Wan 3.0 API 调用参考
最长 30 秒视频，音画同步
用一个 PopNow API 密钥，就能在自己的代码里调用 Wan 3.0。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
- 视频
- 起价
- 6.75 积分 每秒成片 ($0.0675)
- 一般耗时
- 约 147 秒
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。
生成视频
alibaba/wan-3.0/text-to-video
价格
| 选项 | 积分 (每秒成片) | 美元 |
|---|---|---|
480p | 6.75 | $0.0675 |
720p | 13.5 | $0.135 |
1080p | 27 | $0.27 |
参数
| 字段 | 类型 | 默认值 | 取值范围 | 作用 |
|---|---|---|---|---|
prompt必填 | string | — | — | Describe the subject, action, camera, light, pacing, and boundaries for the shot. |
aspect_ratio可选 | string | 16:9 | 16:9, 9:16, 1:1, 4:3, 3:4, adaptive | Output aspect ratio; adaptive follows the input media and the intent. |
enable_thinking可选 | boolean | false | — | Let the model reason about the brief and the reference material before generating. Helps with complex references; slower. Switches on by itself when a reference file or link is given. |
resolution可选 | string | 720p | 480p, 720p, 1080p | Output resolution. |
duration_seconds可选 | integer | 5 | -1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, … (+16) | Requested output length in seconds. Pass -1 for smart duration: the model picks the length from the prompt and any input media instead of a fixed number. |
generate_audio可选 | boolean | true | — | Request generated audio with the video. |
enable_prompt_expansion可选 | boolean | false | — | Allow the service to expand the submitted creative brief before generation. |
seed可选 | integer | — | 0 到 2147483647 | Random seed. Keep it fixed only for controlled comparisons, not as 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-3.0/text-to-video",
"input": {
"prompt": "A paper boat drifts down a rain-soaked street at dusk, neon signs reflecting in the water, slow tracking shot at ground level",
"duration_seconds": 5,
"resolution": "720p"
}
}'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"图生视频
alibaba/wan-3.0/image-to-video
价格
| 选项 | 积分 (每秒成片) | 美元 |
|---|---|---|
480p | 6.75 | $0.0675 |
720p | 13.5 | $0.135 |
1080p | 27 | $0.27 |
参数
| 字段 | 类型 | 默认值 | 取值范围 | 作用 |
|---|---|---|---|---|
image_url必填 | string | — | — | Opening-frame image. |
prompt可选 | string | — | — | Describe the subject, action, camera, light, pacing, and boundaries for the shot. |
last_image_url可选 | string | — | — | Optional last frame: the clip ends exactly on this image. Requires image_url. |
aspect_ratio可选 | string | — | 16:9, 9:16, 1:1, 4:3, 3:4, adaptive | Output aspect ratio. Omit it to let the task adapt to the opening image; adaptive follows the input media and the intent. |
enable_thinking可选 | boolean | false | — | Let the model reason about the brief and the reference material before generating. Helps with complex references; slower. Switches on by itself when a reference file or link is given. |
resolution可选 | string | 720p | 480p, 720p, 1080p | Output resolution. |
duration_seconds可选 | integer | 5 | -1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, … (+16) | Requested output length in seconds. Pass -1 for smart duration: the model picks the length from the prompt and any input media instead of a fixed number. |
generate_audio可选 | boolean | true | — | Request generated audio with the video. |
enable_prompt_expansion可选 | boolean | false | — | Allow the service to expand the submitted creative brief before generation. |
seed可选 | integer | — | 0 到 2147483647 | Random seed. Keep it fixed only for controlled comparisons, not as 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-3.0/image-to-video",
"input": {
"prompt": "He lands softly on the rooftop, laughs and turns toward the camera while the balloons sway in the evening breeze; slow push-in",
"image_url": "https://media.popnow.ai/influencer/examples/marco.webp",
"duration_seconds": 5,
"resolution": "720p"
}
}'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"参考生视频
alibaba/wan-3.0/reference-to-video
价格
| 选项 | 积分 (每秒成片) | 美元 |
|---|---|---|
480p | 6.75 | $0.0675 |
720p | 13.5 | $0.135 |
1080p | 27 | $0.27 |
参数
| 字段 | 类型 | 默认值 | 取值范围 | 作用 |
|---|---|---|---|---|
prompt可选 | string | — | — | Describe the subject, action, camera, light, pacing, and boundaries for the shot. |
reference_image_urls可选 | array<string> | — | 最多 10 项 | Reference images, up to 10 items. |
reference_video_urls可选 | array<string> | — | 最多 5 项 | Reference videos, up to 5 items and 15 seconds in total. |
reference_audio_urls可选 | array<string> | — | 最多 5 项 | Reference audio, up to 5 items and 15 seconds in total. |
reference_file_url可选 | string (uri) | — | — | One reference document (PDF, DOCX, TXT, MD and similar) that the model reads for characters, wardrobe, setting and action. |
reference_link_url可选 | string (uri) | — | — | One public web page the model reads for reference. It must open without a login. |
aspect_ratio可选 | string | 16:9 | 16:9, 9:16, 1:1, 4:3, 3:4, adaptive | Output aspect ratio; adaptive follows the input media and the intent. |
enable_thinking可选 | boolean | false | — | Let the model reason about the brief and the reference material before generating. Helps with complex references; slower. Switches on by itself when a reference file or link is given. |
resolution可选 | string | 720p | 480p, 720p, 1080p | Output resolution. |
duration_seconds可选 | integer | 5 | -1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, … (+16) | Requested output length in seconds. Pass -1 for smart duration: the model picks the length from the prompt and any input media instead of a fixed number. With reference videos, their total length plus the output length must not exceed 30 seconds, and the reference video seconds are billed together with the output seconds. |
generate_audio可选 | boolean | true | — | Request generated audio with the video. |
enable_prompt_expansion可选 | boolean | — | — | Allow the service to expand the submitted creative brief before generation. |
seed可选 | integer | — | 0 到 2147483647 | Random seed. Keep it fixed only for controlled comparisons, not as 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 reference_image_urls 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-3.0/reference-to-video",
"input": {
"prompt": "The man from the reference image jogs across a sunlit rooftop at golden hour and smiles at the camera; smooth tracking shot",
"reference_image_urls": [
"https://media.popnow.ai/influencer/examples/ava.webp"
],
"duration_seconds": 5,
"resolution": "720p"
}
}'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"视频续写
alibaba/wan-3.0/video-extend
价格
| 选项 | 积分 (每秒成片) | 美元 |
|---|---|---|
480p | 6.75 | $0.0675 |
720p | 13.5 | $0.135 |
1080p | 27 | $0.27 |
参数
| 字段 | 类型 | 默认值 | 取值范围 | 作用 |
|---|---|---|---|---|
video_url必填 | string (uri) | — | — | The clip to continue: MP4, MOV or WebM, up to 60 seconds. Its last frame opens the new segment, and the result is your clip with the new segment joined on. |
prompt可选 | string | — | — | Optional. Describe what happens next: the action that follows, the camera move and the sound. |
last_image_url可选 | string | — | — | Optional target end frame: the new segment finishes on exactly this image. |
enable_thinking可选 | boolean | false | — | Let the model reason about the brief and the reference material before generating. Helps with complex references; slower. Switches on by itself when a reference file or link is given. |
resolution可选 | string | 720p | 480p, 720p, 1080p | Resolution the new segment is generated at. Match your source to avoid a visible step in sharpness at the seam. |
duration_seconds可选 | integer | 5 | -1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, … (+16) | Length of the new segment in seconds. Pass -1 to let the model pick the length. The source clip is added on top and is not billed. |
generate_audio可选 | boolean | true | — | Generate sound for the new segment. The source keeps its own sound either way. |
enable_prompt_expansion可选 | boolean | false | — | Allow the service to expand the submitted creative brief before generation. |
seed可选 | integer | — | 0 到 2147483647 | Random seed. Keep it fixed only for controlled comparisons, not as 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 video_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-3.0/video-extend",
"input": {
"prompt": "The flowers keep opening while the camera slowly pulls back to reveal a sunlit meadow",
"video_url": "https://media.popnow.ai/effects/flower-bloom-1abd6efb.mp4",
"duration_seconds": 5,
"resolution": "720p"
}
}'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"