Wan FLF2V | Fast Image-to-Video API

Wan FLF2V — wavespeed-ai/wan-flf2v

Wan FLF2V is a first-last-frame-to-video model that generates a short video by interpolating a coherent motion path between a first_image and a last_image, guided by an optional text prompt. Provide the starting frame and the ending frame, then describe what happens in between (e.g., a transformation, assembly, reveal, or scene change). The model produces a smooth transition clip while keeping the beginning and ending states aligned with your provided frames.

Key capabilities

First-last-frame guided video generation (first_image → last_image)
Prompt-guided in-between action and transformation logic
Supports negative_prompt to reduce artifacts and unwanted motion
Size selection for different output resolutions
Seed control for reproducible results

Use cases

Transformation sequences (frame → completed object, sketch → final render)
Product assembly and reveal animations (parts → finished product)
Before/after transitions (makeover, restoration, environment change)
Visual storytelling between two keyframes for ads and social
Storyboard “in-betweening” from a first and last shot

Pricing

Mode	Size tier	5s	10s
Standard	Non-720p size	$0.30	$0.45
Fast	Non-720p size	$0.15	$0.225
Standard	720p size (1280×720 / 720×1280)	$0.40	$0.60
Fast	720p size (1280×720 / 720×1280)	$0.25	$0.375

Inputs

first_image (required): starting frame
last_image (required): ending frame
prompt (optional): describe the transition and what happens in between
negative_prompt (optional): what to avoid (blur, jitter, distortion, artifacts)

Parameters

duration: video length in seconds
size: output resolution selection (e.g., 832×480)
num_inference_steps: sampling steps
guidance_scale: prompt adherence strength
seed: random seed (-1 for random; fixed value for reproducible results)

Prompting guide (FLF2V)

A good prompt explains how the first becomes the last:

Template: Fixed camera. Start exactly from the first image and end exactly at the last image. In between, show [mechanism] smoothly and coherently. No flicker, no warping.

Example prompts

Transform the car frame into a complete vehicle. Parts assemble step-by-step, bolts tighten, panels slide into place, paint and reflections appear gradually, cinematic lighting, smooth motion, fixed camera.
A rough clay sculpture becomes a polished ceramic statue, cracks heal, glaze forms, subtle dust motes, steady camera, seamless transition.
A bare room becomes fully furnished, objects slide into place naturally, lighting stays consistent, no jitter.

Wan Flf2v API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-flf2v with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to completed, then read the output URL from data.outputs[0]. Examples for Wan Flf2v below.

HTTP example

# Submit the prediction
curl -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-flf2v" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d '{
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "negative_prompt": "blurry, low quality, distorted",
    "duration": 5,
    "size": "832*480",
    "num_inference_steps": 30,
    "guidance_scale": 5,
    "seed": -1
}'

# Response includes a prediction id. Poll for the result:
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY"

# When status is "completed", read the output from data.outputs[0].

Node.js example

// npm install wavespeed
const WaveSpeed = require('wavespeed');

const client = new WaveSpeed(); // reads WAVESPEED_API_KEY from env

const result = await client.run("wavespeed-ai/wan-flf2v", {
        "prompt": "A cinematic shot of a city at sunset, soft golden light",
        "negative_prompt": "blurry, low quality, distorted",
        "duration": 5,
        "size": "832*480",
        "num_inference_steps": 30,
        "guidance_scale": 5,
        "seed": -1
});

console.log(result.outputs[0]); // → URL of the generated output

Python example

# pip install wavespeed
import wavespeed

output = wavespeed.run(
    "wavespeed-ai/wan-flf2v",
    {
    "prompt": "A cinematic shot of a city at sunset, soft golden light",
    "negative_prompt": "blurry, low quality, distorted",
    "duration": 5,
    "size": "832*480",
    "num_inference_steps": 30,
    "guidance_scale": 5,
    "seed": -1
}
)

print(output["outputs"][0])  # → URL of the generated output

Wan Flf2v API — Frequently asked questions

What is the Wan Flf2v API?

Wan Flf2v is a WaveSpeedAI model for video generation from images, exposed as a REST API on WaveSpeedAI. Wan-2.1 FLF2V converts a start and end frame into a smooth, coherent video sequence, bridging frames with realistic motion transitions. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Wan Flf2v API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID; poll the prediction endpoint until status flips to "completed", then read the output URL from the result. The playground generates a ready-to-paste code sample in Python, JavaScript, or cURL for whatever inputs you've set. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/wavespeed-ai/wan-flf2v.

How much does Wan Flf2v cost per run?

Wan Flf2v starts at $0.30 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Wan Flf2v accept?

Key inputs: `prompt`, `duration`, `size`, `seed`, `guidance_scale`, `num_inference_steps`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/wavespeed-ai/wan-flf2v.

How long does Wan Flf2v take to generate?

Average end-to-end generation time on WaveSpeedAI is around 91 seconds per request — measured across recent runs. Queue time scales with global demand; live status is visible in the prediction record.

Can I use Wan Flf2v outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (WaveSpeedAI). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.

示例查看全部

相關模型

README