Introduction
Seedance 2.0 Image-to-Video animates a still image into a moving shot. Your image establishes the opening frame; the prompt describes what happens next, such as a subject turning, fabric moving or the camera approaching. An optional closing image can also guide the ending.
Developed by ByteDance and introduced in its February 12, 2026 launch article, Seedance 2.0 combines video and audio generation. In this mode, the useful starting point is an existing visual you want to bring into motion.
Choose the starting point for your Seedance 2.0 sequence
| Starting material | Mode |
|---|---|
| A script or scene description | Seedance 2.0 Text to Video |
| An approved opening still | Seedance 2.0 Image to Video |
| Separate appearance, motion or audio references | Seedance 2.0 Reference to Video |
Key features & highlights
Multimodal creative direction
Seedance 2.0 brings text, images, video and audio into one creative process. References can guide a character's appearance, a scene's composition, movement, camera language or sound, rather than serving only as pictures to animate.
Complex motion and interaction
The model is designed to handle sequences involving several subjects, connected actions and interaction with the environment. Its motion modeling covers both larger movements and smaller details such as gestures, facial expressions and moving fabric.
Audio and video generated together
Speech, environmental sound, effects and music can be generated alongside the picture. This joint approach lets sound participate in the scene's rhythm instead of being treated solely as a separate editing step.
Storytelling and camera control
Natural-language direction can describe a sequence of shots, changes in viewpoint and the progression of a performance. The model family also supports video editing and continuation; those operations require a compatible video-input workflow, not text-only or first-frame generation.
Request parameters
| Parameter | Required | Description |
|---|---|---|
prompt | No | Optional, but worth writing: say what happens after the frame rather than restate what is already visible — the action, the camera move, the passage of time, the sound. |
image_url | Yes | Public, directly downloadable link to the first frame; required. |
last_image_url | No | Optional closing frame, only valid together with |
aspect_ratio | No | Output framing, |
resolution | No | Output resolution, 720p by default and reaching 4k; no upscaled tier is offered here. It sets a rate tier, and higher tiers mean bigger files and longer renders. |
duration_seconds | No | Length in whole seconds, 4 to 15, defaulting to 5, and the billed quantity. |
generate_audio | No | Whether a native soundtrack is rendered in sync with the picture. On by default; switch it off for silent loops or when sound is added in post. Default: |
seed | No | Integer seed; omit it and each run draws its own. Fix it with everything else held constant to judge what a prompt edit actually changed. |
return_last_frame | No | Also returns the clip’s final frame as a separate image next to the video. Send it to image-to-video as the next opening frame to chain shots without exporting a still yourself. Default: |
bitrate_mode | No | Encoding bitrate of the delivered file: |
watermark | No | Adds the model’s own visible "AI generated" watermark to the video. Off by default; switch it on when the place you publish requires AI-made footage to be labelled. Default: |
Pricing
| Specification | Price |
|---|---|
| $0.07 / second |
| $0.152 / second |
| $0.374 / second |
| $0.778 / second |
Use cases
Animate an approved product photograph
Begin with a desk lamp, bottle or furniture shot and request a restrained camera move or one product action. Compare the result with the original silhouette, label and surface details before publishing.
Bring an illustrated character into motion
Use a character illustration as the first frame and specify a small gesture or expression change. Check the face, hands and drawing style throughout the movement, not just at the opening.
Connect two storyboard frames
Supply opening and closing images that depict compatible subjects and surroundings. Describe the movement between them. Review the middle of the clip for unexpected substitutions or abrupt changes.
Prompt guide & pro tips
How to animate a still with Seedance 2.0
Let the image establish appearance and composition; use the prompt to describe the change over time. Identify the moving subject, state the movement's direction and pace, then specify the camera separately.
- Upload the opening still through
image_url. - Choose one main action that fits the image.
- Add one camera movement, or explicitly keep the camera fixed.
- Describe the sound and the important visual details to retain.
For a source photograph of a ceramic teapot beside a window, choose duration_seconds of 5:
Continue from the supplied teapot photograph in a single shot.
A narrow stream of steam rises from the spout and slowly curls toward the window.
The camera makes a gentle forward push; the teapot and table stay stationary.
Retain the blue painted pattern, lid shape and soft window light.
Quiet room ambience, without speech, music, captions or added logos.
Describe a transition between first and last frames
If you have a closing image, supply it through last_image_url. Describe the action connecting the two states—for example, a closed fan opening toward the final pose. Use compatible subjects and framing so the prompt does not have to reconcile two unrelated scenes.
For a multi-stage action, describe the stages in order rather than assigning exact timestamps. Seedance 2.0 follows shot order more reliably than precise second ranges.
Keep the movement consistent with the source
A stationary object and a moving camera are different instructions. “Push closer to the teapot” changes the view; “the teapot slides toward the camera” changes the object. Remove contradictory directions before adding detail.
If the visual style drifts, name the intended style explicitly and use a source image already in that style. If unwanted text appears, request no captions and use source artwork without incidental text when that text is not needed.
Content boundaries
Seedance 2.0 · Image-to-Video — Uncensored. SpicyAPI adds no platform-side content filter. Model restrictions still apply, and results are not guaranteed. You are responsible for complying with our content policy.
API quick start
# Generate the idempotency key once; reuse it when retrying after a lost response.
export SPICY_IDEMPOTENCY_KEY="${SPICY_IDEMPOTENCY_KEY:-$(uuidgen)}"
curl -X POST https://api.spicyapi.ai/api/v1/jobs/createTask \
-H "Authorization: Bearer $SPICY_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $SPICY_IDEMPOTENCY_KEY" \
-d '{
"model": "bytedance/seedance-2.0/image-to-video",
"input": {
"aspect_ratio": "adaptive",
"bitrate_mode": "standard",
"duration_seconds": 5,
"generate_audio": true,
"image_url": "https://example.com/reference.png",
"prompt": "A slow aerial shot drifting over a misty pine forest at sunrise"
}
}'
# Copy data.taskId from the response into TASK_ID, then poll the status.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.spicyapi.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
-H "Authorization: Bearer $SPICY_API_KEY"
See the API reference for authentication, the complete schema, polling, and error handling.
