Skywork AI Skyreels V4 Image To Video API Documentation
Playground
Try it on WaveSpeedAI!SkyReels V4 Image to Video is a fast AI image-to-video generation model that creates high-quality videos from image references and text prompts using the SkyReels V4 image2video workflow. Ready-to-use REST inference API for animating images, product videos, character motion, branded storytelling, social media clips, advertising creatives, and professional image-to-video workflows with simple integration, no coldstarts, and affordable pricing.
Features
Skywork AI SkyReels V4 Image-to-Video generates videos from a starting image, with optional middle-frame and end-frame guidance for stronger visual control. It supports standard and fast generation modes, multiple resolutions, optional sound effects, and prompt-driven motion design for cinematic, product, and storytelling workflows.
Why Choose This?
-
Image-guided video generation Start from a first-frame image and turn it into a motion video clip with prompt-based control.
-
Multi-frame guidance Optionally add middle-frame images and an end-frame image to better control progression, structure, and visual consistency.
-
Two generation modes Choose
stdfor higher-quality output orfastfor quicker, lower-cost generation. -
Multiple resolution options Supports
480p,720p, and1080pto balance quality and budget. -
Optional sound effects Enable
soundwhen you want the video generated with audio effects. -
Production-ready workflow Suitable for product videos, stylized motion design, short-form storytelling, and visual prototyping.
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | The prompt describing the video motion or camera behavior. |
| first_frame_image | Yes | First frame image URL. |
| end_frame_image | No | Optional end frame image URL. |
| images | No | Optional middle frame image URLs. Upload up to 6 images. |
| duration | No | Duration of the generated video in seconds. Range: 3–15. Default: 5. |
| resolution | No | Output video resolution. Supported values: 480p, 720p, 1080p. Default: 1080p. |
| sound | No | Whether to generate sound effects with the video. Default: false. |
| mode | No | Quality/performance mode. Supported values: std, fast. Default: std. fast mode currently requires sound=false. |
How to Use
- Upload the first frame — provide the starting image for the video.
- Write your prompt — describe the motion, camera movement, pacing, and visual behavior you want.
- Add guide frames (optional) — upload middle-frame images and/or an end-frame image for more controlled progression.
- Choose duration — select a clip length between
3and15seconds. - Choose resolution — use
480p,720p, or1080pdepending on quality and budget needs. - Choose mode — use
stdfor higher quality orfastfor quicker generation. - Enable sound (optional) — turn this on if you want generated sound effects. If using
fast, keepsound=false. - Submit — run the model and download the generated video.
Example Prompt
A cinematic product reveal with smooth forward camera motion, soft reflections, elegant studio lighting, subtle object rotation, and premium commercial pacing.
Pricing
Pricing depends on duration, resolution, and mode.
Standard Mode
| Resolution | Per Second | 5s Cost |
|---|---|---|
| 480p | $0.11 | $0.55 |
| 720p | $0.14 | $0.70 |
| 1080p | $0.35 | $1.75 |
Fast Mode
| Resolution | Per Second | 5s Cost |
|---|---|---|
| 480p | $0.08 | $0.40 |
| 720p | $0.11 | $0.55 |
| 1080p | $0.275 | $1.375 |
Example Costs
Standard Mode
| Resolution | 3s | 5s | 10s | 15s |
|---|---|---|---|---|
| 480p | $0.33 | $0.55 | $1.10 | $1.65 |
| 720p | $0.42 | $0.70 | $1.40 | $2.10 |
| 1080p | $1.05 | $1.75 | $3.50 | $5.25 |
Fast Mode
| Resolution | 3s | 5s | 10s | 15s |
|---|---|---|---|---|
| 480p | $0.24 | $0.40 | $0.80 | $1.20 |
| 720p | $0.33 | $0.55 | $1.10 | $1.65 |
| 1080p | $0.825 | $1.375 | $2.75 | $4.125 |
Billing Rules
- Base multiplier starts from $0.10 per second
- Pricing scales linearly with
duration stdandfastuse different resolution multiplierssounddoes not affect pricing directlyfastmode currently requiressound=false
Best Use Cases
- Product motion videos — Turn still product shots into polished reveal clips.
- Storytelling sequences — Use start, middle, and end guidance to shape a clear visual arc.
- Creative prototyping — Test motion concepts quickly with
fastmode. - Social and ad content — Generate short-form videos with clear visual direction.
- Cinematic image animation — Create controlled motion from a sequence of reference frames.
Pro Tips
- Use a strong first-frame image for better visual consistency.
- Add middle or end frames when scene progression matters more than freeform motion.
- Keep prompts focused on motion, pacing, and camera behavior rather than static visual details already present in the images.
- Use
fastmode for quick iteration, then switch tostdfor final-quality output. - Keep
sound=falsewhen usingfastmode. - Start with shorter durations to validate motion before generating longer clips.
Notes
promptandfirst_frame_imageare required.imagessupports up to 6 optional middle-frame images.durationsupports 3–15 seconds.resolutiondefaults to1080p.modedefaults tostd.fastmode currently requiressound=false.- Pricing depends on
duration,resolution, andmode.
Related Models
- Skywork AI SkyReels V4 Text-to-Video — Generate videos directly from text prompts.
- Skywork AI SkyReels V3 Reference-to-Video — Generate videos from one to four reference images and a prompt.
- Skywork AI SkyReels V3 Extend Video — Continue an existing video clip with newly generated footage.
- Skywork AI SkyReels V3 Pro Multi Avatar — Higher-tier two-speaker avatar generation from one scene image.
Authentication
For authentication details, please refer to the Authentication Guide.
API Endpoints
Submit Task & Query Result
set -euo pipefail
export WAVESPEED_API_KEY="your-api-key"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic ocean wave at sunrise, highly detailed",
"first_frame_image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
"duration": 5,
"resolution": "1080p",
"sound": false,
"mode": "std"
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/skywork-ai/skyreels-v4/image-to-video" \
-H "Authorization: Bearer ${WAVESPEED_API_KEY}" \
-H "Content-Type: application/json" \
-d "${REQUEST_BODY}")
TASK=$(printf '%s' "${SUBMIT_RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "${TASK}" | jq -r '.id // empty')
if [ -z "${PREDICTION_ID}" ]; then
printf 'Submission response did not contain a prediction id
' >&2
exit 1
fi
RESULT_URL=$(printf '%s' "${TASK}" | jq -r '.urls.get // empty')
if [ -z "${RESULT_URL}" ]; then RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/${PREDICTION_ID}/result"; fi
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(curl --silent --show-error --fail-with-body \
"${RESULT_URL}" \
-H "Authorization: Bearer ${WAVESPEED_API_KEY}")
RESULT=$(printf '%s' "${RESPONSE}" | jq 'if type == "object" and has("data") then .data else . end')
STATUS=$(printf '%s' "${RESULT}" | jq -r '.status // empty')
case "${STATUS}" in
completed) printf '%s\n' "${RESULT}" | jq '.outputs'; break ;;
failed|cancelled|timeout) printf '%s\n' "${RESULT}" | jq . >&2; exit 1 ;;
created|processing) sleep 2 ;;
*) printf 'Unexpected status: %s
' "${STATUS}" >&2; exit 1 ;;
esac
doneParameters
Task Submission Parameters
Request Parameters
| Parameter | Type | Required | Default | Range | Description |
|---|---|---|---|---|---|
| prompt | string | Yes | - | The prompt describing the video motion or camera behavior. | |
| first_frame_image | string | Yes | - | - | First frame image URL. |
| end_frame_image | string | No | - | - | Optional end frame image URL. |
| images | array<string> | No | - | 0 ~ 6 items | Optional middle frame image URLs. Upload up to 6 images. |
| duration | integer | No | 5 | 3 ~ 15 | Duration of the generated video in seconds. |
| resolution | string | No | 1080p | 480p, 720p, 1080p | Output video resolution. |
| sound | boolean | No | false | - | Whether to generate sound effects with the video. |
| mode | string | No | std | std, fast | Quality/performance mode. Fast mode currently requires sound to be false. |
Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data.id | string | Unique identifier for the prediction, Task Id |
| data.model | string | Model ID used for the prediction |
| data.outputs | array | Output values, usually URL strings; some models return text strings or structured result objects (empty when status is not completed) |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to retrieve the prediction result |
| data.status | string | Status of the task: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”) |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |
Result Request Parameters
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
| id | string | Yes | - | Task ID |
Result Response Parameters
| Parameter | Type | Description |
|---|---|---|
| code | integer | HTTP status code (e.g., 200 for success) |
| message | string | Status message (e.g., “success”) |
| data | object | The prediction data object containing all details |
| data.id | string | Unique identifier for the prediction |
| data.model | string | Model ID used for the prediction |
| data.outputs | array<string | object> | Array of generated outputs (empty when status is not completed). Items are usually URL strings, but may be text strings or structured result objects, depending on the model. |
| data.urls | object | Object containing related API endpoints |
| data.urls.get | string | URL to poll for the prediction result |
| data.status | string | Status: created, processing, completed, or failed |
| data.created_at | string | ISO timestamp of when the request was created |
| data.error | string | Error message (empty if no error occurred) |
| data.timings | object | Object containing timing details |
| data.timings.inference | integer | Inference time in milliseconds |