Initial commit

.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 +1,52 @@
+---
+license: apple-amlr
+---
+
+# FlexTok: Resampling Images into 1D Token Sequences of Flexible Length
+
+[`Website`](https://flextok.epfl.ch) | [`arXiv`](https://arxiv.org/abs/2502.13967) | [`GitHub`](https://github.com/apple/ml-flextok) | [`🤗 Demo`](https://huggingface.co/spaces/EPFL-VILAB/FlexTok) | [`BibTeX`](#citation)
+
+Official implementation and pre-trained models for: <br>
+[**FlexTok: Resampling Images into 1D Token Sequences of Flexible Length**](https://arxiv.org/abs/2502.13967), arXiv 2025 <br>
+*[Roman Bachmann](https://roman-bachmann.github.io/)\*, [Jesse Allardice](https://github.com/JesseAllardice)\*, [David Mizrahi](https://dmizrahi.com/)\*, [Enrico Fini](https://scholar.google.com/citations?user=OQMtSKIAAAAJ), [Oğuzhan Fatih Kar](https://ofkar.github.io/), [Elmira Amirloo](https://elamirloo.github.io/), [Alaaeldin El-Nouby](https://aelnouby.github.io/), [Amir Zamir](https://vilab.epfl.ch/zamir/), [Afshin Dehghan](https://scholar.google.com/citations?user=wcX-UW4AAAAJ)*
+
+
+## Installation
+For install instructions, please see https://github.com/apple/ml-flextok. 
+
+
+## Usage
+
+To load the 8-channel VAE-GAN directly from HuggingFace Hub and autoencode a sample image, call:
+```python
+from diffusers.models import AutoencoderKL
+from flextok.utils.demo import imgs_from_urls
+
+vae = AutoencoderKL.from_pretrained(
+    'EPFL-VILAB/flextok_vae_c8', low_cpu_mem_usage=False
+).eval()
+
+# Load example images of shape (B, 3, H, W), normalized to [-1,1]
+imgs = imgs_from_urls(urls=['https://storage.googleapis.com/flextok_site/nb_demo_images/0.png'])
+
+# Autoencode with the VAE
+latents = vae.encode(imgs).latent_dist.sample() # Shape (B, 8, H//8, W//8)
+reconst = vae.decode(latents).sample # Shape (B, 3, H, W)
+```
+
+
+## Citation
+
+If you find this repository helpful, please consider citing our work:
+```
+@article{flextok,
+    title={{FlexTok}: Resampling Images into 1D Token Sequences of Flexible Length},
+    author={Roman Bachmann and Jesse Allardice and David Mizrahi and Enrico Fini and O{\u{g}}uzhan Fatih Kar and Elmira Amirloo and Alaaeldin El-Nouby and Amir Zamir and Afshin Dehghan},
+    journal={arXiv 2025},
+    year={2025},
+}
+```
+
+## License
+
+The model weights in this repository are released under the Apple Model License for Research.

config.json

@@ -0,0 +1,31 @@
+{
+    "_class_name": "AutoencoderKL",
+    "_diffusers_version": "0.18.0.dev0",
+    "_name_or_path": ".",
+    "act_fn": "silu",
+    "block_out_channels": [
+        128,
+        256,
+        512,
+        512
+    ],
+    "down_block_types": [
+        "DownEncoderBlock2D",
+        "DownEncoderBlock2D",
+        "DownEncoderBlock2D",
+        "DownEncoderBlock2D"
+    ],
+    "in_channels": 3,
+    "latent_channels": 8,
+    "layers_per_block": 2,
+    "norm_num_groups": 32,
+    "out_channels": 3,
+    "sample_size": 1024,
+    "scaling_factor": 0.65,
+    "up_block_types": [
+        "UpDecoderBlock2D",
+        "UpDecoderBlock2D",
+        "UpDecoderBlock2D",
+        "UpDecoderBlock2D"
+    ]
+}

diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab5f7b81b6c8363ee38da10763e0a8d24af1e95a9900d0d138641bf664aaca55
+size 334865924