All Models

Alibaba logo

WAN 2.5 Fast API

WAN 2.5 Fast creates videos from text or still images and extends existing clips, with supplied or generated audio and lip synchronization for speech-led scenes.

Try in Studio
More options (5)
Generate

Pricing depends on the selected inputs. See the rates below.

Supported modes

Text to Video

Text to Video uses prompt. Adjust the model options to prepare a request for this mode.

video.generate

Animate

Animate uses image and prompt. Adjust the model options to prepare a request for this mode.

video.animate

Extend

Extend uses prompt and video. Adjust the model options to prepare a request for this mode.

video.extend

Pricing

Image to video

Price per run for each listed option.

OfferingPrice (USD)
Duration: 3s · Resolution: 720p$0.21 / run
Duration: 3s · Resolution: 1080p$0.31 / run
Duration: 4s · Resolution: 720p$0.28 / run
Duration: 4s · Resolution: 1080p$0.41 / run
Duration: 5s · Resolution: 720p$0.34 / run
Duration: 5s · Resolution: 1080p$0.51 / run
Duration: 6s · Resolution: 720p$0.41 / run
Duration: 6s · Resolution: 1080p$0.62 / run
Duration: 7s · Resolution: 720p$0.48 / run
Duration: 7s · Resolution: 1080p$0.72 / run
Duration: 8s · Resolution: 720p$0.55 / run
Duration: 8s · Resolution: 1080p$0.82 / run
  • Audio count: 0, 1 (same price).
  • Enable Prompt Expansion: Off, On (same price).

Text to video

Price per run for each listed option.

OfferingPrice (USD)
Duration: 5s · Size: 1280 × 720$0.34 / run
Duration: 5s · Size: 720 × 1280$0.34 / run
Duration: 5s · Size: 1920 × 1080$0.51 / run
Duration: 5s · Size: 1080 × 1920$0.51 / run
Duration: 10s · Size: 1280 × 720$0.68 / run
Duration: 10s · Size: 720 × 1280$0.68 / run
Duration: 10s · Size: 1920 × 1080$1.02 / run
Duration: 10s · Size: 1080 × 1920$1.02 / run
  • Audio count: 0, 1 (same price).
  • Enable Prompt Expansion: Off, On (same price).

Video extension

Price per run for each listed option.

OfferingPrice (USD)
Duration: 3s · Resolution: 720p$0.21 / run
Duration: 3s · Resolution: 1080p$0.31 / run
Duration: 4s · Resolution: 720p$0.28 / run
Duration: 4s · Resolution: 1080p$0.41 / run
Duration: 5s · Resolution: 720p$0.34 / run
Duration: 5s · Resolution: 1080p$0.51 / run
Duration: 6s · Resolution: 720p$0.41 / run
Duration: 6s · Resolution: 1080p$0.62 / run
Duration: 7s · Resolution: 720p$0.48 / run
Duration: 7s · Resolution: 1080p$0.72 / run
Duration: 8s · Resolution: 720p$0.55 / run
Duration: 8s · Resolution: 1080p$0.82 / run
  • Audio count: 0, 1 (same price).
  • Enable Prompt Expansion: Off, On (same price).

Text to Video options

OptionDetailsDefault
Audio
audio
A public URL, a data URI, or an asset id.—
Prompt *
prompt
The positive prompt for the generation.—
Duration
duration
The duration of the generated media in seconds. Options: 5, 10.5
Enable prompt expansion
enable_prompt_expansion
If set to true, the prompt optimizer will be enabled.false
Negative prompt
negative_prompt
The negative prompt for the generation.—
Seed
seed
The random seed to use for the generation. -1 means a random seed will be used.—
Size
size
The size of the generated media in pixels (width*height). Options: 1280*720, 720*1280, 1920*1080, 1080*1920."1280*720"

WAN 2.5 Fast

WAN 2.5 Fast generates moving scenes from written descriptions and animates supplied images. Text defines the scene and action; image input establishes a visual starting point. Both routes support audiovisual generation, including speech synchronized with visible mouth movement.

Supplied audio can guide generation, and the model can also generate audio. Its extension task uses an existing video as the basis for continued footage, carrying forward scene lighting and motion. Extension accepts Chinese and English descriptions to direct how the scene develops.

What it's good for

Presenter-style concepts and dialogue scenes benefit from exploring speech alongside its visible delivery. Prepared character artwork can become an animated scene, while text-to-video offers a way to develop a training example or narrative idea directly from a written concept.

For an established sequence, extension helps test the next action or continue a camera move. Audio guidance also supports exploring how a spoken passage fits the continuation, giving editors material for reviewing scene progression.

Run WAN 2.5 Fast on Protoface

Use WAN 2.5 Fast in Protoface Studio without writing code. Choose your inputs and generation settings, then generate with affordable, usage-based pricing. For your own AI app or workflow, use the Protoface API to submit generations and retrieve their outputs.

Model publisher

About Alibaba

Alibaba’s generative AI work includes the Qwen model family and Alibaba Cloud’s infrastructure for model development. Qwen research spans language, coding, mathematics, vision and audio, with families such as Qwen-Coder and Qwen-VL. Alibaba Cloud provides tools for training, fine-tuning and deploying foundation models as online services.

  • Qwen models
  • Multimodal research
  • Model development

Related models

Unified API

One API for generative media.

Protoface serves popular frontier AI models through one API.

  • minimax
  • minimax
  • z.ai
  • z.ai
  • z.ai
  • z.ai
  • z.ai
  • z.ai
  • z.ai

Unified API

One API for generative media.

Protoface serves popular frontier AI models through one API.

  • minimax
  • minimax
  • z.ai
  • z.ai
  • z.ai
  • z.ai
  • z.ai
  • z.ai
  • z.ai

Unified API

One API for generative media.

Protoface serves popular frontier AI models through one API.

  • minimax
  • minimax
  • z.ai
  • z.ai
  • z.ai
  • z.ai
  • z.ai
  • z.ai
  • z.ai