För konton utan tidigare köp: körningar över 2 credits kräver en påfyllning.
Ny här?
10 gratis credits (0,10 US$) när du registrerar dig med Google
Användbar 24 timmar efter registrering, upp till 5 körningar per dag och högst 2 credits per körning. Andra inloggningsmetoder startar utan credits.
02
Examples
Real outputs from the public examples of this model on Replicate, with the prompt and settings that produced them. They were not generated live on this page.
Prompt
A sports car is driving very fast along a beach at sunset
Längd: 0:05
Settings
aspect_ratio
16:9
resolution
480p
num_frames
81
frames_per_second
16
Prompt
A sports car is driving very fast along a beach at sunset
Längd: 0:05
Settings
aspect_ratio
16:9
resolution
480p
num_frames
81
frames_per_second
16
Prompt
A sports car is driving very fast along a beach at sunset
Längd: 0:05
Settings
aspect_ratio
16:9
resolution
480p
num_frames
81
frames_per_second
16
Exempelprompts
Exempel från Railwail-katalogen. De genererades inte live på denna sida.
Quick
Längd: 0:05
Cat playing with yarn on wooden floor
03
Om Wan 2.2 Text-to-Video
Kort sagtFrån och med 23 september 2026
Wan 2.2 Text-to-Video är en modell av Alibaba (Wan) i kategorin Videogenerering. På Railwail kostar Wan 2.2 Text-to-Video 0,060 US$ per video. Beroende på inställningarna varierar priset mellan 0,060 US$/video och 0,12 US$/video. Bildförhållanden som stöds: 16:9 och 9:16.
Bakgrund
Om Alibaba (Tongyi Wanxiang Lab)
Grundat 1999 · Hangzhou, China
Alibaba's Tongyi Lab in Hangzhou runs the Qwen LLM family and the Wanxiang generative-media family. After Wan 2.0 (mid-2024) and Wan 2.1 (early 2025), the team released Wan 2.2 in 2025 as the next-generation open-weight video model. Wan 2.2 ships as purpose-tuned variants for Text-to-Video, Image-to-Video and Audio/A2V. Wan 2.2 Text-to-Video is the flagship pure-text-conditioned variant and replaces Wan 2.1 T2V-14B as the principal open-weight text-to-video reference for the Chinese research community. The Wan team consistently rank near the top of open-model VBench leaderboards and ship reproducible training code under a permissive Wan-series licence.
Diffusion Transformer (DiT) with 3D causal VAE; MoE-style scaling
Wan 2.2 Text-to-Video is a Diffusion Transformer operating on a 3D causal Wan-VAE latent. Wan 2.2 introduces architectural refinements over Wan 2.1: improved 3D Rotary Position Embeddings, larger attention windows, and (in the flagship) a Mixture-of-Experts feed-forward design that routes tokens to specialist experts. Text conditioning uses a Qwen-family multilingual encoder with strong Chinese-English capability. The denoiser is trained with Flow Matching on a curated multi-million-clip multilingual video corpus with synthetic dense bilingual captions. Native generation is 5 seconds at 720p / 24 fps (with 1080p extensions). The training recipe and weights are open-source on Hugging Face and GitHub under the Wan-series permissive licence, designed to enable broad commercial and research use.
Parameter
14 billion (flagship); smaller variants available
Funktioner
Open-weight text-to-video flagship at 14B parameters (smaller variants available)
Bilingual Chinese/English prompts via Qwen-based text encoder
MoE-style scaling and improved 3D RoPE in flagship variant
Permissive Wan-series licence for research and commercial use
Top-tier results on VBench among open-weight models
Active community ecosystem (LoRAs, fine-tunes, ComfyUI nodes)
Reproducible training recipe and code
Best for: open-source video pipelines, research, on-prem creative tooling, branded fine-tunes.
Träning & licens
Curated multi-million-clip multilingual video corpus filtered for aesthetics, motion and caption quality, with dense bilingual captions; specifics documented in Wan technical materials.
Licens: Open weights under an Apache-style permissive licence (Wan-series release).
Säkerhetstestning: Data-level filtering and recommended NSFW classifier for deployment; Alibaba-hosted endpoints follow Chinese CAC algorithmic-content rules.
Kända begränsningar
Native duration 5 seconds
No native audio
High VRAM requirements for the 14B flagship
Closed leaders (Veo 3, Sora 2, Kling v3) still ahead on absolute fidelity
Resolution capped at 720p natively (1080p only in extended modes)
curl https://railwail.com/api/v1/videos/generations \
-H "Authorization: Bearer $RAILWAIL_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "wan-t2v",
"prompt": "A slow drone shot over a misty pine forest at sunrise"
}'
# Response: {"job_id": "...", "status": "queued", ...}
# Poll until status is completed, failed or cancelled:
curl https://railwail.com/api/v1/jobs/JOB_ID \
-H "Authorization: Bearer $RAILWAIL_API_KEY"
import os
import time
import requests
API = "https://railwail.com/api/v1"
headers = {"Authorization": f"Bearer {os.environ['RAILWAIL_API_KEY']}"}
job = requests.post(
f"{API}/videos/generations",
headers=headers,
json={
"model": "wan-t2v",
"prompt": "A slow drone shot over a misty pine forest at sunrise",
},
).json()
while True:
status = requests.get(f"{API}/jobs/{job['job_id']}", headers=headers).json()
if status["status"] in ("completed", "failed", "cancelled"):
break
time.sleep(5)
print(status["status"], status.get("output_url"))
const API = "https://railwail.com/api/v1";
const headers = {
Authorization: `Bearer ${process.env.RAILWAIL_API_KEY}`,
"Content-Type": "application/json",
};
const job = await fetch(`${API}/videos/generations`, {
method: "POST",
headers,
body: JSON.stringify({
model: "wan-t2v",
prompt: "A slow drone shot over a misty pine forest at sunrise"
}),
}).then((r) => r.json());
let status;
do {
await new Promise((r) => setTimeout(r, 5000));
status = await fetch(`${API}/jobs/${job.job_id}`, { headers }).then((r) => r.json());
} while (!["completed", "failed", "cancelled"].includes(status.status));
console.log(status.status, status.output_url);
Wan 2.2 Text-to-Video är en modell av Alibaba (Wan) i kategorin Videogenerering. På Railwail kan du anropa den med en API-nyckel via Railwail API.
Vad kostar Wan 2.2 Text-to-Video på Railwail?
På Railwail kostar Wan 2.2 Text-to-Video 0,060 US$ per video. Beroende på inställningarna varierar priset mellan 0,060 US$/video och 0,12 US$/video. Priset är känt innan körningen startar. Användningen betalas från förbetald kredit; 1 kredit motsvarar 0,01 US$.
Vilka inställningar stöder Wan 2.2 Text-to-Video?
Enligt sitt inmatningsschema känner Wan 2.2 Text-to-Video till dessa parametrar: prompt och aspect_ratio (16:9 eller 9:16).
Hur snabb är Wan 2.2 Text-to-Video?
Det finns ännu inte tillräckligt många uppmätta körningar av Wan 2.2 Text-to-Video på Railwail för att ange en körningstid. Det beror på inmatningen, inställningarna och belastningen hos leverantören.
Är Wan 2.2 Text-to-Video bättre än Google Veo 3.1?
Det beror på uppgiften. Wan 2.2 Text-to-Video (Alibaba (Wan)) och Google Veo 3.1 (Google DeepMind) är båda modeller i kategorin Videogenerering. Jämförelsesidan visar deras priser och specifikationer sida vid sida.
Hur använder jag Wan 2.2 Text-to-Video via API:et?
Skapa en Railwail API-nyckel och skicka din begäran med modell-ID:t wan-t2v. Kodexempel för curl, Python och JavaScript finns i API-avsnittet på denna sida.
MiniMax Hailuo 02 on Replicate. Text-to-video and image-to-video producing 6s or 10s clips at 768p standard or 1080p pro. Known for accurate real-world physics and stable motion.
