UNO Multi-Subject Compose to Wan Animate

ByteDance UNO composes a character (and optional object/outfit reference) into a single consistent still via in-context multi-image conditioning on FLUX.1-dev, then a CLIP-Vision-encoded image-to-video model animates that still into a moving clip with the same identity and outfit.

Properties

family: character-consistency
modality: reference images (subject + object) + text -> composed still -> animated video
whyMultiModel: UNO's DiT adapter only produces a single still frame from reference images; it has no temporal/motion prior. A separate video diffusion model with its own vision encoder is required to turn the consistent still into motion without re-drifting identity.
steps: [object Object], [object Object], [object Object]
controls: number/order of reference images, text prompt for scene, UnoPE position mapping (subject vs. object disambiguation), CLIP Vision reference averaging across multiple stills to stabilize identity, negative reference image to suppress unwanted traits
exampleStack: ByteDance UNO (FLUX.1 dev) -> CLIP Vision encode -> Wan 2.2 image-to-video
useCases: [product/character mockups that need to move][outfit-consistent social clips from a single compose][game/animation asset previsualization]
pitfalls: UNO can still show attribute confusion between subject and object on complex multi-reference prompts; if the composed still has inconsistent lighting/crop, the video model's identity embedding destabilizes and drifts within a few seconds of generated motion
source: UNO: Less-to-More Generalization (ByteDance, ICCV 2025)

Provenance

Source: https://github.com/bytedance/UNO

Properties

family

character-consistency

modality

reference images (subject + object) + text -> composed still -> animated video

whyMultiModel

UNO's DiT adapter only produces a single still frame from reference images; it has no temporal/motion prior. A separate video diffusion model with its own vision encoder is required to turn the consistent still into motion without re-drifting identity.

steps

[object Object], [object Object], [object Object]

controls

number/order of reference images, text prompt for scene, UnoPE position mapping (subject vs. object disambiguation), CLIP Vision reference averaging across multiple stills to stabilize identity, negative reference image to suppress unwanted traits

exampleStack

ByteDance UNO (FLUX.1 dev) -> CLIP Vision encode -> Wan 2.2 image-to-video

useCases

[product/character mockups that need to move][outfit-consistent social clips from a single compose][game/animation asset previsualization]

pitfalls

UNO can still show attribute confusion between subject and object on complex multi-reference prompts; if the composed still has inconsistent lighting/crop, the video model's identity embedding destabilizes and drifts within a few seconds of generated motion

source

UNO: Less-to-More Generalization (ByteDance, ICCV 2025)