A versatile video family for text, image, sound-to-video, and animate workflows — full fp8 or fast LightX2V.
No GPU. No setup. Cancel anytime.
WAN 2.2 14B is a versatile video model built for smooth motion, consistent visuals, and expressive, prompt-driven storytelling from frame to frame.
Full fp8 variants run the standard 20-step schedule for T2V, I2V, and S2V. LightX2V variants run the fast six-step app schedule for T2V, I2V, S2V, animate-move, and animate-replace workflows.
WAN 2.2 14B ships in 8 workflow and quality variants. Pick the mode that fits, or start with the default.
| Variant | Details | From | |
|---|---|---|---|
T2V Full (fp8) Qualitywan_v2.2-14b-fp8_t2v | Workflow: text-to-video Duration: 1 – 10 s Resolution: 480–1536 px · 16/32 fps (16 default) Steps: 20 default · 20–40 Guidance: 3.5 default · 1.5–8 | 115 Spark · $0.58 | Create → |
I2V Full (fp8) Qualitywan_v2.2-14b-fp8_i2v | Workflow: image-to-video Duration: 1 – 10 s Resolution: 480–1536 px · 16/32 fps (16 default) Steps: 20 default · 20–40 Guidance: 4 default · 1.5–8 | 115 Spark · $0.58 | Create → |
S2V Full (fp8) Qualitywan_v2.2-14b-fp8_s2v | Workflow: sound-to-video / lip-sync with uploaded audio Duration: 1 – 10 s Resolution: 480–1536 px · 16/32 fps (16 default) Steps: 20 default · 20–40 Guidance: 6 default · 1.5–8 | 115 Spark · $0.58 | Create → |
T2V LightX2V Fastwan_v2.2-14b-fp8_t2v_lightx2v | Workflow: text-to-video Duration: 1 – 10 s Resolution: 480–1536 px · 16/32 fps (16 default) Steps: 4 default · 4–8 Guidance: 1 default · 0.7–1.6 | 46.2 Spark · $0.23 | Create → |
I2V LightX2V Fastwan_v2.2-14b-fp8_i2v_lightx2v | Workflow: image-to-video Duration: 1 – 10 s Resolution: 480–1536 px · 16/32 fps (16 default) Steps: 4 default · 4–8 Guidance: 1 default · 0.7–1.6 | 46.2 Spark · $0.23 | Create → |
S2V LightX2V Fastwan_v2.2-14b-fp8_s2v_lightx2v | Workflow: sound-to-video / lip-sync with uploaded audio Duration: 1 – 10 s Resolution: 480–1536 px · 16/32 fps (16 default) Steps: 4 default · 4–8 Guidance: 1 default · 0.7–1.6 | 46.2 Spark · $0.23 | Create → |
Animate Move LightX2V Fastwan_v2.2-14b-fp8_animate-move_lightx2v | Workflow: motion transfer animation Duration: 1 – 20 s Resolution: 480–1536 px · 16/32 fps (16 default) Steps: 6 default · 4–8 Guidance: 1 default · 0.7–1.6 | 46.2 Spark · $0.23 | Create → |
Animate Replace LightX2V Fastwan_v2.2-14b-fp8_animate-replace_lightx2v | Workflow: SAM2 subject replacement animation Duration: 1 – 20 s Resolution: 480–1536 px · 16/32 fps (16 default) Steps: 6 default · 4–8 Guidance: 1 default · 0.7–1.6 | 46.2 Spark · $0.23 | Create → |
Use pay-as-you-go Spark packs for each clip (1 Spark = $0.005), or choose a flat-rate Sogni plan for credit-free fair-use generation in the app.
| Variant / configuration | Spark | USD |
|---|---|---|
| Full variants · 5 s · 1280 × 720 · 81 frames · 20 steps | 115 Spark | $0.58 |
| LightX2V variants · 5 s · 1280 × 720 · 81 frames · 4–6 steps | 46.2 Spark | $0.23 |
| LightX2V variants · 10 s · 1280 × 720 | 92.4 Spark | $0.46 |
One Sogni API key reaches every model on the Supernet — call WAN 2.2 14B with the exact model id for the variant you want.
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
}' Example uses wan_v2.2-14b-fp8_t2v. Use any exact model id from the Variants table above. 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.
Use a flat monthly plan for credit-free fair-use generation, or buy Spark packs when pay-as-you-go fits better. Both run on the same creator-owned GPU network.
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 with Spark packs.
Runs on a decentralized GPU network where workers share subscription revenue.
Use the LightX2V workflow that matches your input when speed matters, including T2V, I2V, S2V, animate-move, and animate-replace. Use Full fp8 T2V, I2V, or S2V when you want the standard 20-step quality path.
Create in the app, or build with the API. Your call.