DreamActor V2
ByteDance DreamActor V2 is a motion transfer model that animates any character — human, cartoon, or creature — by applying movements from a reference video to a static image.
ByteDance 
WaveSpeed Animate any character from a single image
DreamActor V2 is a video generation model developed by ByteDance that animates static images by transferring motion from a reference driving video onto a target character. It is the second generation of ByteDance's DreamActor series and was made available in February 2026. Rather than relying on skeleton extraction or pose estimation pipelines, it uses a spatiotemporal in-context learning framework that reads motion directly from raw video pixels, which allows it to handle character types that traditional pose-based methods struggle with, including animals, cartoon mascots, fantasy creatures, and 3D renders.
DreamActor V2 accepts two inputs — a character image and a driving video — and produces animated video outputs up to 15 seconds at 720p resolution across a range of aspect ratios. It transfers facial expressions, head orientation, eye direction, lip movement, hand gestures, and full-body motion while maintaining the structural consistency of the source character across frames. This makes it applicable to use cases such as social media content creation, brand animation, virtual avatar production, game asset prototyping, and educational video generation.
What DreamActor V2 supports
Motion Transfer
Transfers motion from a driving video onto a static character image by reading movement directly from raw video pixels, without requiring skeleton extraction or pose estimation.
Universal Character Support
Animates human photographs, digital illustrations, anime artwork, cartoon mascots, fantasy creatures, and 3D renders using the same pipeline.
Expression & Gesture Capture
Transfers subtle facial movements including eye direction, lip sync, head turns, hand gestures, and full-body language from the reference video.
Image Input
Accepts a static character image as the primary subject input, supporting photographs, illustrations, and rendered artwork via image URL.
Video Input
Accepts a driving video via URL to serve as the motion reference, with output videos up to 15 seconds at 720p resolution.
Structural Stability
Maintains consistent face, limb, and body form across frames using a spatiotemporal in-context learning framework, reducing per-frame distortion.
Multi-Character Scenes
Coordinates motion transfer across multiple subjects within a single scene, preserving independent motion for each character.
Ready to build with DreamActor V2?
Get Started FreeCommon questions about DreamActor V2
What inputs does DreamActor V2 require?
DreamActor V2 requires exactly two inputs: a character image (provided as an image URL) and a driving video (provided as a video URL). No rigging, pose estimation, or manual keyframing is needed.
What types of characters can DreamActor V2 animate?
The model supports human portraits as well as non-human subjects including animals, robots, cartoon mascots, anime artwork, fantasy creatures, and 3D renders, because it reads motion from raw video pixels rather than relying on human skeleton detection.
What is the maximum output length and resolution?
DreamActor V2 supports video outputs up to 15 seconds in length at 720p resolution, across a range of aspect ratios.
What is the context window for this model?
The model has a context window of 1000 tokens as listed in the metadata.
When was DreamActor V2 released?
DreamActor V2 was released in February 2026 by ByteDance.
How does DreamActor V2 differ from earlier animation approaches?
Earlier animation tools typically extract skeletons or estimate poses from the driving video, which fails for non-human subjects. DreamActor V2 uses a spatiotemporal in-context learning framework that reads motion directly from raw video pixels, enabling it to animate virtually any character type.
Explore similar models
ByteDance Seedance 1.5 Pro
ByteDance's cinematic image-to-video AI model that generates high-quality 1080p videos with natively synchronized audio from static images in a single pass.
ByteDance Seedream 5.0 Lite
ByteDance's lightweight Seedream 5.0 image editing model, delivering fast, high-fidelity transformations with exceptional face preservation and multi-reference support.
ByteDance Seedream 4.5
ByteDance's unified AI model that seamlessly combines high-fidelity image generation and intelligent image editing in a single architecture, with standout text rendering and multi-image composition capabilities.
Kling Kling 3.0 Motion Control
Kling 3.0 Standard Motion Control transfers motion from reference videos to animate still images.
PixVerse PixVerse V5.6
PixVerse V5.6 is an AI video generation model that gives you precise creative control over your videos, including the unique ability to define both the starting and ending frames of every scene.
X.ai Grok Imagine
X.ai's fast, native text-to-video and image-to-video generation model with built-in audio, multiple aspect ratios, and flexible creative modes.
Start building with DreamActor V2
No API keys required. Create AI-powered workflows with DreamActor V2 in minutes — free.