jacket pocket\"; she then turns the camera around to briefly show its compact size against her hand, the background featuring a wooden dresser with scattered jewelry, a small vase of dried flowers, soft morning light pouring through sheer white curtains, a framed poster slightly crooked on the wall, and a houseplant in the corner, all captured with the slightly wider phone-lens distortion, natural skin texture including pores, subtle handheld shake, ambient room tone, and unfiltered warm color grading that feels like an authentic creator review rather than a produced advertisement.",
"resolution": "720p"
}{
"duration": 5,
"images": [
"https://static.sandbase.ai/examples/3dbbd744-3625-4ad2-b8f4-30dba59f5996/input/d71581c5-5b23-4a41-9505-f4f3130a4628.jpg"
],
"prompt": "A hyper-realistic UGC-style medium close-up of a woman in her late 20s standing in her sunlit bedroom in front of a slightly messy bed with white linen sheets, filmed vertically as if she's holding her phone at arm's length for a TikTok or Instagram Reel; she has shoulder-length honey blonde waves, light freckles, natural glowy skin with minimal makeup, wearing a cream ribbed tank top and high-waisted jeans, holding up a compact mirrorless camera on [Image1] in one hand close to the lens so it's clearly visible, her expression bright and genuine — not overly polished — as she says directly to the camera: \"Okay I never do this, but I genuinely have to talk about this camera — I've had it for three weeks and it has not left my bag, the photos look like film straight out of it, no editing, and it literally fits in my jacket pocket\"; she then turns the camera around to briefly show its compact size against her hand, the background featuring a wooden dresser with scattered jewelry, a small vase of dried flowers, soft morning light pouring through sheer white curtains, a framed poster slightly crooked on the wall, and a houseplant in the corner, all captured with the slightly wider phone-lens distortion, natural skin texture including pores, subtle handheld shake, ambient room tone, and unfiltered warm color grading that feels like an authentic creator review rather than a produced advertisement.",
"resolution": "720p"
}Seedance 2.0 Fast 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.
| Field | Type | Default | Notes |
|---|---|---|---|
prompt | string, required | — | Up to 50,000 characters. |
images | image URL[] | — | Reference images, Image 1, Image 2, … |
videos | video URL[] (≤3) | — | Reference clips (up to 3), Video 1, Video 2, … |
audios | audio URL[] | — | Reference audio, Audio 1, Audio 2, … |
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. |
aspect_ratio | 16:9 / 9:16 / 1:1 / 4:3 / 3:4 | — | Output frame shape. |
resolution | 480p / 720p | 720p | Sets the per-second rate. |
generate_audio | boolean | true | Native dialogue, music, and effects. Same price on or off. |
seed | integer -1–4294967295 | random | Fix it to compare prompt changes; -1 is random. |
Without reference videos you pay for output seconds: $0.10 at 480p, $0.20 at 720p. With reference videos, the input video seconds (at least 2) are added to the output length and billed at a lower rate: $0.065 at 480p, $0.13 at 720p. With duration: "auto" the quote assumes 15 seconds and the final charge uses the generated length.
| Output | 480p | 720p |
|---|---|---|
| 5s, images only | $0.50 | $1.00 |
| 10s, images only | $1.00 | $2.00 |
| 5s + 5s reference video | $0.65 | $1.30 |
| 10s + 10s reference video | $1.30 | $2.60 |
Failed runs are not charged.
Other Seedance 2.0 Fast endpoints and tiers: bytedance/seedance/2.0/fast/text-to-video, bytedance/seedance/2.0/fast/image-to-video, bytedance/seedance/2.5/reference-to-video, bytedance/seedance/2.0/reference-to-video, bytedance/seedance/2.0/mini/reference-to-video.
Start building
Submit this model through the SandBase Unified Run API.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/run" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "bytedance/seedance/2.0/fast/reference-to-video",
"images": [
"https://static.sandbase.ai/examples/bfl/flux-1/fill/input_image_0.jpeg",
"https://static.sandbase.ai/examples/alibaba/wan/2.2/animate/replace/input_image_0.png"
],
"prompt": "Room is slowly getting filled from empty state to fully organized with furnitures. Camera is fixed timelapse.",
"duration": 5,
"resolution": "720p",
"generate_audio": true
}
SANDBASE_JSON
)
run_id=$(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"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.
POST to /v1/run with this model ID and its inputs. The request example above includes submission and polling.
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"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.
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.
seedintegerRandom seed for reproducible results. Omit or use -1 for a random seed.
Minimum: -1
Maximum: 4294967295
audiosarrayThe URLs of reference audio files to guide video generation.
imagesarrayThe URLs of reference images to guide video generation.
promptstringrequiredThe text prompt to generate a video from.
Default: "Room is slowly getting filled from empty state to fully organized with furnitures. Camera is fixed timelapse."
videosarrayThe URLs of reference videos to guide video generation. Up to 3 MP4 or MOV files, 2-15 seconds combined duration, under 50 MB total.
durationvalueOutput 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
resolutionstringThe resolution of the video to generate.
Default: "720p"
Possible values: "480p", "720p"
aspect_ratiostringOutput aspect ratio. Omit to let the model choose from the prompt and reference inputs.
Possible values: "16:9", "9:16", "1:1", "4:3", "3:4"
generate_audiobooleanGenerate a synchronized audio track. Pricing is the same either way.
Default: true
{
"model": "bytedance/seedance/2.0/fast/reference-to-video",
"images": [
"https://static.sandbase.ai/examples/bfl/flux-1/fill/input_image_0.jpeg",
"https://static.sandbase.ai/examples/alibaba/wan/2.2/animate/replace/input_image_0.png"
],
"prompt": "Room is slowly getting filled from empty state to fully organized with furnitures. Camera is fixed timelapse.",
"duration": 5,
"resolution": "720p",
"generate_audio": true
}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/75a869b6765226f0e2f4.jpg",
"source": "Self organization completed prediction",
"source_url": "https://www.sandbase.ai/model/bytedance/seedance/2.0/fast/reference-to-video",
"url": "https://static.sandbase.ai/examples/79689fb0-69ec-46be-aec5-bd3e552c32e9/output/1b8bf170-1176-46d6-ae66-c4c218ab9591.mp4"
}
]