RobusTok

--- pipeline_tag: unconditional-image-generation --- # Image Tokenizer Needs Post-Training This repository contains **RobusTok**, a novel image tokenizer presented in the paper [Image Tokenizer Needs Post-Training](https://huggingface.co/papers/2509.12474). <div align="center"> [](https://qiuk2.github.io/works/RobusTok/index.html)&nbsp; [](https://github.com/qiuk2/RobusTok)&nbsp; [](https://huggingface.co/qiuk6/RobusTok)&nbsp; </div> <div align="center"> <img src="https://github.com/qiuk2/RobusTok/raw/main/assets/teaser.png" alt="Teaser" width="95%"> </div> --- ## About RobusTok Recent image generative models typically rely on a frozen image tokenizer to capture the image distribution in a latent space. However, a significant discrepancy exists between the reconstruction and generation distribution, as current tokenizers often prioritize the reconstruction task without fully considering generation errors during sampling. **RobusTok** addresses this by proposing a novel tokenizer training scheme that includes both main-training and post-training: * **Main training:** Constructs a robust latent space by simulating sampling noises and unexpected tokens. * **Post-training:** Further optimizes the tokenizer decoder with respect to a well-trained generative model, mitigating the distribution difference between generated and reconstructed tokens. This approach significantly enhances the robustness of the tokenizer, boosting generation quality and convergence speed. ## Key Highlights of Post-Training - 🚀 **Better generative quality**: Achieves notable improvements in gFID (e.g., 1.60 gFID → 1.36 gFID with a ~400M generator). - 🔑 **Generalizability**: Applicable to both autoregressive & diffusion models. - ⚡ **Efficiency**: Provides strong results with relatively small generative models. ## Model Zoo | Generator \ Tokenizer | RobusTok w/o. P.T | RobusTok w/. P.T | |---|---:|---:| | Base ([weights](https://huggingface.co/qiuk6/RobusTok/resolve/main/rar_b.bin?download=true)) | gFID = 1.83 | gFID = 1.60 | | Large ([weights](https://huggingface.co/qiuk6/RobusTok/resolve/main/rar_l.bin?download=true)) | gFID = 1.60 | gFID = 1.36 | ## U...

Source context: 0 downloads · 1 likes · Pipeline unconditional-image-generation · Repo qiuk6/RobusTok