PopNowAPI 文档
正文

Wan 2.2 Image LoRA API 调用参考

Wan 2.2 出静帧,三个槽位最多挂九个 LoRA

用一个 PopNow API 密钥,就能在自己的代码里调用 Wan 2.2 Image LoRA。下面列出要填的调用名、这个型号接受的每个输入字段、每次请求花多少积分,以及一段可以直接粘进终端运行的请求。

参数说明直接取自型号的输入 schema,暂时只有英文。

一览

出品方
Alibaba
产出
图片
起价
4.5 积分 每张图 ($0.045)

1 积分 = 0.01 美元。任务受理时先冻结可能的最高费用,完成后按实际用量结算、向上取整到整积分,多冻的退回;失败的任务不扣积分。想在运行前知道确切数字,先调 POST /api/v1/jobs/quote。

生成图片

alibaba/wan-2.2-image-lora/text-to-image

价格

选项积分 (每张图)美元
默认4.5$0.045

参数

字段类型默认值取值范围作用
prompt必填string—最多 5000 个字符Describe the subject, the place, the light and the lens. Put a LoRA trigger word first.
aspect_ratio可选string1:11:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9, 9:21Output aspect ratio.
loras可选array<object>[]最多 3 项Up to three LoRA weight files applied to both noise experts of Wan 2.2 A14B.
high_noise_loras可选array<object>[]最多 3 项Up to three LoRA weight files applied to the high-noise expert only (layout and composition).
low_noise_loras可选array<object>[]最多 3 项Up to three LoRA weight files applied to the low-noise expert only (detail and texture).
output_format可选stringjpegjpeg, png, webpContainer of the returned image.
seed可选integer—0 到 2147483647Random seed for controlled comparisons, not a frame-identical guarantee.

请求示例

这段请求原样就能运行,没写的字段都用默认值。运行前先把密钥放进环境变量 POPNOW_API_KEY。

POST /api/v1/jobs/createTask
curl -X POST "https://api.popnow.ai/api/v1/jobs/createTask" \
  -H "Authorization: Bearer $POPNOW_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
  "model": "alibaba/wan-2.2-image-lora/text-to-image",
  "input": {
    "prompt": "A cozy reading nook beside a rain-streaked window, warm lamp light, a sleeping orange cat on a knitted blanket, soft film grain"
  }
}'

响应里会立刻带回 taskId。之后用 GET /api/v1/jobs/recordInfo 取结果,或者在请求里加上 callBackUrl 等通知。

GET /api/v1/jobs/recordInfo
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=TASK_ID_FROM_CREATE_TASK" \
  -H "Authorization: Bearer $POPNOW_API_KEY"

接下来

本页内容