cs.CVNov 6, 2026

UniRGBA: Unifying RGB and Alpha in Pretrained Video Diffusion Models

Authors: Lei Xu, Zhuo Li, Yongyi Jin, Aoyu Wang

Organizations: ByteDance

Abstract

Recent advances in video diffusion models have achieved remarkable photorealistic RGB synthesis, yet generating videos with a native alpha channel remains an open challenge. Existing approaches often rely on matting-style data and non-native RGBA designs, causing them to specialize in real-object scenes and to degrade severely on visual-effect content whose semi-transparency is spatially non-local and non-elliptical. We present UniRGBA, a unified framework whose key insight is that RGBA generation does not require a dedicated alpha encoder or complex latent-space restructuring---a minimal, targeted extension of the existing RGB pathway is sufficient. UniRGBA-VAE extends a causal video VAE to 4-channel RGBA via zero-initialized channel expansion, symmetric selective layer unfreezing (5% trainable), and a six-term progressive reconstruction loss anchored by a KL reference loss that prevents latent drift, followed by a two-stage schedule that introduces a lightweight GAN objective. We then apply standard DoRA to the pretrained DiT, reusing the unified 4-channel latent without any alpha-specific architectural changes. On a visual-effect RGBA benchmark, UniRGBA substantially outperforms Wan-Alpha on RGBA reconstruction while preserving RGB fidelity. For generation, UniRGBA outperforms Wan-Alpha on RGBA text-to-video tasks and matches or surpasses the original pretrained Wan2.1 backbone on RGB-only metrics, demonstrating that native alpha support can be integrated without compromising the underlying RGB prior or the model's architectural versatility.

Figures & tables

Appendix figures & tables6 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Wan-Alpha++: Animating a Single RGBA Asset into Controllable Transparent Video Effects

    Oct 19, 2026Haotian Dong, Xin Wang, Wenjing Wang +7Controllable Video GenerationVideo Diffusion Models

  2. Alpha as an Efficiency Signal: Visibility-Routed RGBA Image-to-Video Generation

    Aug 10, 2026Zhe Li, Honghao Qiao, Zhixin Xu +3Image-to-Video GenerationDiffusion Model Acceleration

  3. AlphaAnything: Extending Pretrained RGB Generators to RGBA

    Oct 23, 2026Qijie Wang, Zhixin Xu, Zhe Li +5Image GenerationT2I Diffusion Models