All Models

Alibaba logo

WAN 2.5 API

WAN 2.5 generates still images and video, animates artwork, and extends clips. Video generation supports supplied or generated audio with synchronized speech and mouth movement.

Try in Studio
More options (4)
Generate

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

WAN 2.5 example

Supported modes

Text to Image

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

image.generate

Animate

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

video.animate

Text to Video

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

video.generate

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: 480p$0.15 / run
Duration: 3s · Resolution: 720p$0.30 / run
Duration: 3s · Resolution: 1080p$0.45 / run
Duration: 4s · Resolution: 480p$0.20 / run
Duration: 4s · Resolution: 720p$0.40 / run
Duration: 4s · Resolution: 1080p$0.60 / run
Duration: 5s · Resolution: 480p$0.25 / run
Duration: 5s · Resolution: 720p$0.50 / run
Duration: 5s · Resolution: 1080p$0.75 / run
Duration: 6s · Resolution: 480p$0.30 / run
Duration: 6s · Resolution: 720p$0.60 / run
Duration: 6s · Resolution: 1080p$0.90 / run
  • Audio count: 0, 1 (same price).
  • Enable Prompt Expansion: Off, On (same price).

Image generation

Price per run for each listed option.

OfferingPrice (USD)
All listed options$0.03 / run
  • Enable Prompt Expansion: Off, On (same price).
  • Size: 768 × 768, 1024 × 1024, 1440 × 1440 (same price).

Text to video

Price per run for each listed option.

OfferingPrice (USD)
Duration: 5s · Size: 832 × 480$0.25 / run
Duration: 5s · Size: 480 × 832$0.25 / run
Duration: 5s · Size: 1280 × 720$0.50 / run
Duration: 5s · Size: 720 × 1280$0.50 / run
Duration: 5s · Size: 1920 × 1080$0.75 / run
Duration: 5s · Size: 1080 × 1920$0.75 / run
Duration: 10s · Size: 832 × 480$0.50 / run
Duration: 10s · Size: 480 × 832$0.50 / run
Duration: 10s · Size: 1280 × 720$1.00 / run
Duration: 10s · Size: 720 × 1280$1.00 / run
Duration: 10s · Size: 1920 × 1080$1.50 / run
Duration: 10s · Size: 1080 × 1920$1.50 / 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: 480p$0.15 / run
Duration: 3s · Resolution: 720p$0.30 / run
Duration: 3s · Resolution: 1080p$0.45 / run
Duration: 4s · Resolution: 480p$0.20 / run
Duration: 4s · Resolution: 720p$0.40 / run
Duration: 4s · Resolution: 1080p$0.60 / run
Duration: 5s · Resolution: 480p$0.25 / run
Duration: 5s · Resolution: 720p$0.50 / run
Duration: 5s · Resolution: 1080p$0.75 / run
Duration: 6s · Resolution: 480p$0.30 / run
Duration: 6s · Resolution: 720p$0.60 / run
Duration: 6s · Resolution: 1080p$0.90 / run
  • Audio count: 0, 1 (same price).
  • Enable Prompt Expansion: Off, On (same price).

Text to Image options

OptionDetailsDefault
Prompt *
prompt
The positive prompt for the generation.—
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
Optional output canvas. Explicit sizes: 768*768, 1024*1024, or 1440*1440. Options: 768*768, 1024*1024, 1440*1440. Minimum: 384. Maximum: 2880."1024*1024"

WAN 2.5

WAN 2.5 covers still-image creation and moving scenes. Written descriptions can produce images with photographic or illustrated treatments, or generate video directly. A supplied image provides the visual starting point for animation, connecting concept artwork with motion development.

Video generation supports audio and lip synchronization, using supplied audio or sound generated by the model. Video extension takes an existing clip and develops further footage, carrying forward its motion and lighting. These tasks allow a project to progress from a visual idea to an audiovisual scene and its continuation.

What it's good for

A creative team can develop character artwork or a product concept as a still, then animate the chosen image for a campaign mockup. This gives reviewers material for assessing appearance and movement within the same development process.

Speech-aware generation suits dialogue scenes and presenter-led training concepts. Extension helps explore how an established shot carries on through another action or a spoken passage, supporting story and editorial decisions.

Run WAN 2.5 on Protoface

Use WAN 2.5 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