imagestringrequired
Input image URL (face / character).
ByteDance DreamActor 2.0
bytedance/dreamactor/2.0DreamActor 2.0 by ByteDance transfers motion, facial expressions and lip movement from a driving video to the character in a reference image.
Try the model
Playground
Input
PNG, JPEG, WebP, or GIF · 20 MiB maximum
Input image URL (face / character).
This field is required.
Driving video providing motion, expressions and lip movement.
Additional Settings More
Customize your input with more control.
Crop the 1-second transition at the start of the output.
ResultExample
What would you like to do next?
Examples
Select an example to load its inputs and result into the playground.
- Open result ↗
Input
{ "image": "https://static.sandbase.ai/examples/1668055b-f263-449e-a2b0-64ce4b82aba2/input/e2db078d-d0b4-4317-bf55-9372a99f8359.png", "video": "https://static.sandbase.ai/examples/1668055b-f263-449e-a2b0-64ce4b82aba2/input/df52f6c5-d3e1-4bd2-8348-a8f1ab03ac18.mp4" }
ByteDance DreamActor 2.0
DreamActor 2.0 transfers body motion, facial expression, and lip movement from a driving video to the character in image.
Fields
| Field | Type | Default | Notes |
|---|---|---|---|
image | image URL, required | — | Character to animate. JPEG, PNG, or WebP URL. |
video | video URL, required | — | Driving video that supplies motion and expression. |
trim_first_second | boolean | true | Drop the first second, which is often used for alignment. |
Billing
$0.05 per output second. The quote before submission assumes 5 seconds; the final charge uses the measured length.
| Output | Price |
|---|---|
| 5s | $0.25 |
| 10s | $0.50 |
| 30s | $1.50 |
Failed runs are not charged.
Prompting
- Use a driving video with one clearly visible face and body.
- Match the character image's framing to the driving video.
Limits
- Output length follows the driving video.
Also on SandBase
Related: bytedance/omnihuman/1.5 (audio-driven).
Start building
Send your first request
Submit this model through the SandBase Unified Run API.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/run" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "bytedance/dreamactor/2.0",
"image": "https://static.sandbase.ai/examples/alibaba/wan/2.2/animate/move/input_image_1.png",
"video": "https://static.sandbase.ai/examples/alibaba/wan/2.2/animate/move/input_video_0.mp4",
"trim_first_second": true
}
SANDBASE_JSON
)
run_id=$(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
videostringrequired
Driving video providing motion, expressions and lip movement.
trim_first_secondboolean
Crop the 1-second transition at the start of the output.
Default: true
{
"model": "bytedance/dreamactor/2.0",
"image": "https://static.sandbase.ai/examples/alibaba/wan/2.2/animate/move/input_image_1.png",
"video": "https://static.sandbase.ai/examples/alibaba/wan/2.2/animate/move/input_video_0.mp4",
"trim_first_second": 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/75b7435157e8b8167bf1.jpg",
"source": "Self organization completed prediction",
"source_url": "https://www.sandbase.ai",
"url": "https://static.sandbase.ai/examples/1668055b-f263-449e-a2b0-64ce4b82aba2/output/12b99cff-c2ad-4774-b236-da1077703b6f.mp4"
}
]