Try Google Gemini Omni Flash Video Generator from Google →
Models
Agents
WorkflowsStudioPricingBlogDocs
ExploreDiscover models by categoryBrowse All ModelsBrowse the complete catalogSee FavoritesSign in to view saved models
OverviewThe platform at a glanceLearnSkills, knowledge, guardrailsAnatomyWhat makes agents reasonBuild Your AgentPick skills, set tier, deploy
Pre-built AgentsBrowse the catalog
Agent Usecases
Ad Campaign ManagerApp Event ManagerApp Review RepliesBarber BookingCustomer Win-BackEcommerce ListingsRestaurant Reviews
Sign InStart Building

Task History

Click to see output list

No tasks yet

Go to Models
Explore models/
Video GenerationActive

alibaba / wan 2.7

wan 2.7

byalibaba

Generate videos from text prompts using Alibaba's WAN 2.7 model. Supports both text-to-video and image-to-video conversion with customizable duration and resolution.

Text to VideoImage to Video
Model ID
wan 2.7
Provider
alibaba
Updated
1784809403
13
Comments
Average rating : 5 (14 users)
Provideralibaba
Modelwan 2.7
Text to VideoImage to Video
wiro playground—alibaba/wan 2.7
Reset to defaults
0 / 1
Maximum 1 image allowed
Drop image to upload

OR

Click to browse your device

Supports: JPG, JPEG, PNG, GIF, WEBP, HEIC

Optional. First frame image for i2v. If not provided, model runs as t2v. Formats: JPEG, JPG, PNG, WEBP. Resolution: 240-8000px. Max 20 MB.

Required. Describes the elements and visual characteristics for the generated video. Up to 5,000 characters.

Sample outputs
Updated 1784809403
## Overview WAN 2.7 is a text-to-video and image-to-video generation model developed by Alibaba. It enables users to create dynamic videos from textual descriptions or images, offering flexible controls over video duration, resolution, and additional customization options. ## What you can build - Dynamic video content from text prompts - Video animations from static images - Customized video sequences for creative projects - Automated video generation for marketing or educational use ## Inputs - **Image (First Frame)**: Optional first-frame image for image-to-video conversion. Formats: JPEG, JPG, PNG, WEBP (240-8000px, max 20 MB) - **Prompt**: Required description of video elements and visual characteristics (up to 5000 characters) - **Negative Prompt**: Optional exclusion criteria for output (up to 500 characters) - **Audio**: Optional driving audio for image-to-video or background audio for text-to-video (WAV, MP3, 2-30s, max 15 MB) - **Video (First Clip)**: Optional input video for continuation (MP4, MOV, 2-10s, max 100 MB) ## Outputs - Generated video files with customizable duration, resolution, and aspect ratio - Optional watermark for AI-generated content ## Recommended settings - Use 720P or 1080P resolution for best visual quality - Set duration between 5-15 seconds for optimal processing time - Enable prompt extension for improved quality with shorter prompts ## Limitations - Processing time may increase with longer durations or complex prompts - Watermarking is optional and must be manually enabled - Audio and video inputs must meet specified format and size requirements ## Safety & compliance - All generated content must comply with local laws and regulations - Users should verify all outputs before distribution - Model usage is subject to Alibaba's terms of service

Example prompts

Great starting points for wan 2.7.

The yellow commuter train finishes passing through the frame, with its final carriages exiting smoothly to the right, revealing the empty tracks and green trees behind the fence. Just as the train disappears, a person riding a vintage bicycle enters the frame from the bottom left foreground. They pedal leisurely down the left side of the empty street, riding over the white painted arrow and away from the camera. The leaves on the trees in the background gently rustle in a sudden light breeze, and the daytime lighting remains perfectly consistent, casting realistic, moving shadows of the cyclist onto the asphalt.Video Generation
The scene comes alive with a gentle breeze. The calm green water begins to ripple naturally, softly distorting the crisp reflections of the brightly colored buildings. The moored boats gently bob up and down against their wooden poles, creating small, realistic wakes. On the left, the man in the foreground casually walks forward a few steps while looking around. The camera executes a very slow, stable push-in straight down the center of the canal.Video Generation
A highly detailed macro shot of a crystal-clear glass on a rustic wooden table. Thick, steaming hot espresso is slowly poured into cold milk, creating intricate, physically accurate swirling gradients and foam patterns. As the liquids mix, the ambient lighting drastically shifts from cool, dim morning blue to intense, warm golden-hour sunlight, casting realistic dynamic shadows across the table.Video Generation

API quick start

Run wan 2.7 with a single API call.

POST https://api.wiro.ai/v1/Run/alibaba/wan 2.7
{
  "prompt": "The scene comes alive with a gentle breez…",
  "negativePrompt": "...",
  "duration": 5,
  "resolution": "720P"
}
View full API docs

Discover, test, and run AI models, build workflows and agents with one unified API.

All systems operational
WiroAboutBlogCareersContact
ProductModelsAgentsPricingChangelogStatusFAQ
Getting StartedIntroductionAuthenticationProjectsCode ExamplesWiro MCP ServerSelf-Hosted MCPn8n IntegrationLLMs.txt
API ReferenceModelsRun a ModelModel ParametersTasksLLM & Chat StreamingWebSocketRealtime VoiceFiles
© 2026 Wiro AI. All rights reserved.
PrivacyTermsData Deletion