Duplicate from CGTuebingen/InterpTok-Models

Co-authored-by: Ole Beißwenger <Obeisswenger@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,58 @@
+---
+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.

SHA256SUMS.txt

@@ -0,0 +1,9 @@
+f5d8f2e28514c3b40eb459aec1e8ce258c78896ca27f0a29ca5e13e2d65382e9 *interptok_41k.safetensors
+c7c328edf7ba9fe78817b3e6fe385c3453d0821de4987072e5568ff4c620c2ad *interptok_82k.safetensors
+b6c9cf981823dab73bdc207ef3d1404da6caee04ae5e3dc6efd1c95ab089a4ee *interptok_decoder_41k.safetensors
+23d486a56b2d93edc2d9484f9045433afa67d03be216ecde91d8a09c1647d368 *sit-b_interptok-41k/args.json
+d5426a307d26324dd281369190f6e3df2153b9d1c6e849d4db3fb8c413df52fa *sit-b_interptok-41k/checkpoints/0400000.pt
+0e3d4cc3ea59a3f13ec43fbe192ac019ba802c70bddf7747f603d2f501e66900 *sit-b_interptok-41k/interptok_41k.yaml
+9c36a8917d781357f73734587ec0edad228f1e52d1e021ef0d4eb303a3d77369 *sit-b_maetok/args.json
+6840a53617484036458ddb5ac3306bba92cd0a51ad13231fa08c0aba63fc1ddd *sit-b_maetok/checkpoints/0400000.pt
+d0b9830d165a7ea0c17cbfd7d5a94c6704b2f5cb8a4ae7185d2819d8ab0c1666 *sit-b_maetok/maetok.yaml

interptok_41k.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5d8f2e28514c3b40eb459aec1e8ce258c78896ca27f0a29ca5e13e2d65382e9
+size 868094680

interptok_82k.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7c328edf7ba9fe78817b3e6fe385c3453d0821de4987072e5568ff4c620c2ad
+size 868094680

interptok_decoder_41k.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6c9cf981823dab73bdc207ef3d1404da6caee04ae5e3dc6efd1c95ab089a4ee
+size 868094680

sit-b_interptok-41k/args.json

@@ -0,0 +1,45 @@
+{
+    "output_dir": "exps",
+    "exp_name": "sit-b_interptok-41k",
+    "logging_dir": "logs",
+    "report_to": null,
+    "sampling_steps": 10000,
+    "resume_step": 0,
+    "continue_train_exp_dir": null,
+    "wandb_history_path": null,
+    "model": "SiT-B/1D",
+    "num_classes": 1000,
+    "qk_norm": false,
+    "fused_attn": true,
+    "bn_momentum": 0.1,
+    "compile": false,
+    "data_dir": null,
+    "resolution": 256,
+    "batch_size": 256,
+    "allow_tf32": true,
+    "ploss": false,
+    "mixed_precision": "no",
+    "epochs": 1400,
+    "max_train_steps": 400000,
+    "checkpointing_steps": 50000,
+    "gradient_accumulation_steps": 1,
+    "learning_rate": 0.0001,
+    "adam_beta1": 0.9,
+    "adam_beta2": 0.999,
+    "adam_weight_decay": 0.0,
+    "adam_epsilon": 1e-08,
+    "max_grad_norm": 1000000000.0,
+    "max_grad_norm_vae": 1.0,
+    "seed": 0,
+    "num_workers": 4,
+    "path_type": "linear",
+    "prediction": "v",
+    "prediction_internal": "v",
+    "cfg_prob": 0.1,
+    "weighting": "uniform",
+    "vae_config": "sit-b_interptok-41k/interptok_41k.yaml",
+    "token_drop": -1,
+    "token_drop_mode": "drop",
+    "token_drop_param": 1.0,
+    "token_drop_dim": 1
+}

sit-b_interptok-41k/checkpoints/0400000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5426a307d26324dd281369190f6e3df2153b9d1c6e849d4db3fb8c413df52fa
+size 553237336

sit-b_interptok-41k/interptok_41k.yaml

@@ -0,0 +1,3 @@
+target: model.Tokenizer
+params:
+  weights: interptok_41k.safetensors

sit-b_maetok/args.json

@@ -0,0 +1,45 @@
+{
+    "output_dir": "exps",
+    "exp_name": "sit-b_maetok",
+    "logging_dir": "logs",
+    "report_to": null,
+    "sampling_steps": 10000,
+    "resume_step": 0,
+    "continue_train_exp_dir": null,
+    "wandb_history_path": null,
+    "model": "SiT-B/1D",
+    "num_classes": 1000,
+    "qk_norm": false,
+    "fused_attn": true,
+    "bn_momentum": 0.1,
+    "compile": false,
+    "data_dir": null,
+    "resolution": 256,
+    "batch_size": 256,
+    "allow_tf32": true,
+    "ploss": false,
+    "mixed_precision": "no",
+    "epochs": 1400,
+    "max_train_steps": 400000,
+    "checkpointing_steps": 50000,
+    "gradient_accumulation_steps": 1,
+    "learning_rate": 0.0001,
+    "adam_beta1": 0.9,
+    "adam_beta2": 0.999,
+    "adam_weight_decay": 0.0,
+    "adam_epsilon": 1e-08,
+    "max_grad_norm": 1000000000.0,
+    "max_grad_norm_vae": 1.0,
+    "seed": 0,
+    "num_workers": 4,
+    "path_type": "linear",
+    "prediction": "v",
+    "prediction_internal": "v",
+    "cfg_prob": 0.1,
+    "weighting": "uniform",
+    "vae_config": "sit-b_maetok/maetok.yaml",
+    "token_drop": -1,
+    "token_drop_mode": "drop",
+    "token_drop_param": 1.0,
+    "token_drop_dim": 1
+}

sit-b_maetok/checkpoints/0400000.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6840a53617484036458ddb5ac3306bba92cd0a51ad13231fa08c0aba63fc1ddd
+size 553237336

sit-b_maetok/maetok.yaml

@@ -0,0 +1 @@
+target: model.Tokenizer