Try MiniMax H3 (Text-to-Video) (Image-to-Video) from MiniMax →
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

ByteDance / DreamActor

DreamActor

bybytedance

Transform images into dynamic videos using ByteDance's DreamActor model. Supports real people, animation, and pets with facial and body movement driving.

Image to Video
Model ID
DreamActor
Provider
bytedance
Updated
1774537888
0
Comments
Average rating : 5 (3 users)
Providerbytedance
ModelDreamActor
Image to Video
wiro playground—bytedance/DreamActor
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

Format: jpeg, jpg or png. Size: maximum 4.7 MB. Resolution: between 480✖️480 and 1920✖️1080 (anything larger will be proportionally reduced) Image supports driving for real people, animation, pets, etc.; overly abstract subjects may fail to generate.

0 / 1
Maximum 1 video allowed
Drop video to upload

OR

Click to browse your device

Supports: MP4, WEBM, MOV

Format: mp4 or webm. Duration: maximum 30 seconds. Resolution: between 200✖️200 and 2048✖️1440(2K) supports both facial expressions and body movement driving, and can handle full-body, half-body, or portrait driving: source: Video (supports real people, animation, pets) range: Full face + body

Sample outputs
Updated 1774537888
# Overview DreamActor is a tool developed by ByteDance for generating videos from input images and reference videos. It enables users to create dynamic video content by leveraging facial expressions and body movements from source materials. # What you can build - Animated character videos - Video editing enhancements - Motion graphics for content creators - Personalized video content generation # Inputs - **Input Image**: JPEG, JPG, or PNG format (max 4.7 MB). Resolution between 480×480 and 1920×1080. - **Video**: MP4 or WebM format (max 30 seconds). Resolution between 200×200 and 2048×1440. # Outputs - Generated video with facial expressions and body movements driven by input data # Recommended settings - Use high-resolution input images (minimum 480×480) - Ensure reference videos contain clear facial and body movements - Test with various subject types including real people, animals, and animations # Limitations - Overly abstract subjects may fail to generate - Video duration must not exceed 30 seconds - Resolution of input images beyond 1920×1080 will be proportionally reduced # Safety & compliance - This tool is designed for creative and entertainment purposes - Users should ensure proper permissions when using real person references - Generated content should comply with platform guidelines

API quick start

Run DreamActor with a single API call.

POST https://api.wiro.ai/v1/Run/ByteDance/DreamActor
{
  "inputImage": "https://your-cdn.com/input.png",
  "inputVideo": "https://your-cdn.com/input.mp4"
}
View full API docs

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

All systems operational
WiroAboutBlogCareersContact
ProductModelsAgentsPricingPartnerChangelogStatusFAQ
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