Act-Two
Act-Two enables animation of any character by transferring movements, expressions, and speech from a driving performance video onto a static image or reference video of your character. By selecting the Gen‑4 Video model and then the Act‑Two icon in Runway’s web interface, you supply two inputs; a performance video of an actor enacting your desired scene and a character input (either a single image or a video clip), and optionally enable gesture control to map hand and body movements onto character images. Act‑Two automatically adds environmental and camera motion to still images, supports a range of angles, non‑human subjects, and artistic styles, and retains original scene dynamics when using character videos (though with facial rather than full‑body gesture mapping). Users can adjust facial expressiveness on a sliding scale to balance natural motion with character consistency, preview results in real time, and generate high‑resolution clips up to 30 seconds long.
Learn more
Wan2.2-Animate
Wan2.2 Animate is a specialized module within the Wan video generation framework designed for high-fidelity character animation and character replacement, enabling users to transform static images into dynamic videos or swap subjects within existing footage while preserving realism and motion consistency. It works by taking two primary inputs: a reference image that defines the character’s appearance and a reference video that provides motion, expressions, and scene context. Using this combination, it can animate a still character by replicating body movements, gestures, and facial expressions from the source video, or replace the original subject in a video while maintaining the original lighting, camera movement, and environment for seamless integration. It relies on advanced techniques such as spatially aligned skeleton signals and implicit facial feature extraction to accurately reproduce motion and expressions.
Learn more
AvatarFX
Character.AI has unveiled AvatarFX, an AI-powered video generation tool currently in closed beta. This technology enables users to animate static images into realistic, long-form videos featuring synchronized lip movements, gestures, and expressions. AvatarFX supports a variety of visual styles, including 2D animated characters, 3D cartoon figures, and non-human faces like pets. It maintains high temporal consistency in facial, hand, and body movements, even in extended videos, ensuring smooth and natural animations. Unlike traditional text-to-image generation methods, AvatarFX allows users to create videos directly from existing images, offering greater control over the final output. AvatarFX is particularly beneficial for enhancing AI chatbot interactions, enabling the creation of lifelike avatars that can speak, emote, and engage in dynamic conversations. Users interested in early access can apply through Character.AI's platform.
Learn more
MiniMax H3
MiniMax H3 is a general-purpose omni-modal generation model that jointly understands multimodal contexts spanning text, images, video, and audio. It generates videos with native stereo sound at up to 2K resolution and 15 seconds in length, delivering content for advertising, branding, ecommerce, product design, UI/UX, gaming, and creative workflows. Users can combine reference types in one instruction, for example, transferring camera movement from a video, placing a character from an image into the scene, and matching vocals from an audio clip, while describing the relationships in natural language. H3 supports text-to-image, text-to-video with jointly generated audio, multi-shot modeling, text-to-audio, and generalized reference and editing across images, videos, and audio. Voice, sound effects, and music are modeled together. The model excels at instruction following, accurate text and brand presentation, and video-to-video motion transfer.
Learn more
