Black Forest Labs Flux 3 Start End To Video Draft
Playground
Try it on WaveSpeedAI!FLUX 3 Start-End-to-Video Draft quickly generates a transition between required start and end images, with prompt-guided motion, optional synchronized audio, and flexible 5-20 second duration for rapid keyframe iteration.
Features
FLUX 3 Draft Start-End-to-Video quickly generates a transition between a required starting image and a required ending image. Use the prompt to test the action, transformation, camera movement, pacing, and visual style that connect the two keyframes before moving to a final-quality workflow.
Key Capabilities
- Create quick transition previews between a start image and an end image.
- Test subject movement, transformations, camera paths, environment changes, and pacing.
- Optionally generate synchronized audio for early transition and sound tests.
- Choose a duration from 5 to 20 seconds.
- Support landscape, portrait, square, and cinematic aspect ratios.
Parameters
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Describe the action or transformation connecting the start and end images, including camera movement, timing, mood, lighting, and style. |
| start_image | Yes | Image used as the first visual keyframe. |
| end_image | Yes | Image used as the final visual keyframe. |
| aspect_ratio | No | Output aspect ratio. Options: 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, or 9:16. |
| duration | No | Draft video duration in seconds. Choose an integer from 5 to 20. Default: 5. |
| generate_audio | No | Generate synchronized audio for the draft transition. Default: true. |
How to Use
- Provide the image that should appear at the beginning of the transition.
- Provide the image that should appear at the end of the transition.
- Describe the movement, transformation, camera path, and pacing between the keyframes.
- Choose the aspect ratio and duration for the draft preview.
- Enable generate_audio when you want to test matching ambience, effects, music, or dialogue.
Prompting Tips
- Describe the visual path from the start image to the end image rather than listing unrelated scenes.
- Explain what moves, transforms, appears, disappears, or changes between the keyframes.
- Use camera directions such as dolly-in, pull-back, orbit, tracking shot, or crane movement.
- Start with a simple transition, then refine the prompt after reviewing the first draft.
Pricing
| Billing Unit | Price |
|---|---|
| Per second | $0.06 |
Billing Rules
- The billed duration is rounded up to the next whole second.
- The minimum billed duration is 5 seconds.
- The maximum billed duration is 20 seconds.
- Audio generation does not add a separate charge in the current pricing formula.
- Example: a 5-second draft costs $0.30.
- Example: a 10-second draft costs $0.60.
Best Use Cases
- Product reveals, logo transitions, and before-and-after concepts.
- Character transformations and outfit or environment changes.
- Keyframe-based story moments and social-media transitions.
- Quickly comparing different motion paths between two defined states.
Notes
- Prompt, start_image, and end_image are required.
- Use visually compatible start and end images when you want a smoother transition.
- Draft outputs are intended for exploration and iteration.
Authentication
For authentication details, please refer to the Authentication Guide.
API Endpoints
Submit Task & Query Result
set -euo pipefail
export WAVESPEED_API_KEY="your-api-key"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic ocean wave at sunrise, highly detailed",
"start_image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
"end_image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
"aspect_ratio": "21:9",
"resolution": "720p",
"duration": 5,
"generate_audio": true
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/black-forest-labs/flux-3/start-end-to-video-draft" \
-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 text prompt describing the video you want to generate. | |
| start_image | string | Yes | - | - | Optional image used as the edited video's first frame. |
| end_image | string | Yes | - | - | Optional image used as the edited video's first frame. |
| aspect_ratio | string | No | - | 21:9, 2:1, 16:9, 4:3, 1:1, 3:4, 9:16 | The aspect ratio of the generated media. |
| resolution | string | No | 720p | 720p, 1080p | Resolution of the generated video. |
| duration | integer | No | 5 | 5 ~ 20 | Video length in seconds (5-20). |
| generate_audio | boolean | No | true | - | Whether to generate audio for the video. |
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 |