wan_v2.2-14b-fp8_t2v Full-step WAN — maximum quality from the WAN line.
No GPU. No setup. Cancel anytime.
The undistilled WAN 2.2 14B runs twenty to forty steps for the cleanest motion the WAN line can produce.
Choose it when WAN’s character strengths matter and the clip is worth the full-step price; otherwise LightX2V covers the same workflows at 40% of the cost.
WAN 2.2 14B exposes these workflow variants — pass the matching model id.
| Workflow | Model id |
|---|---|
| Text → video | wan_v2.2-14b-fp8_t2v |
| Image → video | wan_v2.2-14b-fp8_i2v |
| Sound → video (lip-sync) | wan_v2.2-14b-fp8_s2v |
On the Sogni API you pay per clip in Spark (1 Spark = $0.005). Prefer a flat rate? The Sogni app runs WAN 2.2 14B and 100+ other models credit-free under fair use.
| Configuration | Spark | USD |
|---|---|---|
| 5 s · 1280 × 720 · 81 frames · 20 steps | 115 Spark | $0.58 |
One Sogni API key reaches every model on the Supernet — call WAN 2.2 14B by id.
import { SogniClient } from '@sogni-ai/sogni-client';
const client = await SogniClient.createInstance({
appId: crypto.randomUUID(),
apiKey: process.env.SOGNI_API_KEY,
network: 'fast',
});
const project = await client.projects.create({
type: 'video',
modelId: 'wan_v2.2-14b-fp8_t2v',
positivePrompt: 'a slothicorn surfing a wave of liquid paint, slow push-in, cinematic',
numberOfMedia: 1,
duration: 5,
});
const [url] = await project.waitForCompletion();
console.log(url); // result link — download within 24hcurl https://api.sogni.ai/v1/creative-agent/workflows \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $SOGNI_API_KEY" \
-d '{
"input": {
"title": "First render",
"steps": [{
"id": "step1",
"toolName": "generate_video",
"arguments": { "prompt": "a slothicorn surfing a wave of liquid paint, slow push-in, cinematic", "videoModel": "wan22", "duration": 5 }
}]
},
"confirm_cost": true
}' REST workflow alias: wan22. Pin the exact id with the SDK. Full reference at docs.sogni.ai.
Real generations from Sogni. Hit Use prompt to open the app with WAN 2.2 14B selected and the full prompt preloaded.
Most platforms ration credits or rent a cloud GPU by the hour. Sogni gives you a flat monthly price for credit-free fair-use generation, powered by a creator-owned GPU network — or per-render Spark pricing if you'd rather pay as you go via the API.
One flat price in the app. Generate under fair use without a per-image meter.
Image, video, music, and language models in one workspace and one API key.
Prefer pay-as-you-go? Call WAN 2.2 14B by id and pay in Spark.
Runs on a decentralized GPU network where workers share subscription revenue.
Wan 2.2 is the leading open-source AI video model from Alibaba. It supports text-to-video and image-to-video, plus Animate Move and Animate Replace motion-transfer, and produces smooth motion with consistent visuals and expressive frame-to-frame storytelling. It ships in a fast LightX2V "Speed" version and a "Quality" version, and is released under the permissive Apache-2.0 license.
On Sogni, Wan 2.2 supports 480px to 1536px per side in 16px steps. Text-to-video and image-to-video support 17-161 frames, while sound-to-video and Animate modes support up to 321 frames. Wan renders internally at 16 fps; the 32 fps option is post-render interpolation for smoother output.
Animate Move and Animate Replace are motion-transfer modes: you supply a reference video and Wan 2.2 drives a character or subject's motion and appearance from it — retargeting the movement onto your subject (Move) or swapping who performs it (Replace). On versions, Wan 2.2 comes in a fast LightX2V "Speed" build that generates clips in just a few steps — the turbo default this page launches you into — and a "Quality" build tuned for maximum fidelity. Pick Speed for quick iteration, Quality for the final render.
Yes — covered jobs are credit-free under fair-use. There are no per-clip credits to buy, but active-job concurrency, generate queue limits, and fair-use controls apply. Covered jobs run on Sogni's shared GPU network and may queue during peak demand; heavy-usage based throttles reset each UTC day. Current model-level resolution and duration limits still apply, and larger supported outputs may vary by plan.
Sogni Unlimited is $20/month (or $199/year). Unlimited Pro is $50/month (or $498/year) and adds higher throughput, higher queue priority, and larger supported video outputs where available. Every plan starts with a 3-day free trial and you can cancel anytime.
Absolutely — Wan 2.2 follows long, structured prompts faithfully. The examples above show complete, unedited prompts alongside the playable clip each produced. Hit "Use prompt" to load the full prompt into the app and reproduce or remix it.
Create in the app, or build with the API. Your call.