curl --request POST \
--url https://api.apimart.ai/v1/videos/generations \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
"model": "pixverse-v6-max",
"prompt": "A blue glass marble rolls across a clean white table in morning light",
"duration": 5,
"resolution": "720p",
"aspect_ratio": "16:9",
"audio": true
}'
import requests
response = requests.post(
"https://api.apimart.ai/v1/videos/generations",
headers={"Authorization": "Bearer <token>"},
json={
"model": "pixverse-v6-max",
"prompt": "A blue glass marble rolls across a clean white table in morning light",
"duration": 5,
"resolution": "720p",
"aspect_ratio": "16:9",
"audio": True
}
)
response.raise_for_status()
print(response.json())
const response = await fetch("https://api.apimart.ai/v1/videos/generations", {
method: "POST",
headers: {
Authorization: "Bearer <token>",
"Content-Type": "application/json"
},
body: JSON.stringify({
model: "pixverse-v6-max",
prompt: "A blue glass marble rolls across a clean white table in morning light",
duration: 5,
resolution: "720p",
aspect_ratio: "16:9",
audio: true
})
});
if (!response.ok) throw new Error(await response.text());
console.log(await response.json());
PixVerse V6 Max
PixVerse V6 Max 视频生成
支持文生视频和单图生视频,输出 360p / 540p / 720p / 1080p 视频,时长 1–15 秒,可选原生音轨。
POST
/
v1
/
videos
/
generations
curl --request POST \
--url https://api.apimart.ai/v1/videos/generations \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
"model": "pixverse-v6-max",
"prompt": "A blue glass marble rolls across a clean white table in morning light",
"duration": 5,
"resolution": "720p",
"aspect_ratio": "16:9",
"audio": true
}'
import requests
response = requests.post(
"https://api.apimart.ai/v1/videos/generations",
headers={"Authorization": "Bearer <token>"},
json={
"model": "pixverse-v6-max",
"prompt": "A blue glass marble rolls across a clean white table in morning light",
"duration": 5,
"resolution": "720p",
"aspect_ratio": "16:9",
"audio": True
}
)
response.raise_for_status()
print(response.json())
const response = await fetch("https://api.apimart.ai/v1/videos/generations", {
method: "POST",
headers: {
Authorization: "Bearer <token>",
"Content-Type": "application/json"
},
body: JSON.stringify({
model: "pixverse-v6-max",
prompt: "A blue glass marble rolls across a clean white table in morning light",
duration: 5,
resolution: "720p",
aspect_ratio: "16:9",
audio: true
})
});
if (!response.ok) throw new Error(await response.text());
console.log(await response.json());
本接口采用异步处理。提交后使用返回的
task_id,通过 GET /v1/videos/generations/{task_id} 查询任务状态和结果。curl --request POST \
--url https://api.apimart.ai/v1/videos/generations \
--header 'Authorization: Bearer <token>' \
--header 'Content-Type: application/json' \
--data '{
"model": "pixverse-v6-max",
"prompt": "A blue glass marble rolls across a clean white table in morning light",
"duration": 5,
"resolution": "720p",
"aspect_ratio": "16:9",
"audio": true
}'
import requests
response = requests.post(
"https://api.apimart.ai/v1/videos/generations",
headers={"Authorization": "Bearer <token>"},
json={
"model": "pixverse-v6-max",
"prompt": "A blue glass marble rolls across a clean white table in morning light",
"duration": 5,
"resolution": "720p",
"aspect_ratio": "16:9",
"audio": True
}
)
response.raise_for_status()
print(response.json())
const response = await fetch("https://api.apimart.ai/v1/videos/generations", {
method: "POST",
headers: {
Authorization: "Bearer <token>",
"Content-Type": "application/json"
},
body: JSON.stringify({
model: "pixverse-v6-max",
prompt: "A blue glass marble rolls across a clean white table in morning light",
duration: 5,
resolution: "720p",
aspect_ratio: "16:9",
audio: true
})
});
if (!response.ok) throw new Error(await response.text());
console.log(await response.json());
模型能力
PixVerse V6 Max 是 PixVerse V6 的高画质版本,仅支持文生视频和单图生视频,使用同一个模型名pixverse-v6-max。
| 模式 | 输入方式 | 宽高比 |
|---|---|---|
| 文生视频 | 不传 image_urls,必须提供 prompt | 使用 aspect_ratio,默认 16:9 |
| 图生视频 | image_urls 传入 1 张图片,prompt 可选 | 跟随输入图片,aspect_ratio 不生效 |
请求头
string
必填
Bearer 认证,格式为
Bearer <token>,其中 <token> 为你的 APIMart API Key。请求参数
string
必填
固定为
pixverse-v6-max。string
描述要生成的内容。文生视频必填,最长 5000 字符;图生视频可省略,最长 2048 字符。
string[]
输入图片 URL 列表。图生视频只能传 1 张图片;传入 2 张及以上会同步返回 HTTP 400。不传此字段为文生视频。图片要求:公网 HTTP(S) 可访问,支持 JPEG、PNG、WebP,文件小于 20 MB,每条边不超过 10000 像素。
integer
默认值:"5"
输出时长,单位为秒,支持
1–15,默认 5。string
默认值:"540p"
输出分辨率,支持
360p、540p、720p、1080p,默认 540p。输出采用上游原生尺寸,以实际返回为准。实测代表规格包括 640×360、1108×832(宽 × 高,单位为像素)。也接受 quality 字段;同时传入时,resolution 优先。string
分辨率的兼容字段,可选值与
resolution 相同。仅在未传 resolution 时使用;两者均不传时使用 540p。string
默认值:"16:9"
仅对文生视频生效,支持
16:9、9:16、4:3、3:4、1:1、2:3、3:2、21:9,默认 16:9。图生视频始终跟随输入图片的宽高比,此字段不生效。boolean
默认值:"false"
传
true 生成原生音轨;默认无声。有声生成的每秒单价更高。只识别请求体顶层的 audio。metadata.generate_audio_switch 不会开启音轨,也不会触发有声计费。integer
随机种子,取值范围为
0–2147483647。图生视频示例
{
"model": "pixverse-v6-max",
"prompt": "Make the subject walk forward slowly",
"image_urls": ["https://example.com/start.png"],
"duration": 5,
"resolution": "1080p"
}
查询任务
将以下请求中的任务 ID 替换为提交时返回的task_id:
curl --request GET \
--url 'https://api.apimart.ai/v1/videos/generations/<task_id>' \
--header 'Authorization: Bearer <token>'
计费
费用按输出秒数乘以对应分辨率及音频档位的每秒单价计算。有声与无声使用不同单价,有声单价更高。 未指定resolution 或 quality 时,输出和计费均使用 540p。
当前单价以模型价格查询接口为准:
| 音频档位 | 价格字段 |
|---|---|
| 无声 | resolution_paid_prices 中对应分辨率的价格 |
| 有声 | billing_tier_paid_prices 中对应的 <resolution>-audio 档位 |
不支持的功能及参数错误
以下请求会同步返回 HTTP 400,不创建任务、不扣费:| 请求 | 错误信息 |
|---|---|
传入 extend_from_task_id | pixverse-v6-max does not support video extend …; use pixverse-v6 instead |
传入 img_references | pixverse-v6-max does not support multi-image reference … |
传入 first_frame_image 或 last_frame_image | pixverse-v6-max does not support first/last frame transition … |
image_urls 传入 2 张及以上 | pixverse-v6-max image-to-video takes exactly 1 image in image_urls (got N) |
resolution 不在上述 4 档内 | invalid resolution … |
duration 超过 15 秒 | invalid duration … |
文生视频的 aspect_ratio 不在上述 8 种内 | invalid aspect_ratio … |