Stand-In Lightweight Identity Video Control

Stand-In adds a tiny conditional-image branch (~1% extra parameters) onto Wan2.1/2.2 that restricts self-attention with conditional position mapping, locking a face identity across an entire generated video clip while composing with pose-driven control or community style LoRAs.

Properties

family: character-consistency
modality: single face photo + text (+ optional pose video / style LoRA) -> identity-locked video
whyMultiModel: Identity extraction and video synthesis are handled by two separate networks: a dedicated face-recognition encoder produces the identity embedding, and a large pretrained video DiT (untouched in its core weights) consumes it; optional third-party pose control (VACE) or LoRA further compose in as independent modules.
steps: [object Object], [object Object], [object Object]
controls: single reference face image, text prompt, optional driving pose video (VACE), optional LoRA for stylization, denoising-strength adjustment for the experimental face-swap mode
exampleStack: antelopev2 face encoder -> Stand-In adapter + Wan 2.1-14B text-to-video -> VACE pose control (optional)
useCases: [identity-locked talking/acting clips from one photo][face-swap-in-video variants][stylized (cartoon/anime) identity-consistent video via community LoRA composition]
pitfalls: trained only on real-person data, so cartoon/object generalization is a secondary, less-tested mode; combining pose control (VACE) with identity locking simultaneously can still trade off motion naturalness against strict facial consistency
source: Stand-In: A Lightweight and Plug-and-Play Identity Control for Video Generation (arXiv:2508.07901)

Provenance

Source: https://github.com/WeChatCV/Stand-In

Properties

family

character-consistency

modality

single face photo + text (+ optional pose video / style LoRA) -> identity-locked video

whyMultiModel

Identity extraction and video synthesis are handled by two separate networks: a dedicated face-recognition encoder produces the identity embedding, and a large pretrained video DiT (untouched in its core weights) consumes it; optional third-party pose control (VACE) or LoRA further compose in as independent modules.

steps

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

controls

single reference face image, text prompt, optional driving pose video (VACE), optional LoRA for stylization, denoising-strength adjustment for the experimental face-swap mode

exampleStack

antelopev2 face encoder -> Stand-In adapter + Wan 2.1-14B text-to-video -> VACE pose control (optional)

useCases

[identity-locked talking/acting clips from one photo][face-swap-in-video variants][stylized (cartoon/anime) identity-consistent video via community LoRA composition]

pitfalls

trained only on real-person data, so cartoon/object generalization is a secondary, less-tested mode; combining pose control (VACE) with identity locking simultaneously can still trade off motion naturalness against strict facial consistency

source

Stand-In: A Lightweight and Plug-and-Play Identity Control for Video Generation (arXiv:2508.07901)