Skip to main content
Video generation and editing

Text-to-video

The Wan text-to-video models generate videos from text, images, and audio input. wan3.0-video supports up to 30 seconds, adaptive aspect ratio, smart duration, 480P/720P/1080P resolution, audio toggle, reference audio, and reference files and web links.

Quick access: Try it online (Singapore | US (Virginia) | China (Beijing)) | API reference | Prompt guide

Getting started

Input promptOutput video (multi-shot, audio-enabled)
Shot 1 The sequence opens with an extreme long shot. The camera starts at a low angle near the ground and moves forward across the grassland while tilting upward. As the camera rises from ground level to a slightly elevated position, the cheetah enters the frame from the left. This shot establishes a clear spatial relationship by placing the cheetah and the fleeing antelope on the same path. Shot 2 The camera descends to a near-ground level and tracks to the right, parallel to the cheetah. The cheetah is kept consistently left of center, which creates a continuous lateral shift in the background. For a period, the camera movement remains steady to enhance the sense of speed and spatial continuity. Shot 3 While still moving to the right, the camera executes a slight arc along the inside of the cheetah's path. This movement creates a subtle orbiting effect in the frame as the camera continues to follow the subject. Shot 4 The camera gradually slows its lateral movement and becomes relatively stable while simultaneously zooming in. This action narrows the focus to the shrinking distance between the cheetah and the antelope. Shot 5 The camera again moves forward and slightly downward, hugging the ground to close the distance between the two animals. The shot stops at the critical point just as the cheetah's forelimbs are about to reach the antelope's hindquarters, which creates intense pressure and tension. This action is synchronized with a crescendoing symphonic score, a densifying drumbeat, and the sounds of wind and footsteps that drive the rhythm. In the final moment, the music volume drops, leaving only ambient and rhythmic sounds to create a brief pause.
Before making an API call, get an API key and set it as an environment variable. To use an SDK, install the DashScope SDK. All examples use asynchronous calls that submit a video generation task and poll for the result.
  • Python SDK
  • Java SDK
  • curl
Ensure that your DashScope SDK for Python is version 1.25.16 or later before you run the following code.If the version is too low, errors such as "url error, please check url!" may occur. To update the SDK, see Install the SDK.
import os
from http import HTTPStatus
from dashscope import VideoSynthesis
import dashscope

# The following URL is for the Singapore region. URLs differ by region. To obtain the URL for your region, visit: https://www.alibabacloud.com/help/en/model-studio/text-to-video-api-reference
dashscope.base_http_api_url = 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1'
# The API key varies by region. For more information about how to obtain an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
api_key = os.getenv("DASHSCOPE_API_KEY", "YOUR_API_KEY")

print('please wait...')
rsp = VideoSynthesis.call(api_key=api_key,
                          model='wan3.0-video',
                          prompt='Shot 1: Opening with a long shot. The camera starts from a low angle close to the ground and moves forward across the grassland. At the same time, the camera moves upward, gradually raising the point of view from ground level to a slightly elevated position. A cheetah enters the frame from the left, on the same chase path as a fleeing antelope in front of it, establishing a clear foreground-background spatial relationship. Shot 2: The camera moves downward, returning to a position close to the ground, and pans right to follow the cheetah\'s movement, steadily tracking it from a parallel side view. The subject remains consistently positioned slightly to the left of the frame\'s center, creating a continuous lateral movement effect in the background. The camera movement stays stable for a while to enhance the sense of speed and spatial continuity. Shot 3: While maintaining the rightward movement, the camera moves in a slight arc along the inside of the cheetah\'s path. This creates a subtle circling effect in the shot, but the camera always moves in the same direction as the subject. Shot 4: Gradually slow down the lateral movement and transition to a relatively stable camera position. At the same time, execute a zoom-in, progressively narrowing the visual focus onto the shrinking distance between the cheetah and the antelope. Shot 5: The camera moves forward again and slightly downward, closing in on the space between the two animals near the ground. It holds the shot at the critical moment when the cheetah\'s forelimbs are about to reach the antelope\'s rear, creating intense pressure and tension. This is accompanied by a crescendoing symphonic score, an increasingly intense drumbeat, and the sounds of wind and footsteps to drive the rhythm. In the final moments, the music volume drops, leaving only ambient and rhythmic sounds for a brief pause.',
                          resolution="720P",
                          ratio="16:9",
                          duration=15,
                          watermark=True)
print(rsp)
if rsp.status_code == HTTPStatus.OK:
    print("video_url:", rsp.output.video_url)
else:
    print('Failed, status_code: %s, code: %s, message: %s' % (rsp.status_code, rsp.code, rsp.message))
  • Python SDK
  • Java SDK
  • curl
Ensure that your DashScope SDK for Python is version 1.25.16 or later before you run the following code.If the version is too low, errors such as "url error, please check url!" may occur. To update the SDK, see Install the SDK.
import os
from http import HTTPStatus
from dashscope import VideoSynthesis
import dashscope

# The following URL is for the Singapore region. URLs differ by region. To obtain the URL for your region, visit: https://www.alibabacloud.com/help/en/model-studio/text-to-video-api-reference
dashscope.base_http_api_url = 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1'
# The API key varies by region. For more information about how to get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key.
api_key = os.getenv("DASHSCOPE_API_KEY", "YOUR_API_KEY")

print('please wait...')
rsp = VideoSynthesis.call(api_key=api_key,
                          model='wan2.6-t2v',
                          prompt='A thrilling detective chase story with cinematic storytelling. Shot 1 [0-3s]: Wide shot of a rainy New York street at night, neon lights flickering, a detective in a black trench coat walking briskly. Shot 2 [3-6s]: Medium shot of the detective entering an old building, rain soaking his coat, the door closing slowly behind him. Shot 3 [6-9s]: Close-up of the detectives focused, determined eyes as distant sirens wail and he frowns slightly in thought. Shot 4 [9-12s]: Medium shot of the detective moving carefully down a dim hallway, his flashlight illuminating the path ahead. Shot 5 [12-15s]: Close-up of the detective discovering a key clue, his face lighting up with sudden realization.',
                          size="1280*720",
                          duration=15,
                          shot_type="multi",
                          watermark=True)
print(rsp)
if rsp.status_code == HTTPStatus.OK:
    print("video_url:", rsp.output.video_url)
else:
    print('Failed, status_code: %s, code: %s, message: %s' % (rsp.status_code, rsp.code, rsp.message))
Sample output
video_url is valid for 24 hours. Download the video promptly.
{
    "request_id": "c1209113-8437-424f-a386-xxxxxx",
    "output": {
        "task_id": "966cebcd-dedc-4962-af88-xxxxxx",
        "task_status": "SUCCEEDED",
        "video_url": "https://dashscope-result-sh.oss-accelerate.aliyuncs.com/xxx.mp4?Expires=xxx"
    }
}

Availability

Supported models vary by region. Resources are isolated between regions. When making a call, make sure your model, endpoint URL, and API key all belong to the same region. Cross-region calls fail. Supported models:
  • Global
  • International
  • US
  • Chinese mainland
If you select the Global deployment scope, model inference compute resources are dynamically scheduled worldwide. Static data is stored in your selected region. Supported regions: US (Virginia), Germany (Frankfurt),China (Hong Kong).

Model

Features

Input modality

Output video specifications

wan2.6-t2v Recommended

Video with audio

Multi-shot narrative, audio-video synchronization

Text, audio

Resolution options: 720P, 1080P

Video duration: 5s, 10s, 15s

Defined specifications: 30 fps, MP4 (H.264 encoding)

The sample code in this topic applies to the Singapore region.

Core capabilities

Create multi-shot videos

Supported models: wan3.0, wan2.7, and wan2.6 series. Description: Automatically switches between shots — for example, from a wide shot to a close-up. Ideal for music videos and cinematic narratives. Parameters:
  • wan2.7: The shot_type parameter is not required. Describe shot structure in the prompt using natural language, such as timestamps to define shots. If the prompt does not contain shot structure descriptions, the model analyzes semantics and automatically determines whether to generate a single-shot or multi-shot video.
  • wan2.6: The shot_type parameter must be set to "multi", and the prompt_extend parameter must be set to true to enable intelligent rewriting to optimize shot descriptions.
Input promptOutput video (wan3.0)
A vision of harmony between future technology and nature. Shot 1 [0-2s]: Wide shot of an aerial garden in a futuristic city, floating plants swaying gently in the breeze. Shot 2 [2-4s]: A robot gardener carefully trims plants with precise, graceful movements. Shot 3 [4-7s]: Sunlight streams through a transparent dome, illuminating the entire garden and showcasing the perfect fusion of technology and nature. Shot 4 [7-10s]: The camera pulls back to reveal the grand scale of the entire futuristic city, with the aerial garden as just one part of it.
This is a martial arts film clip centered on a hardcore duel. On a stone clearing under the midday sun, two men charge at each other. One strikes with his palm, but his opponent spins and blocks with his arm, the impact kicking up dust from the ground. They then exchange rapid punches and palm strikes in a tight space. One leaps into the air for a series of heavy kicks, forcing his opponent to cross his arms to block and slide back several meters, leaving clear white marks on the stone surface. Finally, they stand apart, breathing heavily and locking eyes. The scene presents a realistic action texture with sharp lighting, creating a tone that shifts from powerful explosion to a tense standoff.
  • Python SDK
  • Java SDK
  • curl
Ensure that your DashScope SDK for Python is version 1.25.16 or later. To update the SDK, see Install the SDK .
import os
from http import HTTPStatus
from dashscope import VideoSynthesis
import dashscope

# The following URL is for the Singapore region. URLs differ by region. To obtain the URL for your region, visit: https://www.alibabacloud.com/help/en/model-studio/text-to-video-api-reference
dashscope.base_http_api_url = 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1'

# If you have not configured environment variables, replace the following line with api_key="sk-xxx". Use your Model Studio API key.
# The API key varies by region. For more information about how to get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key.
api_key = os.getenv("DASHSCOPE_API_KEY")

def sample_async_call_t2v():
    # Asynchronous invocation that returns a task_id.
    rsp = VideoSynthesis.async_call(api_key=api_key,
                                    model='wan3.0-video',
                                    prompt='A vision of harmony between future technology and nature. Shot 1 [0-2s]: Wide shot of an aerial garden in a futuristic city, floating plants swaying gently in the breeze. Shot 2 [2-4s]: A robot gardener carefully trims plants with precise, graceful movements. Shot 3 [4-7s]: Sunlight streams through a transparent dome, illuminating the entire garden and showcasing the perfect fusion of technology and nature. Shot 4 [7-10s]: The camera pulls back to reveal the grand scale of the entire futuristic city, with the aerial garden as just one part of it.',
                                    resolution='720P',
                                    ratio='16:9',
                                    duration=10,
                                    watermark=True,
                                    seed=12345)
    print(rsp)
    if rsp.status_code == HTTPStatus.OK:
        print("task_id: %s" % rsp.output.task_id)
    else:
        print('Failed, status_code: %s, code: %s, message: %s' % (rsp.status_code, rsp.code, rsp.message))

    # Wait for the asynchronous task to complete.
    rsp = VideoSynthesis.wait(task=rsp, api_key=api_key)
    print(rsp)
    if rsp.status_code == HTTPStatus.OK:
        print(rsp.output.video_url)
    else:
        print('Failed, status_code: %s, code: %s, message: %s' % (rsp.status_code, rsp.code, rsp.message))

if __name__ == '__main__':
    sample_async_call_t2v()
  • Python SDK
  • Java SDK
  • curl
Ensure that your DashScope SDK for Python is version 1.25.16 or later. To update the SDK, see Install the SDK .
import os
from http import HTTPStatus
from dashscope import VideoSynthesis
import dashscope

# The following URL is for the Singapore region. URLs differ by region. To obtain the URL for your region, visit: https://www.alibabacloud.com/help/en/model-studio/text-to-video-api-reference
dashscope.base_http_api_url = 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1'

# If you have not configured the environment variable, replace the following line with your Model Studio API key: api_key="sk-xxx"
# API keys vary by region. To obtain an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
api_key = os.getenv("DASHSCOPE_API_KEY")

def sample_async_call_t2v():
    # Make an asynchronous invocation to return a task_id.
    rsp = VideoSynthesis.async_call(api_key=api_key,
                                    model='wan2.6-t2v',
                                    prompt='Show a beautiful vision of the future where technology and nature coexist in harmony. Shot 1 [0-2s]: A panoramic view of a hanging garden in a futuristic city, with floating plants swaying in the breeze. Shot 2 [2-4s]: A robot gardener meticulously prunes the plants with precise and elegant movements. Shot 3 [4-7s]: Sunlight streams through a transparent dome, illuminating the entire garden and showcasing the perfect fusion of technology and nature. Shot 4 [7-10s]: The camera pulls back to reveal the magnificent view of the entire futuristic city, of which the hanging garden is just one part.',
                                    size='1280*720',
                                    duration=10,
                                    shot_type='multi',
                                              watermark=True,
                                    seed=12345)
    print(rsp)
    if rsp.status_code == HTTPStatus.OK:
        print("task_id: %s" % rsp.output.task_id)
    else:
        print('Failed, status_code: %s, code: %s, message: %s' % (rsp.status_code, rsp.code, rsp.message))

    # Wait for the asynchronous task to complete.
    rsp = VideoSynthesis.wait(task=rsp, api_key=api_key)
    print(rsp)
    if rsp.status_code == HTTPStatus.OK:
        print(rsp.output.video_url)
    else:
        print('Failed, status_code: %s, code: %s, message: %s' % (rsp.status_code, rsp.code, rsp.message))

if __name__ == '__main__':
    sample_async_call_t2v()

Synchronize audio and video

Supported models: wan3.0, wan2.7, wan2.6, and wan2.5 series. Description: Characters in the video can "speak" or sing, with mouth movements matching the audio. For more examples, see Video audio generation. Parameters:
  • Provide an audio file: Set audio_url. The model synchronizes mouth movements with the audio file.
  • Automatic dubbing: Without an audio_url, the model automatically generates audio-enabled video by default — adding background sound effects, music, or voices based on the visual content.
Input exampleOutput video (audio-enabled video)
Input prompt: Shot from a low angle, in a medium close-up, with warm tones, mixed lighting (the practical light from the desk lamp blends with the overcast light from the window), side lighting, and a central composition. In a classic detective office, wooden bookshelves are filled with old case files and ashtrays. A green desk lamp illuminates a case file spread out in the center of the desk. A fox, wearing a dark brown trench coat and a light gray fedora, sits in a leather chair, its fur crimson, its tail resting lightly on the edge, its fingers slowly turning yellowed pages. Outside, a steady drizzle falls beneath a blue sky, streaking the glass with meandering streaks. It slowly raises its head, its ears twitching slightly, its amber eyes gazing directly at the camera, its mouth clearly moving as it speaks in a smooth, cynical voice: 'The case was cold, colder than a fish in winter. But every chicken has its secrets, and I, for one, intended to find them '.Input audio:
  • Python SDK
  • Java SDK
  • curl
Ensure that your DashScope SDK for Python is version 1.25.16 or later. To update the SDK, see Install the SDK .
import os
from http import HTTPStatus
from dashscope import VideoSynthesis
import dashscope

# The following URL is for the Singapore region. URLs differ by region. To obtain the URL for your region, visit: https://www.alibabacloud.com/help/en/model-studio/text-to-video-api-reference
dashscope.base_http_api_url = 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1'

# If you have not configured environment variables, replace the following line with api_key="sk-xxx". Use your Model Studio API key.
# The API key varies by region. For more information about how to get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key.
api_key = os.getenv("DASHSCOPE_API_KEY")

def sample_async_call_t2v():
    # Asynchronous invocation that returns a task_id.
    rsp = VideoSynthesis.async_call(api_key=api_key,
                                    model='wan3.0-video',
                                    prompt="Shot from a low angle, in a medium close-up, with warm tones, mixed lighting (the practical light from the desk lamp blends with the overcast light from the window), side lighting, and a central composition. In a classic detective office, wooden bookshelves are filled with old case files and ashtrays. A green desk lamp illuminates a case file spread out in the center of the desk. A fox, wearing a dark brown trench coat and a light gray fedora, sits in a leather chair, its fur crimson, its tail resting lightly on the edge, its fingers slowly turning yellowed pages. Outside, a steady drizzle falls beneath a blue sky, streaking the glass with meandering streaks. It slowly raises its head, its ears twitching slightly, its amber eyes gazing directly at the camera, its mouth clearly moving as it speaks in a smooth, cynical voice: 'The case was cold, colder than a fish in winter. But every chicken has its secrets, and I, for one, intended to find them '.",
                                    audio_url='https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250929/stjqnq/%E7%8B%90%E7%8B%B8.mp3',
                                    resolution='720P',
                                    ratio='16:9',
                                    duration=10,
                                    watermark=True,
                                    seed=12345)
    print(rsp)
    if rsp.status_code == HTTPStatus.OK:
        print("task_id: %s" % rsp.output.task_id)
    else:
        print('Failed, status_code: %s, code: %s, message: %s' % (rsp.status_code, rsp.code, rsp.message))

    # Wait for the asynchronous task to complete.
    rsp = VideoSynthesis.wait(task=rsp, api_key=api_key)
    print(rsp)
    if rsp.status_code == HTTPStatus.OK:
        print(rsp.output.video_url)
    else:
        print('Failed, status_code: %s, code: %s, message: %s' % (rsp.status_code, rsp.code, rsp.message))

if __name__ == '__main__':
    sample_async_call_t2v()
  • Python SDK
  • Java SDK
  • curl
Ensure that your DashScope SDK for Python is version 1.25.16 or later. To update the SDK, see Install the SDK .
import os
from http import HTTPStatus
from dashscope import VideoSynthesis
import dashscope

# The following URL is for the Singapore region. URLs differ by region. To obtain the URL for your region, visit: https://www.alibabacloud.com/help/en/model-studio/text-to-video-api-reference
dashscope.base_http_api_url = 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1'

# If you have not configured the environment variable, replace the following line with your Model Studio API key: api_key="sk-xxx"
# API keys vary by region. To get an API key, visit: https://www.alibabacloud.com/help/en/model-studio/get-api-key
api_key = os.getenv("DASHSCOPE_API_KEY")

def sample_async_call_t2v():
    # Make an asynchronous invocation to return a task_id.
    rsp = VideoSynthesis.async_call(api_key=api_key,
                                    model='wan2.6-t2v',
                                    prompt="Shot from a low angle, in a medium close-up, with warm tones, mixed lighting (the practical light from the desk lamp blends with the overcast light from the window), side lighting, and a central composition. In a classic detective office, wooden bookshelves are filled with old case files and ashtrays. A green desk lamp illuminates a case file spread out in the center of the desk. A fox, wearing a dark brown trench coat and a light gray fedora, sits in a leather chair, its fur crimson, its tail resting lightly on the edge, its fingers slowly turning yellowed pages. Outside, a steady drizzle falls beneath a blue sky, streaking the glass with meandering streaks. It slowly raises its head, its ears twitching slightly, its amber eyes gazing directly at the camera, its mouth clearly moving as it speaks in a smooth, cynical voice: 'The case was cold, colder than a fish in winter. But every chicken has its secrets, and I, for one, intended to find them '.",
                                    audio_url='https://help-static-aliyun-doc.aliyuncs.com/file-manage-files/zh-CN/20250929/stjqnq/%E7%8B%90%E7%8B%B8.mp3',
                                    size='1280*720',
                                    duration=10,
                                    watermark=True,
                                    seed=12345)
    print(rsp)
    if rsp.status_code == HTTPStatus.OK:
        print("task_id: %s" % rsp.output.task_id)
    else:
        print('Failed, status_code: %s, code: %s, message: %s' % (rsp.status_code, rsp.code, rsp.message))

    # Wait for the asynchronous task to complete.
    rsp = VideoSynthesis.wait(task=rsp, api_key=api_key)
    print(rsp)
    if rsp.status_code == HTTPStatus.OK:
        print(rsp.output.video_url)
    else:
        print('Failed, status_code: %s, code: %s, message: %s' % (rsp.status_code, rsp.code, rsp.message))

if __name__ == '__main__':
    sample_async_call_t2v()

Generate silent videos

Supported models: wan2.2 series, wan2.1 series. Description: Best for scenarios that need only visual content, such as dynamic posters and silent short videos. Parameters: The wan2.2 and earlier models generate silent videos by default. No additional configuration is needed.
Input promptOutput video (silent video)
Rim light, low contrast, medium close-up, daylight, left-heavy composition, clean single-person shot, warm tones, soft light, sunny day light, side light, daytime. A young girl sits in a field of tall grass with two fluffy donkeys standing behind her. The girl, about eleven or twelve, wears a simple floral dress, her hair in two braids, and has an innocent smile. She sits cross-legged, gently touching the wildflowers beside her. The donkeys are sturdy, their ears pricked up, curiously looking toward the camera. Sunlight bathes the field, creating a warm and natural scene.
  • Python SDK
  • Java SDK
  • curl
Ensure that your DashScope SDK for Python is version 1.25.16 or later. To update the SDK, see Install the SDK .
import os
from http import HTTPStatus
from dashscope import VideoSynthesis
import dashscope

# The following URL is for the Singapore region. URLs differ by region. To obtain the URL for your region, visit: https://www.alibabacloud.com/help/en/model-studio/text-to-video-api-reference
dashscope.base_http_api_url = 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1'

# If you have not configured environment variables, replace the following line with api_key="sk-xxx". Use your Model Studio API key.
# The API key varies by region. For more information about how to get an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key.
api_key = os.getenv("DASHSCOPE_API_KEY")

def sample_async_call_t2v():
    # Asynchronous invocation that returns a task_id.
    rsp = VideoSynthesis.async_call(api_key=api_key,
                                    model='wan2.2-t2v-plus',
                                    prompt='Rim light, low contrast, medium close-up, daylight, left-heavy composition, clean single-person shot, warm tones, soft light, sunny day light, side light, daytime. A young girl sits in a field of tall grass with two fluffy donkeys standing behind her. The girl, about eleven or twelve, wears a simple floral dress, her hair in two braids, and has an innocent smile. She sits cross-legged, gently touching the wildflowers beside her. The donkeys are sturdy, their ears pricked up, curiously looking toward the camera. Sunlight bathes the field, creating a warm and natural scene.',
                                              size='832*480',
                                    watermark=True,
                                    seed=12345)
    print(rsp)
    if rsp.status_code == HTTPStatus.OK:
        print("task_id: %s" % rsp.output.task_id)
    else:
        print('Failed, status_code: %s, code: %s, message: %s' % (rsp.status_code, rsp.code, rsp.message))

    # Wait for the asynchronous task to complete.
    rsp = VideoSynthesis.wait(task=rsp, api_key=api_key)
    print(rsp)
    if rsp.status_code == HTTPStatus.OK:
        print(rsp.output.video_url)
    else:
        print('Failed, status_code: %s, code: %s, message: %s' % (rsp.status_code, rsp.code, rsp.message))

if __name__ == '__main__':
    sample_async_call_t2v()

Input audio

  • Number of files: One.
  • Input methods:
    • Public URL: HTTP or HTTPS.

Output video

  • Number of videos: One.
  • Format: MP4. For more information, see Video specifications.
  • URL expiration: 24 hours.
  • Video dimensions:
    • The wan3.0 and wan2.7 models use the resolution and ratio parameters.
    • The wan2.6 and earlier models use the size parameter.

Billing and rate limiting

  • For free quota and pricing details, see Wanx-Text-to-Video.
  • For model rate limiting, see Wanxiang series.
  • Billing details:
    • Input is free. Output is billed per successfully generated video second.
    • Failed model calls or processing errors do not incur charges or consume free quota.
    • Text-to-video also supports savings plans.

API reference

Text-to-video API reference

FAQ

Q: What code changes are needed to upgrade from wan2.7 to wan3.0?

  • Model name: Change model from wan2.7-t2v-* to wan3.0-video.
  • Remove prompt_extend: wan3.0 does not support the prompt_extend parameter. Remove this field.
  • Extended duration: wan3.0 supports up to 30 seconds (wan2.7 supports up to 15 seconds). Set duration to an integer between 2 and 30.
  • New file and web input: wan3.0 supports passing type: "file" (docx, ppt, pdf, etc.) or type: "link" (public web URL) in input.media. The model automatically understands the content and generates a video. These two types cannot be used simultaneously.

Q: The videos generated in the console have a watermark. How do I remove it?

  • The video generation page in the Model Studio console does not provide a watermark switch, so you cannot disable the watermark in the console.
  • When you call the model through the API, set watermark to false to generate a video without a watermark.
  • If you omit the watermark parameter, the API adds a watermark by default. The sample code in this topic passes watermark=true; change it to false to remove the watermark.

Q: I purchased an AI general-purpose savings plan. Why do the generated videos still have a watermark?

  • An AI general-purpose savings plan only offsets your cost. It does not change model output and is unrelated to whether a video carries a watermark.
  • The watermark is controlled solely by the API watermark parameter: set it to false to remove the watermark, or omit it to keep the default watermark.
Token Plan
Model Playground
Statistics and Monitoring
Support