Toward Diffusible High-Dimensional Latent Spaces: A Frequency Perspective
By: Bolin Lai , Xudong Wang , Saketh Rambhatla and more
Potential Business Impact:
Makes AI image makers create sharper, more detailed pictures.
Latent diffusion has become the default paradigm for visual generation, yet we observe a persistent reconstruction-generation trade-off as latent dimensionality increases: higher-capacity autoencoders improve reconstruction fidelity but generation quality eventually declines. We trace this gap to the different behaviors in high-frequency encoding and decoding. Through controlled perturbations in both RGB and latent domains, we analyze encoder/decoder behaviors and find that decoders depend strongly on high-frequency latent components to recover details, whereas encoders under-represent high-frequency contents, yielding insufficient exposure and underfitting in high-frequency bands for diffusion model training. To address this issue, we introduce FreqWarm, a plug-and-play frequency warm-up curriculum that increases early-stage exposure to high-frequency latent signals during diffusion or flow-matching training -- without modifying or retraining the autoencoder. Applied across several high-dimensional autoencoders, FreqWarm consistently improves generation quality: decreasing gFID by 14.11 on Wan2.2-VAE, 6.13 on LTX-VAE, and 4.42 on DC-AE-f32, while remaining architecture-agnostic and compatible with diverse backbones. Our study shows that explicitly managing frequency exposure can successfully turn high-dimensional latent spaces into more diffusible targets.
Similar Papers
Latent Diffusion Inversion Requires Understanding the Latent Space
Machine Learning (CS)
Finds hidden personal data in AI art.
Missing Fine Details in Images: Last Seen in High Frequencies
CV and Pattern Recognition
Makes computer pictures look more real.
Diffusion Transformers with Representation Autoencoders
CV and Pattern Recognition
Makes AI create better, clearer pictures faster.