---
license: apache-2.0
tags:
- image-tokenizer
- autoencoder
- latent-diffusion
- imagenet
datasets:
- ILSVRC/imagenet-1k
---

# InterpTok

Weights of **Image Tokenizers Should Be Trained Between Images**, by Ole Beißwenger, Jan-Niklas Dihlmann and Hendrik Lensch, University of Tübingen.

[📄 Paper](https://arxiv.org/abs/2610.16759)  |  [💻 Code](https://github.com/cgtuebingen/InterpTok)  |  [🌐 Project Page](https://graphics.cs.uni-tuebingen.de/papers/interptok/)

InterpTok fine-tunes the image tokenizer [MAETok](https://huggingface.co/MAETok/maetok-b-128) to decode mixtures of the codes of two images into natural images.
On ImageNet at 256 × 256, it keeps MAETok's reconstruction quality and lowers its interpolation FID from 14.42 to 4.30.
A SiT-B trained on its codes improves its generation FID without guidance from 11.61 to 8.48.

| File | Model |
|---|---|
| `interptok_41k.safetensors` | InterpTok, the model of the paper, 41,000 steps |
| `interptok_82k.safetensors` | InterpTok trained further, to 82,000 steps |
| `interptok_decoder_41k.safetensors` | InterpTok's decoder on MAETok's frozen encoder, which decodes MAETok's codes and the samples of generators trained on them |
| `sit-b_interptok-41k/` | SiT-B trained for 400,000 steps on the codes of `interptok_41k` |
| `sit-b_maetok/` | SiT-B trained for 400,000 steps on MAETok's codes, the baseline of the paper |

Each tokenizer holds 217M parameters in float32, MAETok-B-128's encoder and a decoder of 18 blocks, and encodes a 256 × 256 image into a code of 128 tokens with 32 values each.
Each SiT-B folder is an experiment of the code of [Xu et al.](https://github.com/tongdaxu/Making-rFID-Predictive-of-Diffusion-gFID): `args.json`, the moving average of the weights in `checkpoints/0400000.pt`, and the configuration of its tokenizer.
`SHA256SUMS.txt` lists the checksum of every file.

## Usage

```bash
git clone --recursive https://github.com/cgtuebingen/InterpTok
hf download CGTuebingen/InterpTok-Models --local-dir InterpTok/weights
cd InterpTok
python src/interpolate.py a.jpg b.jpg --weights weights/interptok_41k.safetensors --out a_to_b.png
```

The [code repository](https://github.com/cgtuebingen/InterpTok) explains installation, training and evaluation.

## Citation

```bibtex
@article{beisswenger2026interptok,
  title   = {Image Tokenizers Should Be Trained Between Images},
  author  = {Bei{\ss}wenger, Ole and Dihlmann, Jan-Niklas and Lensch, Hendrik},
  journal = {arXiv preprint arXiv:2610.16759},
  year    = {2026}
}
```

## License

Apache License 2.0.