krea/krea-wan/video-to-video
Krea Wan Video To Video is krea's video-to-video AI model. Transform, enhance, and edit video content using text prompts - from style changes to object manipulation and scene modification.
Example output — click Run to generate your own
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
https://api.sandbase.ai/v1/runkrea/krea-wan/video-to-videoInput Schema
4 parameters · 1 required · 3 optional
| Parameter | Type | Required | Description |
|---|---|---|---|
prompt | string | Required | Prompt for the video-to-video generation. |
seed | integer | Optional | Seed for the video-to-video generation. |
video | string | Optional | URL of the input video. Currently, only outputs of 16:9 aspect ratio and 480p resolution are supported. Video duration should be less than 1000 frames at 16fps, and output frames will be 6 plus a multiple of 12, for example 18, 30, 42, etc. |
strength | number | Optional | Denoising strength for the video-to-video generation. 0.0 preserves the original, 1.0 completely remakes the video. · Min: 0.01 · Max: 1 · Default: 0.85 |
Output Schema
| Field | Type | Description |
|---|---|---|
id | string | Unique identifier for the generation task |
status | string | Task status: pending, running, completed, failed, timeout |
model | string | Model used for the generation |
outputs | array | Array of output items |
outputs[].url | string | URL of the generated artifact |
outputs[].content_type | string | MIME type (e.g. image/png, video/mp4) |
error | object | null | Error details if failed, null on success |
error.type | string | Machine-readable error type code |
error.message | string | Human-readable error description |
Async Workflow
This model uses asynchronous execution. Submit a request and poll for the result.
- Submit — POST to /v1/run, receive an
id - Poll — GET /v1/run/{id} until status is
completed,failed, ortimeout - Retrieve — Read
outputsfrom the completed response
Code Examples
Ready-to-run snippets
# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "krea/krea-wan/video-to-video",
"video": "https://static.sandbase.ai/examples/krea/krea-wan/video-to-video/input_video_0.mp4",
"prompt": "A powerful, matte black jeep, its robust frame contrasting with the lush green surroundings, navigates a winding jungle road, kicking up small clouds of dust and loose earth from its tires.",
"strength": 0.85
}'
# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
-H "Authorization: Bearer YOUR_API_KEY"API README
Krea Wan 14B
video to video in the Krea WAN lineup is built to reinterpret an existing clip while using its timing and motion as the foundation. The krea wan video to video configuration combines that transformation with the quality and motion profile represented by this exact model version, so teams can choose it deliberately among adjacent family variants. It is useful when the input already establishes part of the creative intent and the model must supply a polished result rather than a generic media conversion, with subject identity, scene logic, visual hierarchy, and the delivery goal kept explicit.
For production work with krea/krea-wan/video-to-video, begin with the non-negotiable content, then describe the desired change, framing, action, atmosphere, and finishing cues in that order. Separate what must remain recognizable from what may vary, and prefer concrete nouns and observable actions over abstract praise. That structure makes outputs easier to compare across storyboard passes, campaign variants, catalog assets, and other repeatable creative pipelines.
Highlights
Motion-preserving transformation. Uses source action and timing as a foundation for a new interpretation.
Temporal style transfer. Applies changed texture, atmosphere, or subject treatment consistently across frames.
Scene-aware revision. Changes requested content while keeping unrelated motion and composition recognizable.
krea wan video to video reduced frame drift. Maintains visual continuity as the transformed sequence progresses. This is the defining creative strength of the krea wan video to video configuration.
Pricing
| Duration | Price per generated clip |
|---|---|
| Per generated second | $0.0250 |
Billing follows params.duration * 0.025: multiply generated seconds by the $0.0250 per-second rate.
When to Use
| ✅ Good fit | ❌ Consider alternatives |
|---|---|
| The model's named workflow matches the source material and intended output | A different input modality or model route is required |
| A managed asynchronous result is suitable for the production pipeline | A synchronous, interactive editor is essential |
| The documented controls cover the required duration, framing, or format | The project needs controls outside this endpoint's schema |
| Creative iteration benefits from a repeatable request structure | Exact deterministic pixels, frames, geometry, or samples are mandatory |
| A finished downloadable media asset is the desired deliverable | Editable source layers or a native project file are required |
Prompt Guide
For generation, state the intended result first, then add the subject or source treatment, progression, style, and delivery constraints. Keep one creative variable per phrase, use the documented field names for controls, and change one setting at a time when comparing results.
{
"prompt": "A powerful, matte black jeep, its robust frame contrasting with the lush green surroundings, navigates a winding jungle road, kicking up small clouds of dust and loose earth from its tires.",
"video": "https://static.sandbase.ai/examples/krea/krea-wan/video-to-video/input_video_0.mp4"
}
Technical Specs
| Spec | Value |
|---|---|
| Model ID | krea/krea-wan/video-to-video |
| Inputs | prompt, seed, strength, video |
| Required inputs | prompt |
| Output fields | content_type, url |
| Execution | Async (submit, then poll for result) |