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

Haotian Dong; Xin Wang; Wenjing Wang; Chen Li; Jing Lyu; Yan Tina Luximon; Ping Li; Wanchao Su

cs.CVOct 19, 2026

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

Authors: Haotian Dong, Xin Wang, Wenjing Wang, Chen Li, Jing Lyu, Yan Tina Luximon, Ping Li, Wanchao Su,

Organizations: College of Intelligence and Computing, Tianjin University, China. · Laboratory for Artificial Intelligence in Design Limited (AiDLab), The Hong Kong Polytechnic University, Hong Kong. · independent researcher. · School of Design, The Hong Kong Polytechnic University, Hong Kong. ·

Abstract

RGBA video generation is essential for creating compositable visual assets in filmmaking, game development, and digital content production. However, generating high-quality RGB appearance alongside temporally coherent transparency remains a significant challenge. Existing text-to-RGBA video methods often entangle RGB and alpha distributions and offer limited control over the precise appearance of a target asset. In addition, incorporating image conditioning typically suffers from the emergence-disappearance effects, which fail existing first-frame or first-and-last-frame conditions due to their fully transparent boundary frames. To address these issues, we present Wan-Alpha++, a unified framework that brings controllable RGBA video generation to both text- and image-to-video diffusion backbones through a shared RGBA latent space, extending our conference version Wan-Alpha from the text-conditioned setting to image-conditioned generation with an interior reference frame. Our method first learns shiftable RGB-alpha distributions while preserving the pretrained RGB prior. Specifically, we introduce a transparency-aware bidirectional diffusion objective to produce distinguishable RGBA latent representations, and a transparency-guided mean sampler that shifts the noise distribution to improve transparency generation and enable spatial controllability. Building upon this RGBA generation prior, we introduce temporal phase reparameterization for image-conditioned effect generation. By cyclically transforming a zero-positive-zero alpha pattern into a positive-zero-positive pattern, it relocates visible content to both temporal boundaries, facilitating effective appearance conditioning with limited RGBA data.

Figures & tables

Fig. 1: Training framework of our RGBA VAE. The RGB and alpha channels are encoded separately and fused into a shared latent representation. The transparency-aware bidirectional diffusion objective preserves the pretrained RGB distribution while shifting alpha-related representations. Rendering-based reconstruction objectives further supervise RGB appearance and alpha transparency.

Fig. 2: Training framework of our RGBA video generator. The pretrained RGBA VAE encodes the input video into the shared latent space. Transparency-guided mean sampler provides a transparency prior for DiT adaptation.

Fig. 3: A Gaussian ellipse derived from the alpha channel shifts the noise mean, providing a transparency prior for DiT adaptation. During inference, the mask can be specified by users to control the approximate position and extent of generated content.

Fig. 4: Inference framework of the proposed phase-reparameterized image-to-RGBA video generation. The same input RGBA image conditions both temporal boundaries. Transparent-state guidance applies normalized gradient updates to a user-specified invisible interval. Finally, temporal transformation recovers the desired emergence-disappearance effect.

Fig. 5: Samples from our dataset. Our videos show clear motion and complex edges, such as hair. Each video has short and long captions, plus attribute labels. The dataset also includes various semi‑transparent effects like sheer fabric, smoke, water, and glow.

Fig. 6: The detailed architecture for the feature merging block. RGB and alpha features are concatenated and fused by a causal 3D convolution. Then, we use several causal residual blocks and attention layers. Finally, a causal 3D convolution generates the merged latent $Z$ .

Fig. 7: Qualitative comparison with existing text-to-RGBA video generation methods. Our method produces more realistic RGB content, finer alpha boundaries, and more accurate transparency for challenging objects and semi-transparent effects. Please refer to the supplementary material for video results.

Method	Text Alignment $\uparrow$	Aesthetic Quality $\uparrow$	Naturalness $\uparrow$	Motion Smoothness $\uparrow$	Temporal Flickering $\uparrow$
LayerFlow (Single) [ 30 ]	2.67	0.535	2.35	0.9837	0.9788
LayerDiffuse [ 5 ] + AnimateDiff [ 6 ]	3.15	0.617	3.03	0.9893	0.9853
TransPixeler (Open) [ 7 ]	3.16	0.570	2.97	0.9821	0.9872
TransPixeler (Close) [ 7 ]	3.45	0.573	3.07	0.9907	0.9822
Ours	4.00	0.649	3.19	0.9949	0.9941

TABLE I: Quantitative comparison with existing text-to-RGBA video generation methods. Our Wan-Alpha consistently achieves superior video generation performance across all five evaluation metrics.

Method	Transparency $\downarrow$	Overall $\downarrow$
LayerFlow (Single) [ 30 ]	4.29	3.57
LayerDiffuse [ 5 ] + AnimateDiff [ 6 ]	3.40	4.23
TransPixeler (Open) [ 7 ]	2.51	2.71
TransPixeler (Close) [ 7 ]	2.57	3.37
Ours	1.23	1.11

TABLE II: User ranking for text-to-RGBA generation. Lower transparency and overall indicate better performance.

Fig. 8: Qualitative comparison with the two-stage Wan + MatAnyone pipeline. Despite using a white-background prompt and a user-provided initial mask, the matting pipeline leaves residual background content and struggles with semi-transparent effects. Our end-to-end RGBA generation model produces cleaner alpha channels and more accurate transparency.

Method			RGB-A VAE								Text-to-Video Generation
VAE		T2V	PSNR $\uparrow$		SSIM $\uparrow$		LPIPS $\downarrow$		Dist		Text Alignment $\uparrow$	Aesthetic Quality $\uparrow$	Naturalness $\uparrow$	Motion Smoothness $\uparrow$	Temporal Flickering $\uparrow$
Rendering	TABD	MS	RGB	$\alpha$	RGB	$\alpha$	RGB	$\alpha$	RGB $\downarrow$	$\alpha$ $\uparrow$	Text Alignment $\uparrow$	Aesthetic Quality $\uparrow$	Naturalness $\uparrow$	Motion Smoothness $\uparrow$	Temporal Flickering $\uparrow$
			40.12	39.98	0.97	0.97	0.043	0.025	0.985	3.56	3.67	0.616	3.17	0.990	0.987
✓			40.88	41.22	0.97	0.98	0.040	0.023	1.015	4.10	3.77	0.619	3.17	0.992	0.984
✓	✓		41.47	42.22	0.97	0.98	0.037	0.022	0.857	4.29	3.86	0.621	3.19	0.992	0.990
✓	✓	✓	41.47	42.22	0.97	0.98	0.037	0.022	0.857	4.29	4.00	0.649	3.19	0.995	0.994

TABLE III: Ablation study on RGB-A video reconstruction and generation performance. Our full model achieves the best performance across all metrics, demonstrating the effectiveness of the proposed framework design.

Fig. 9: Qualitative ablation of the text-to-RGBA generation framework. TABD improves RGB–alpha separation, while MS facilitates clean transparent backgrounds.

Fig. 10: Effect of the mean-shift strength $\mu$ in the transparency-guided mean sampler.

Fig. 11: Results under different Gaussian ellipse masks $G$ (shown at the bottom right). Users can use $G$ to control the shape and position of transparent regions.

Fig. 12: Qualitative comparison with the two-stage Wan2.1-I2V + MatAnyone pipeline. Despite using a white-background prompt and a user-provided initial mask, the matting pipeline leaves residual background content and struggles with semi-transparent effects. Our end-to-end RGBA generation model produces cleaner alpha channels and more accurate transparency.

Fig. 13: Qualitative comparison with the two-stage Wan2.1-FLF2V + MatAnyone pipeline under different matting initialization positions. With First initialization, MatAnyone extracts the visible first frame, but fails to produce the emergence-disappearance RGBA effect. The RGB generator also fails to preserve fine appearance details such as text. With Middle initialization, MatAnyone only processes the frames following the condition frame and discards the first half of the video. Moreover, it continues to propagate an object-shaped alpha artifact even after the RGB content has disappeared. In contrast, our method conditions on a user-specified visible frame and generates a complete RGBA effect that gradually emerges and then disappears with clean transparent states.

Method		DINO-I $\uparrow$	CLIP-I $\uparrow$	Aesthetic Quality $\uparrow$	Motion Smoothness $\uparrow$	Temporal Flickering $\uparrow$
Normal	Wan2.1-I2V + MatAnyone [ 61 ]	0.9033	0.9089	0.6296	0.9912	0.9858
Normal	Ours	0.9066	0.9445	0.6305	0.9916	0.9864
Effect	Wan2.1-FLF2V + MatAnyone [ 61 ]	0.6679	0.7969	0.5749	0.9917	0.9926
Effect	Ours	0.9227	0.9368	0.5968	0.9941	0.9930

TABLE IV: Quantitative comparison on normal and effect image-to-RGBA video generation. DINO-I and CLIP-I measure reference fidelity, while the remaining metrics evaluate general video quality.

Method		Temporal Effect $\downarrow$	Overall $\downarrow$
Normal	Wan2.1-I2V + MatAnyone	1.73	1.62
Normal	Ours	1.27	1.38
Effect	Wan2.1-FLF2V + MatAnyone	1.88	1.84
Effect	Ours	1.12	1.16

TABLE V: User ranking for image-to-RGBA generation.

Reparameterization	Guidance	DINO-I $\uparrow$	CLIP-I $\uparrow$	Aesthetic Quality $\uparrow$	Motion Smoothness $\uparrow$	Temporal Flickering $\uparrow$	Temporal Effect $\downarrow$
		0.6315	0.7542	0.5793	0.9919	0.9918	2.76
✓		0.9136	0.9275	0.5924	0.9936	0.9927	2.09
✓	✓	0.9227	0.9368	0.5968	0.9941	0.9930	1.12

TABLE VI: Component ablation of temporal phase reparameterization ( Reparameterization ) and transparent-state guidance ( Guidance ). We report reference fidelity, general video quality, and the user ranking for temporal-effect correctness. Lower is better for Temporal Effect, while higher is better for all other metrics.

Parameter	Value	DINO-I $\uparrow$	CLIP-I $\uparrow$	Aesthetic Quality $\uparrow$	Motion Smoothness $\uparrow$	Temporal Flickering $\uparrow$
Step size $\eta_{s}$	10	0.9208	0.9335	0.5908	0.9935	0.9925
	25	0.9220	0.9352	0.5947	0.9939	0.9928
	50	0.9227	0.9368	0.5968	0.9941	0.9930
	75	0.9188	0.9310	0.5921	0.9934	0.9924
Guided sampling steps	16	0.9235	0.9372	0.5905	0.9934	0.9924
	24	0.9230	0.9369	0.5943	0.9938	0.9927

TABLE VII: Sensitivity to transparent-state guidance hyperparameters.

Controllable Video Generation

Controllable video generation steers how videos look, move, and change over time using user-provided instructions and structured controls.

See all 321 papers

Alpha as an Efficiency Signal: Visibility-Routed RGBA Image-to-Video Generation
Aug 10, 2026Zhe Li, Honghao Qiao, Zhixin Xu +3Image-to-Video Generation Diffusion Model Acceleration
Peking University · ByteDance · Tsinghua University
AlphaAnything: Extending Pretrained RGB Generators to RGBA
Oct 23, 2026Qijie Wang, Zhixin Xu, Zhe Li +5Image Generation T2I Diffusion Models
Tsinghua University · ByteDance · Peking University
TransText: Alpha-as-RGB Representation for Transparent Text Animation
Mar 18, 2026Fei Zhang, Zijian Zhou, Bohao Tang +9Image-to-Video Generation Video Diffusion Models
Shanghai Jiao Tong University · Shanghai Innovation Institute (SII) · Meta AI

Aug 10, 2026J/K move · Enter open · S save

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

Zhe Li, Honghao Qiao, Zhixin Xu, Qijie Wang+2

Peking University · ByteDance · Tsinghua University

Image-to-Video Generation Diffusion Model Acceleration

Open paper AskPDF arXiv

RGBA videos combine RGB appearance with an alpha channel, enabling animated assets to be applied across arbitrary backgrounds, which are heavily used in gaming industry. However, generating high-quality RGBA animations for games remains challenging for two reasons. First, most existing RGBA video datasets are dominated by photorealistic content, with limited coverage of game assets. Second, the traditional generate-then-matte pipelines estimate alpha only after RGB synthesis, so semi-transparent regions are often blurred by background, resulting in unstable matting outputs. More recently, many methods have begun to model RGB and alpha jointly, but existing approaches are mostly text-conditioned, and still have unresolved issues in efficiency and quality. To address these challenges, we introduce GameAlpha-2.4K, a 2.4K-clip game-style RGBA video dataset built with matte-friendly synthesis, multi-hypothesis alpha recovery, and compositing-based quality gates. Using this dataset, we train a reference-conditioned RGBA video generator that jointly produces RGB frames and alpha mattes in a single pass. To improve efficiency, we propose a visibility router that identifies transparent tokens in an early stage and bypasses their later DiT updates, while x_0-lock guides them along the original flow-matching schedule toward self-predicted endpoints. Our model obtains lower FVD than traditional two-stage pipelines, and the visibility router skips 35% of token evaluations in the final two DiT denoising steps, providing a 1.2x backbone speedup with negligible quality degradation compared to dense inference.

Abstract

Controllable Video Generation

Explore similar work

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

AlphaAnything: Extending Pretrained RGB Generators to RGBA

TransText: Alpha-as-RGB Representation for Transparent Text Animation