cs.CVMar 18, 2026

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

Authors: Fei Zhang, Zijian Zhou, Bohao Tang, Sen He, Hang Li, Zhe Wang, Soubhik Sanyal, Pengfei Liu, 

Organizations: Shanghai Jiao Tong University · Shanghai Innovation Institute (SII) · Meta AI

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

We introduce the first method, to the best of our knowledge, for adapting image-to-video models to layer-aware text (glyph) animation, a capability critical for practical dynamic visual design. Existing approaches predominantly handle the transparency-encoding (alpha channel) as an extra latent dimension appended to the RGB space, necessitating the reconstruction of the underlying RGB-centric variational autoencoder (VAE). However, given the scarcity of high-quality transparent glyph data, retraining the VAE is computationally expensive and may erode the robust semantic priors learned from massive RGB corpora, potentially leading to latent pattern mixing. To mitigate these limitations, we propose TransText, a framework based on a novel Alpha-as-RGB paradigm to jointly model appearance and transparency without modifying the pre-trained generative manifold. TransText embeds the alpha channel as an RGB-compatible visual signal through latent spatial concatenation, explicitly ensuring strict cross-modal (RGB-and-Alpha) consistency while preventing feature entanglement. Our experiments demonstrate that TransText significantly outperforms baselines, generating coherent, high-fidelity transparent animations with diverse, fine-grained effects.

Figures & tables

Figure 1: Visual frame-wise results of our image-to-video (I2V) RGBA glyph animation model. TransText generates diverse and complex glyph animations with accurate, clean transparency while strictly preserving the style of the reference image. See the Supplementary Materials for additional video results.
Figure 2: Overview of the TransText pipeline . We obtain input latents by encoding the RGB video and the RGB-projected Alpha video ( Alpha-as-RGB ) via the VAE. These latents are spatially concatenated for alignment. Additionally, the reference image and its derived trimap serve as structural conditions to guide the joint generation of both RGB textures and α\alpha mattes. During training, in addition to the standard velocity prediction loss Lmse\mathcal{L}_{\mathrm{mse}} , we introduce an α\alpha -oriented reconstruction term Lrec\mathcal{L}_{\mathrm{rec}} . Reconstruction loss performs one-step denoising using the predicted velocity to reconstruct the clean latent state, and explicitly aligns the reconstructed α\alpha with the ground-truth matte, thereby significantly improving fine-grained transparency generation.
Figure 3: Comparison with various I2V generalist models on our text animation dataset. Each example shows the high-fidelity, motion-consistent RGB video (top row) and the corresponding transparent video (bottom row) generated by TransText . Zoom in for better details.
MethodGeneration Metric Alignment & Quality Score Time Efficiency
FVD ↓\downarrowSoft α\alpha -mIoU ↑\uparrow RGBA Alignment (%) ↑\uparrowMotion Quality † ↑\uparrow Training ↓\downarrowInference ↓\downarrow
Wan * + ConText Zhang et al. (2025a)480.9257.24 13.5129.55 53.447.92
Transpixeler * Wang et al. (2025)673.1143.76 83.0164.52 72.3111.25
TransText123.4879.90 87.3175.94 69.7210.11
Table 1: Comparison with existing RGBA-based methods on our validation set. TransText outperforms all baselines in generation quality with promising efficiency. * Fine-tuned on our training data. † Scores derived from a user study. Bold indicates the best performance, and underlined indicates the second best.
Figure 5
Figure 5: Qualitative results on background compositing. Visual effects include: Letter Collection , Flickering Green , Snow Falls , and Small Squares .
Figure 6: Qualitative results on background compositing. Visual effects include: Dark Fire , From the Sand , Lightning Strikes , and Blue Lights .
Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

IDEffectTrainVal
1From the sand2,515137
2Flickering Green2,471127
3Letters Collected2,318117
4Small Squares2,080109
5Lightning Strikes1,99299
6Snow Falls1,56186
Appendix
Table 1: Distribution of 8 visual effects in the dataset. Below shows the sample counts for training (Train) and validation (Val) splits.
Figure 1: Visualization of original samples from our glyph animation dataset, with one example shown for each visual effect. The reference image (the column marked in blue) corresponds to the middle frame of each video clip. Please zoom in for a better view.
Figure 10
More in this topic

Image-to-Video Generation

Image-to-video generation creates coherent moving clips from still images, guided by learned models and controls such as motion, camera, or text.

See all 95 papers

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

    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. +3

  2. AlphaAnything: Extending Pretrained RGB Generators to RGBA

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

    Tsinghua University · ByteDance · Peking University

  3. 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

    Peking University · ByteDance · Tsinghua University