Wan 2.1 Image LoRA API 调用参考
照片级的 Wan 2.1 静帧和换风格，可挂你的 LoRA
用一个 PopNow API 密钥，就能在自己的代码里调用 Wan 2.1 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-2.1-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 setting and the light. If a LoRA has trigger words, put them first. |
aspect_ratio可选 | string | 1:1 | 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9, 9:21 | Output aspect ratio. |
resolution可选 | string | 1k | 1k, 1.5k | Output size: 1k is about one megapixel, 1.5k puts 1536 pixels on the long edge. |
loras可选 | array<object> | [] | 最多 3 项 | Up to three LoRA weight files trained for Wan 2.1 14B, each with its own strength. |
output_format可选 | string | jpeg | jpeg, png, webp | Container of the returned image. |
seed可选 | integer | — | 0 到 2147483647 | Random 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。
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-2.1-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。
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=TASK_ID_FROM_CREATE_TASK" \
-H "Authorization: Bearer $POPNOW_API_KEY"编辑图片
alibaba/wan-2.1-image-lora/edit
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 image you want back, not just the change. |
image_url必填 | string (uri) | — | — | Source image. The result keeps its aspect ratio. |
resolution可选 | string | 1k | 1k, 1.5k | Output width: 1k is 1024 pixels, 1.5k is 1536. The height follows the source's shape. |
strength可选 | number | 0.6 | 0 到 1 | How far to move away from the source, from 0 to 1. |
loras可选 | array<object> | [] | 最多 3 项 | Up to three LoRA weight files trained for Wan 2.1 14B, each with its own strength. |
output_format可选 | string | jpeg | jpeg, png, webp | Container of the returned image. |
seed可选 | integer | — | 0 到 2147483647 | Random 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。
示例里的 image_url 用的是 PopNow 的示例素材，换成你自己的公开 HTTPS 链接、上传文件或已保存的素材即可。
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-2.1-image-lora/edit",
"input": {
"prompt": "Change the orange jacket to deep forest green and add soft golden-hour light; keep the face, pose and background unchanged",
"image_url": "https://media.popnow.ai/influencer/examples/marco.webp"
}
}'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。
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=TASK_ID_FROM_CREATE_TASK" \
-H "Authorization: Bearer $POPNOW_API_KEY"