Wan 2.2 API
Alibaba 的 Wan 2.2 是開放權重的影片工具組,已部署於 WaveSpeedAI,提供 35 種以上的原廠版本:Animate(120 秒角色動畫)、Video Edit、Speech-to-Video(10 分鐘音訊驅動)、Fun-Control(Apache 2.0 授權),以及多種模型大小(5B、A14B)與解析度(480p / 720p)的圖片轉影片與文字轉影片。
僅限 WaveSpeedAI 託管的版本。Animate 可生成最長 120 秒的 720p 影片;Speech-to-Video 可生成最長 10 分鐘的 480p 影片;Fun-Control 使用預設的 Control Codes,以 Apache 2.0 授權可商用。LoRA 訓練端點可在數分鐘內完成微調。
概覽
關於 Wan 2.2 API
Wan 2.2 的功能、它在 Alibaba 模型陣容中的定位,以及團隊選用它的原因。
Wan 2.2 是來自 Alibaba 的影片生成模型,可透過 WaveSpeedAI REST API 使用。Alibaba 的 Wan 2.2 是開放權重的影片工具組,已部署於 WaveSpeedAI,提供 35 種以上的原廠版本:Animate(120 秒角色動畫)、Video Edit、Speech-to-Video(10 分鐘音訊驅動)、Fun-Control(Apache 2.0 授權),以及多種模型大小(5B、A14B)與解析度(480p / 720p)的圖片轉影片與文字轉影片。
僅限 WaveSpeedAI 託管的版本。Animate 可生成最長 120 秒的 720p 影片;Speech-to-Video 可生成最長 10 分鐘的 480p 影片;Fun-Control 使用預設的 Control Codes,以 Apache 2.0 授權可商用。LoRA 訓練端點可在數分鐘內完成微調。
WaveSpeedAI 上的 Wan 2.2 系列提供 32 個 REST 端點,涵蓋 Image-To-Video, Motion-Control, Video-To-Video, Image-To-Image, Digital-Human, Text-To-Image, Training, Text-To-Video 等工作流程。每個變體都有各自的定價、參數選項與範例輸出 — 請挑選符合您輸入模態與生產限制的版本,或使用同一組 API 金鑰呼叫多個變體,組合成多步驟的處理流程。
使用您呼叫其他 1,000+ 個 WaveSpeedAI AI 模型時相同的 API 金鑰、帳單帳戶與速率限制額度來執行 Wan 2.2。無需另外設定供應商、無需各家 SDK、無需處理各家不同的速率限制 — 一次整合,涵蓋從文字轉圖片、文字轉影片,到音訊合成、3D 生成、放大與編輯的所有功能。
端點
所有 Wan 2.2 API 端點
WaveSpeedAI 目前提供 32 個 Wan 2.2 端點 — 請選擇符合您工作流程的變體。
/filters:quality(82)/media/images/20260408111216_2fizlz7x.webp)
Wan 2.2 Image To Video Lora
Wan-2.2/image-to-video-lora enables unlimited image-to-video generation from a single image, producing smooth, cinematic motion with clean detail. Supports custom LoRAs for style and character consistency. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.
/filters:quality(82)/media/images/20260408111152_zehbgma1.webp)
Wan 2.2 Image To Video
Wan 2.2 Image-to-Video turns a single image into smooth, cinematic motion with clean detail—ideal for storyboards, mood shots, and product demos. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.
/filters:quality(82)/media/images/20260408111211_p8f6ffxe.webp)
Wan 2.2 Animate
Wan2.2-Animate unified character animation & replacement model replicating movement and expression; generates 720p videos up to 120s. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/20260408111241_3bzr5rd1.webp)
Wan 2.2 Video Edit
Wan 2.2 Video Edit lets you modify videos via text prompts (e.g., change clothing or characters). Powered by Wan 2.2, it supports 480p ($0.20/5s) and 720p ($0.40/5s), up to 120s. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/20260408111257_4rmbjsgj.webp)
Wan 2.2 Image To Image
WAN 2.2 (14B) is an image-to-image model for high-resolution photorealistic image editing with exceptional precision and fidelity. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/20260408111154_gvj4f5sj.webp)
Wan 2.2 Speech To Video
Wan-2.2-S2V turns images and speech into high-fidelity videos with realistic face and body motion; supports up to 10-minute clips in 480p, from $0.15/5s. Ready-to-use REST API, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/20260408111206_p4ked9pu.webp)
Wan 2.2 Text To Image Lora
WAN 2.2 generates super-detailed images from text prompts and supports custom LoRAs for fine-grained style and subject control. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/20260408111250_80jkk4zs.webp)
Wan 2.2 Fun Control
Wan2.2-Fun-Control uses Control Codes and multi-modal inputs to generate preset-controlled videos up to 120s at 720p; released under Apache 2.0 for commercial use. Ready-to-use REST API, no coldstarts, affordable.
/filters:quality(82)/media/images/20260408112009_zkynaf2n.webp)
Wan 2.2 Image Lora Trainer
Train custom Wan 2.2 character/style LoRA models 10x faster. Style training, character training, object training. From concept to model in minutes, not hours. Upload a ZIP file containing images to start!
/filters:quality(82)/media/images/20260408111954_4jny6q8q.webp)
Wan 2.2 I2v Lora Trainer
Train custom Wan 2.2 I2V LoRA models 10x faster. Action training, motion training, video efect training. From concept to model in minutes, not hours. Upload a ZIP file containing videos to start!
/filters:quality(82)/media/images/20260408111226_b3370qq2.webp)
Wan 2.2 Text To Image Realism
WAN 2.2 delivers ultra-realistic text-to-image generation, converting prompts into photoreal images with high fidelity and detail. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/20260408111246_kbtz9m3g.webp)
Wan 2.2 I2v 5b 720p Lora
Wan 2.2 i2v-5B-720p is a 5B image-to-video model producing 720p videos with LoRA support for style customization. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/20260408111210_znuyn6r8.webp)
Wan 2.2 T2v 5b 720p Lora
Wan 2.2 T2V 5B is a 5B text-to-video model with LoRA support that generates 720p videos from text prompts for easy personalization. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/20260408111236_0was1j4o.webp)
Wan 2.2 I2v 480p Lora Ultra Fast
Wan 2.2 i2v delivers ultra-fast Image-to-Video at 480p with support for custom LoRAs for tailored styles. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/20260408111252_sejz6k48.webp)
Wan 2.2 I2v 480p Ultra Fast
Wan 2.2 A14B Image-to-Video (i2v-480p) produces ultra-fast 480p videos from single images, enabling unlimited AI video generation with high throughput. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/20260408111149_z1lz7r9s.webp)
Wan 2.2 I2v 720p Ultra Fast
Generate unlimited ultra-fast 720p AI videos from images with Wan 2.2 A14B image-to-video model. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/20260408111259_8bca6477.webp)
Wan 2.2 T2v 480p Lora Ultra Fast
Ultra-fast Wan 2.2 text-to-video model producing 480p videos with custom LoRA support—generate unlimited AI videos with personalized styles. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/20260408111238_h7qxvir0.webp)
Wan 2.2 I2v 720p Lora Ultra Fast
Wan 2.2 i2v 720P is an ultra-fast Image-to-Video model that generates unlimited AI videos and supports custom LoRAs for personalized outputs. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/20260408111248_iyye47z8.webp)
Wan 2.2 T2v 480p Ultra Fast
Wan 2.2 t2v 480p Ultra-Fast generates unlimited AI videos from text prompts at 480p with ultra-fast inference. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/20260408111201_lv1td92d.webp)
Wan 2.2 T2v 5b 720p
Wan 2.2 T2V 5B is a 720P text-to-video model that generates unlimited AI videos from simple text prompts, producing consistent high-quality 720p outputs. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/20260408111221_xo8hpiqi.webp)
Wan 2.2 I2v 5b 720p
Wan 2.2 I2V 5B converts images into high-quality 720P videos using a 5B image-to-video model for AI video generation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/20260408111214_rct2hj0c.webp)
Wan 2.2 I2v 480p
Wan 2.2 A14B converts images into 480p videos, enabling unlimited AI video generation from single images. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/20260408111234_cplw518o.webp)
Wan 2.2 I2v 480p Lora
WAN 2.2 A14B Image-to-Video model generates unlimited 480p videos from images and supports custom LoRAs for personalized styles and fine-tuning. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/20260408111232_8tgp9v7m.webp)
Wan 2.2 I2v 720p Lora
WAN 2.2 Image-to-Video (i2v) 720p converts images into 720p videos and supports custom LoRAs for style personalization. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/20260408111239_qlur3dn5.webp)
Wan 2.2 I2v 720p
WAN 2.2 A14B i2v-720p converts images into smooth 720p videos, enabling unlimited AI video generation with the Wan 2.2 image-to-video model. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/20260408111156_b3olejjy.webp)
Wan 2.2 T2v 480p
Wan 2.2 t2v-480p generates unlimited AI videos from text prompts at 480p resolution, ideal for rapid prototyping and content creation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/20260408111208_sw0j3xam.webp)
Wan 2.2 T2v 480p Lora
WAN 2.2 T2V 480p with LoRA generates text-to-video at 480p and supports custom LoRAs for personalized styles. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/20260408111218_00vzkvbl.webp)
Wan 2.2 T2v 720p
Wan 2.2 t2v-720p converts text prompts into native 720P videos, producing high-quality 720P clips from simple prompts. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/20260408111230_mtxgxh1x.webp)
Wan 2.2 T2v 720p Lora
Wan 2.2 T2V 720p with custom LoRA support turns text prompts into 720p AI videos and enables unlimited video generation. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/20260408111158_csf9651o.webp)
Wan 2.2 T2v 720p Lora Ultra Fast
Ultra-fast Wan 2.2 Text-to-Video generates unlimited 720p AI videos with custom LoRAs for personalized styles. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/20260408111244_aqp0x6b0.webp)
Wan 2.2 T2v 720p Ultra Fast
WAN 2.2 T2V 720p Ultra-Fast generates high-quality 720p videos from text prompts with unlimited output and ultra-fast throughput. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
/filters:quality(82)/media/images/1786269272686834557_4oOX6gqz.webp)
Wan 2.2 Animate 2
Wan 2.2 Animate 2 is the next-generation Wan character animation model: an end-to-end DiT that makes the character in a reference image perform the motion of a driving video, with no pose extraction, prompt-controlled background, and strong identity preservation; generates 480p/720p videos up to 120s. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
範例
看看 Wan 2.2 的實際效果
由 Wan 2.2 API 生成的真實輸出。將滑鼠移到任一影片上即可預覽,點擊可開啟完整尺寸檢視器。
使用方式
如何使用 Wan 2.2 API
從註冊到完成生成,只要四個步驟。完整的 Python、Node.js 與 cURL 範例請見下方的 API 區段。
- 01
取得 API 金鑰
註冊 WaveSpeedAI 帳號,並從控制台複製您的 API 金鑰。新帳號會獲贈免費入門點數 — 足以在開始計費前執行數十次 Playground。
- 02
提交 prediction
將您的輸入以 JSON 格式 POST 到 https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.2/image-to-video。端點會立即回傳 prediction id — 生成是非同步進行的,因此推論期間您不需要保持連線。
- 03
輪詢完成狀態
GET https://api.wavespeed.ai/api/v3/predictions/{request_id}/result。狀態為 completed 時回傳輸出;狀態為 failed、cancelled、timeout 或 deleted 時停止並回報錯誤;其他狀態則持續輪詢。
- 04
讀取輸出網址
當狀態為 "completed" 時,從 data.outputs[0] 讀取網址。該網址指向 WaveSpeedAI CDN 上您生成的媒體 — 依您呼叫的 Wan 2.2 變體,可能是圖片、影片、音訊或 3D 檔案。
應用情境
您可以用 Wan 2.2 打造什麼
開發者與創作者使用 Wan 2.2 API 的常見工作流程。
Wan 2.2 Animate:最長 120 秒的角色動畫
wavespeed-ai/wan-2.2/animate 是「統一的角色動畫與替換模型,可複製動作與表情,生成最長 120 秒的 720p 影片」,此為目錄說明。明顯長於多數由姿態驅動的動畫工具。
最長 10 分鐘的 Speech-to-Video
wavespeed-ai/wan-2.2/speech-to-video「可將圖片與語音轉為高保真影片,具寫實的臉部與肢體動作,支援最長 10 分鐘的 480p 影片」。適合長篇說話內容。
以提示詞驅動修改的 Video Edit
wavespeed-ai/wan-2.2/video-edit 可透過文字提示詞修改影片(目錄範例:更換服裝或角色)。支援 480p 與 720p,最長 120 秒。
Apache 2.0 授權的 Fun-Control
wavespeed-ai/wan-2.2/fun-control 使用「Control Codes 與多模態輸入,生成最長 120 秒、720p 的預設控制影片;以 Apache 2.0 發布,可供商用」。Apache 2.0 授權對商業管線而言是真正的差異化優勢。
LoRA 訓練(快 10 倍)
wavespeed-ai/wan-2.2-image-lora-trainer 用於圖片 LoRA,wavespeed-ai/wan-2.2-i2v-lora-trainer 用於 I2V LoRA。目錄說明:「訓練速度快 10 倍」。支援風格、角色、物件、動作、行為與影片特效的訓練。上傳 ZIP 檔即可開始。
多種大小的圖片轉影片(5B / A14B)
選擇模型大小:5B(較小)重速度與成本,A14B 則提供完整畫質。標準 i2v 用於 480p;另有支援 LoRA 的版本,以及超快速版本。
技巧
Wan 2.2 提示詞技巧
讓 Wan 2.2 產出更好結果的實用建議 — 整理自在實際生產流程中,影片模型通用的有效做法。
- 01
依任務選擇版本
Wan 2.2 提供多個專用端點,而非單一的通用模型。Animate 用於姿態驅動的動態,video-edit 用於局部修改,speech-to-video 用於說話內容,image-to-video 用於一般生成。請將端點與任務搭配,效果明顯優於要求通用模型包辦一切。
- 02
訓練 LoRA 以達成正式製作規模的一致性
Wan 2.2 的 LoRA 訓練端點是 API 的核心功能,而非附屬工具。對於需要在數百次生成中維持固定身分的製作(品牌吉祥物、固定角色、招牌風格),只需訓練一次 LoRA,之後每次生成都呼叫 LoRA 推論端點。
- 03
開放權重讓微調成為可能
閉源權重的競爭對手會將您鎖定在供應商的模型行為中。Wan 2.2 底層是開放權重,因此當基礎模型無法解決某項限制時,仍可選擇微調,多數其他商用影片 API 並不提供這條路徑。
- 04
將 Animate 與 Kling Motion Control 搭配使用
兩者都提供姿態驅動的動畫,但各有取捨。Wan 2.2 Animate 支援 LoRA 且為開放權重;Kling Motion Control 的身分保留更強。請依微調更重要,或身分品質更重要來選擇。
定價
Wan 2.2 API 定價
依輸出計費。最終費用會依您在各變體 Playground 中設定的參數(解析度、時長、輸出數量、參考素材)而調整。
API
呼叫 Wan 2.2 API
請到 wavespeed.ai/accesskey 註冊取得 API 金鑰,然後透過 REST 提交 prediction。Playground 會為任何輸入組合產生可直接貼上的範例。
POSThttps://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.2/image-to-video
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.2/image-to-video" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
"resolution": "480p",
"duration": 5
}')
TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
printf 'Submission response did not contain a prediction id
' >&2
exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
-H "Authorization: Bearer $WAVESPEED_API_KEY")
RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
case "$STATUS" in
completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
failed|cancelled|timeout|deleted) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
*) sleep 2 ;;
esac
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.2/image-to-video";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');
async function requestJson(url, options = {}) {
const response = await fetch(url, options);
if (!response.ok) throw new Error(await response.text());
return response.json();
}
// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
method: "POST",
headers: {
"Authorization": `Bearer ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
"resolution": "480p",
"duration": 5
}),
});
const task = body.data ?? body;
const resultUrl = `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;
// 2. Poll until the prediction finishes.
while (true) {
const resultBody = await requestJson(resultUrl, {
headers: { "Authorization": `Bearer ${apiKey}` },
});
const result = resultBody.data ?? resultBody;
if (result.status === "completed") {
console.log(result.outputs);
break;
}
if (["failed", "cancelled", "timeout", "deleted"].includes(result.status)) throw new Error(JSON.stringify(result));
await new Promise(resolve => setTimeout(resolve, 2000));
}import json
import os
import time
from urllib.request import Request, urlopen
api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"image": "https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg",
"resolution": "480p",
"duration": 5
}
def request_json(url, data=None):
request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
with urlopen(request) as response:
return json.load(response)
# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.2/image-to-video", json.dumps(payload).encode())
task = body.get("data", body)
result_url = f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"
# 2. Poll until the prediction finishes.
while True:
result_body = request_json(result_url)
result = result_body.get("data", result_body)
status = result.get("status")
if status == "completed":
print(result.get("outputs", []))
break
if status in {"failed", "cancelled", "timeout", "deleted"}:
raise RuntimeError(result)
time.sleep(2)比較
Wan 2.2 與其他選擇比較
在 WaveSpeedAI 上,何時該選擇 Wan 2.2 而非類似的模型。
Wan 2.2 vs Wan 2.7
Wan 2.7(alibaba/wan-2.7/*)是 Alibaba 較新的架構,同系列提供參考轉影片、video-edit、image-edit 與文字轉圖片,跨模態工具組更廣。Wan 2.2(WaveSpeedAI 版本)則提供 2.7 所沒有的專用端點:Animate(120 秒)、Speech-to-Video(10 分鐘)、Fun-Control(Apache 2.0)與 LoRA 訓練器。
Wan 2.2 vs Seedance 2.0
Seedance 2.0 提供好萊塢等級的輸出,所有版本皆具原生音訊。Wan 2.2 則在版本數量(35 個以上的端點)與 LoRA 訓練上勝出,當您需要特定的專用功能(Animate、Speech-to-Video、Fun-Control),而非通用影片模型時,這是正確的選擇。
Wan 2.2 vs Kling 3.0 Motion Control
兩者都提供姿態驅動的角色動畫。Wan 2.2 Animate 可生成 120 秒的 720p 影片,並提供 LoRA 微調。Kling Motion Control 受限於參考影片的時長(3 至 30 秒),但以快手的影片資料庫訓練,具有更強的動作先驗。
常見問題
Wan 2.2 API — 常見問題
定價、授權、整合 — 關於在 WaveSpeedAI 上執行 Wan 2.2 的常見問題。
什麼是 Wan 2.2 API?
Wan 2.2 是 Alibaba 的影片生成模型,在 WaveSpeedAI 上以 REST API 提供。Alibaba 的 Wan 2.2 是開放權重的影片工具組,已部署於 WaveSpeedAI,提供 35 種以上的原廠版本:Animate(120 秒角色動畫)、Video Edit、Speech-to-Video(10 分鐘音訊驅動)、Fun-Control(Apache 2.0 授權),以及多種模型大小(5B、A14B)與解析度(480p / 720p)的圖片轉影片與文字轉影片。您可以透過程式呼叫,也可以在上方連結的 Playground 試用。
如何呼叫 Wan 2.2 API?
註冊 WaveSpeedAI 帳號,從 /accesskey 複製您的 API 金鑰,然後將您的輸入以 JSON 格式 POST 到 https://api.wavespeed.ai/api/v3/wavespeed-ai/wan-2.2/image-to-video。端點會回傳 prediction id。請從約每 2 秒輪詢一次結果端點開始,長時間任務可拉長間隔,並在任何終止狀態時停止。上方提供適用於生產環境的 Python / Node.js / cURL 範例。
Wan 2.2 API 的費用是多少?
Wan 2.2 每次執行 $0.02 起。實際費用會依您設定的參數(解析度、時長、輸出數量、參考素材)而調整。Playground 中「生成」按鈕旁的即時費用預覽會顯示您目前輸入的確切價格。
有哪些 Wan 2.2 變體可用?
WaveSpeedAI 提供 32 個已上線的 Wan 2.2 端點:wavespeed-ai/wan-2.2/image-to-video-lora, wavespeed-ai/wan-2.2/image-to-video, wavespeed-ai/wan-2.2/animate, wavespeed-ai/wan-2.2/video-edit, wavespeed-ai/wan-2.2/image-to-image, wavespeed-ai/wan-2.2/speech-to-video, wavespeed-ai/wan-2.2/text-to-image-lora, wavespeed-ai/wan-2.2/fun-control等。每個變體都有各自的 Playground 頁面與定價。
Wan 2.2 的輸出可以商用嗎?
商業使用權依 Alibaba 的模型授權而定。多數 Alibaba 模型允許商用輸出;請參閱各模型 Playground 頁面中的授權摘要,以及 WaveSpeedAI 的服務條款了解平台層級的條件。
為什麼要在 WaveSpeedAI 上使用 Wan 2.2,而不是直接使用?
一組 API 金鑰、一個帳單帳戶,即可使用 Wan 2.2 以及來自其他供應商的 1,000+ 個 AI 模型。無需設定各家 SDK、無需處理各自獨立的速率限制、無需為每個供應商重寫整合程式碼。價格通常與 Alibaba 的直接 API 相當或更低。
提供者
關於 Alibaba
Wan 2.2 背後的團隊,以及 Alibaba 在 WaveSpeedAI 上的完整模型陣容。
Alibaba 通義實驗室打造了 Wan 影片模型系列與 Qwen 大型語言模型系列。Wan 的特色在於以開放權重釋出、版本涵蓋廣泛(文字轉影片、圖片轉影片、參考轉影片、video-edit、video-extend、image-edit、文字轉圖片),並在多語言提示詞下持續展現出色的動態穩定性與提示詞遵循度。
在 WaveSpeedAI 上開始使用 Wan 2.2 打造應用
註冊即贈免費入門點數。一組 API 金鑰,涵蓋來自 Alibaba 與所有其他供應商的 1,000+ 個 AI 模型。