Model card and the original license

LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [2023] [Han Cai]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -0,0 +1,234 @@
+---
+license: apache-2.0
+pipeline_tag: mask-generation
+library_name: mlx
+tags:
+- mlx
+- moonbox
+- efficientvit
+- efficientvit-sam
+- segment-anything
+- image-segmentation
+---
+
+# EfficientViT-SAM MLX
+
+MLX builds of [EfficientViT-SAM](https://github.com/mit-han-lab/efficientvit), made by Moonbox for Apple Silicon Macs. Each precision is a folder; keep a folder's
+files together. Only the parts listed below are converted: the rest of the pipeline comes from the original
+repository unless the section below says otherwise.
+
+## Files
+
+The last column is how far each build is from the original PyTorch model on the same inputs (see the section below
+for what was measured).
+
+| Precision | File | Size | sha256 | Checked against the original |
+|---|---|---|---|---|
+| fp16 | [`fp16/config.json`](https://huggingface.co/moonbox-ai/efficientvit-MLX/blob/main/fp16/config.json) | 0.3 kB | `9b286f991620` | below threshold (experimental): mask IoU 0.942 mean / 0.611 worst (float32 port: 0.9996 / 0.997) |
+| fp16 | [`fp16/mlx_model.py`](https://huggingface.co/moonbox-ai/efficientvit-MLX/blob/main/fp16/mlx_model.py) | 25.4 kB | `42cea84fb312` | below threshold (experimental): mask IoU 0.942 mean / 0.611 worst (float32 port: 0.9996 / 0.997) |
+| fp16 | [`fp16/model.safetensors`](https://huggingface.co/moonbox-ai/efficientvit-MLX/blob/main/fp16/model.safetensors) | 122.7 MB | `f4b4b159c9f7` | below threshold (experimental): mask IoU 0.942 mean / 0.611 worst (float32 port: 0.9996 / 0.997) |
+
+## How to run
+
+EfficientViT-SAM **L2** (EfficientViT-L2 image encoder at 512 px + SAM's prompt encoder and mask decoder) ported to
+MLX. Each folder holds `model.safetensors`, `config.json` and `mlx_model.py`, the port (only `mlx`, `numpy` and
+`pillow` needed), with EfficientViTSamPredictor's interface:
+
+```python
+import numpy as np, mlx_model
+from PIL import Image
+model = mlx_model.load("fp16")
+rgb = np.array(Image.open("in.jpg").convert("RGB"))
+emb = mlx_model.embed(model, rgb)
+masks, scores, low_res, logits = mlx_model.predict(model, emb, points=[[320, 240]], labels=[1], multimask=True)
+```
+
+**Both folders are experimental: this model needs float32.** Thirty of its 1x1 convolutions are followed by a
+BatchNorm with a running variance down to 5.5e-7 (scales up to 600): those channels carry their signal in the 4th-5th
+significant digit of the convolution output, which 16-bit weights or arithmetic can't hold. The port itself is exact:
+run in float32 (with `MLX_ENABLE_TF32=0`, else MLX's float32 matmuls use TF32) it matches PyTorch to mask IoU 0.9996.
+There are no 8bit / 6bit / 4bit folders: quantized, the model gives no usable masks.
+
+| Precision | Size | Mask IoU vs PyTorch fp32 (mean / worst) | Status |
+|---|---|---|---|
+| `fp16/` | 122.7 MB | 0.942 / 0.611 | **below threshold (0.95), experimental** |
+| `bf16/` | 122.7 MB | 0.714 / 0.091 | **below threshold, experimental** |
+
+To run in float32, load either folder and cast the parameters up (`model.update(mlx.utils.tree_map(lambda a:
+a.astype(mx.float32), model.parameters()))`): fp16 weights in float32 give 0.966 mean / 0.62 worst, still short of
+the original's float32 weights. About 55 ms per image (encoder + 2 prompts) on an Apple M5.
+
+## How these were made
+
+From [EfficientViT-SAM](https://github.com/mit-han-lab/efficientvit) at revision `de7d7733cc`: the original weights loaded in MLX and stored as bf16 or fp16, or
+quantized with MLX's affine quantization (`8bit`, `6bit`, `4bit`, group size 64; layers MLX can't quantize, such as
+convolutions and norms, stay bf16). Every build was checked against the original before upload; the `sha256` column
+above is what the files must hash to.
+
+## License
+
+apache-2.0. These files are a derivative of the original model and carry its license: it is copied in this
+repository, and it governs your use of these files. The original model card follows unchanged.
+
+---
+
+# Original model card
+
+# Efficient Vision Foundation Models for High-Resolution Generation and Perception
+
+[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/deep-compression-autoencoder-for-efficient/image-generation-on-imagenet-512x512)](https://paperswithcode.com/sota/image-generation-on-imagenet-512x512?p=deep-compression-autoencoder-for-efficient)
+
+## News
+- (🔥 New) [2025/09/05] We will no longer maintain this codebase. All future updates and announcements will be made on [DC-Gen](https://github.com/dc-ai-projects/DC-Gen).
+- (🔥 New) [2025/01/24] We released DC-AE-SANA-1.1: [doc](https://github.com/mit-han-lab/efficientvit/blob/master/assets/docs/dc_ae_sana_1.1.md). 
+- (🔥 New) [2025/01/23] DC-AE and SANA are accepted by ICLR 2025.
+- (🔥 New) [2025/01/14] We released **DC-AE+USiT models**: [model](https://huggingface.co/collections/mit-han-lab/dc-ae-diffusion-670dbb8d6b6914cf24c1a49d), [training](https://github.com/mit-han-lab/efficientvit/blob/master/applications/dc_ae/README.md#dc-ae--usit). Using the default training settings and sampling strategy, DC-AE+USiT-2B achieves 1.72 FID on ImageNet 512x512, surpassing the SOTA diffusion model EDM2-XXL and SOTA auto-regressive image generative models (MAGVIT-v2 and MAR-L).
+
+______________________________________________________________________
+
+- (🔥 New) [2024/12/24] **diffusers** supports DC-AE models. All [DC-AE models in diffusers safetensors](https://huggingface.co/collections/mit-han-lab/dc-ae-670085b9400ad7197bb1009b) are released. [Usage](https://github.com/mit-han-lab/efficientvit/tree/master/applications/dc_ae#deep-compression-autoencoder-diffusers).
+- [2024/10/21] DC-AE and EfficientViT block are used in our latest text-to-image diffusion model SANA! Check the [project page](https://nvlabs.github.io/Sana/) for more details.
+- [2024/10/15] We released **Deep Compression Autoencoder (DC-AE)**: [link](#deep-compression-autoencoder-for-efficient-high-resolution-diffusion-models-paper-readme)!
+- [2024/07/10] EfficientViT is used as the backbone in [Grounding DINO 1.5 Edge](https://arxiv.org/pdf/2405.10300) for efficient open-set object detection.
+- [2024/07/10] EfficientViT-SAM is used in [MedficientSAM](https://github.com/hieplpvip/medficientsam), the 1st place model in [CVPR 2024 Segment Anything In Medical Images On Laptop Challenge](https://www.codabench.org/competitions/1847/).
+- [2024/04/06] EfficientViT-SAM is accepted by [eLVM@CVPR'24](https://sites.google.com/view/elvm/home?authuser=0).
+- [2024/03/19] Online demo of EfficientViT-SAM is available: [https://evitsam.hanlab.ai/](https://evitsam.hanlab.ai/). 
+- [2024/02/07] We released [EfficientViT-SAM](https://arxiv.org/abs/2402.05008), the first accelerated SAM model that matches/outperforms SAM-ViT-H's zero-shot performance, delivering the SOTA performance-efficiency trade-off.
+- [2023/11/20] EfficientViT is available in the [NVIDIA Jetson Generative AI Lab](https://www.jetson-ai-lab.com/tutorial_efficientvit.html).
+- [2023/09/12] EfficientViT is highlighted by [MIT home page](https://www.mit.edu/archive/spotlight/efficient-computer-vision/) and [MIT News](https://news.mit.edu/2023/ai-model-high-resolution-computer-vision-0912).
+- [2023/07/18] EfficientViT is accepted by ICCV 2023.
+
+## Content
+
+### [ICLR 2025] Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models [[paper](https://arxiv.org/abs/2410.10733)] [[readme](applications/dc_ae/README.md)] [[poster](assets/dc_ae_poster.pdf)]
+
+**Deep Compression Autoencoder (DC-AE) is a new family of high-spatial compression autoencoders with a spatial compression ratio of up to 128 while maintaining reconstruction quality. It accelerates all latent diffusion models regardless of the diffusion model architecture.**
+
+#### Demo
+
+![demo](https://huggingface.co/mit-han-lab/dc-ae-f64c128-in-1.0/resolve/main/assets/dc_ae_demo.gif)
+<p align="center">
+<b> Figure 1: We address the reconstruction accuracy drop of high spatial-compression autoencoders.
+</p>
+
+![demo](assets/dc_ae_diffusion_demo.gif)
+<p align="center">
+<b> Figure 2: DC-AE speeds up latent diffusion models.
+</p>
+
+<p align="center">
+<img src="https://huggingface.co/mit-han-lab/dc-ae-f64c128-in-1.0/resolve/main/assets/dc_ae_sana.jpg"  width="1200">
+</p>
+
+<p align="center">
+<b> Figure 3: DC-AE enables efficient text-to-image generation on the laptop: <a href="https://nvlabs.github.io/Sana/">SANA</a>.
+</p>
+
+- [Usage of Deep Compression Autoencoder](applications/dc_ae/README.md#deep-compression-autoencoder)
+- [Usage of DC-AE-Diffusion](applications/dc_ae/README.md#efficient-diffusion-models-with-dc-ae)
+- [Evaluate Deep Compression Autoencoder](applications/dc_ae/README.md#evaluate-deep-compression-autoencoder)
+- [Demo DC-AE-Diffusion Models](applications/dc_ae/README.md#demo-dc-ae-diffusion-models)
+- [Evaluate DC-AE-Diffusion Models](applications/dc_ae/README.md#evaluate-dc-ae-diffusion-models)
+- [Train DC-AE-Diffusion Models](applications/dc_ae/README.md#train-dc-ae-diffusion-models)
+- [Reference](applications/dc_ae/README.md#reference)
+
+### [CVPR 2024 eLVM Workshop] EfficientViT-SAM: Accelerated Segment Anything Model Without Accuracy Loss [[paper](https://arxiv.org/abs/2402.05008)] [[online demo](https://evitsam.hanlab.ai/)] [[readme](applications/efficientvit_sam/README.md)]
+
+**EfficientViT-SAM is a new family of accelerated segment anything models by replacing SAM's heavy image encoder with EfficientViT. It delivers a 48.9x measured TensorRT speedup on A100 GPU over SAM-ViT-H without sacrificing accuracy.**
+
+<p align="left">
+<img src="https://huggingface.co/mit-han-lab/efficientvit-sam/resolve/main/sam_zero_shot_coco_mAP.png"  width="500">
+</p>
+
+- [Pretrained EfficientViT-SAM Models](applications/efficientvit_sam/README.md#pretrained-efficientvit-sam-models)
+- [Usage of EfficientViT-SAM](applications/efficientvit_sam/README.md#usage)
+- [Evaluate EfficientViT-SAM](applications/efficientvit_sam/README.md#evaluation)
+- [Visualize EfficientViT-SAM](applications/efficientvit_sam/README.md#visualization)
+- [Deploy EfficientViT-SAM](applications/efficientvit_sam/README.md#deployment)
+- [Train EfficientViT-SAM](applications/efficientvit_sam/README.md#training)
+- [Reference](applications/efficientvit_sam/README.md#reference)
+
+### [ICCV 2023] EfficientViT-Classification [[paper](https://arxiv.org/abs/2205.14756)] [[readme](applications/efficientvit_cls/README.md)]
+
+**Efficient image classification models with EfficientViT backbones.**
+
+<p align="left">
+<img src="https://huggingface.co/han-cai/efficientvit-cls/resolve/main/efficientvit_cls_results.png"  width="600">
+</p>
+
+- [Pretrained EfficientViT Classification Models](applications/efficientvit_cls/README.md#pretrained-efficientvit-classification-models)
+- [Usage of EfficientViT Classification Models](applications/efficientvit_cls/README.md#usage)
+- [Evaluate EfficientViT Classification Models](applications/efficientvit_cls/README.md#evaluation)
+- [Export EfficientViT Classification Models](applications/efficientvit_cls/README.md#export)
+- [Train EfficientViT Classification Models](applications/efficientvit_cls/README.md#training)
+- [Reference](applications/efficientvit_cls/README.md#reference)
+
+### [ICCV 2023] EfficientViT-Segmentation [[paper](https://arxiv.org/abs/2205.14756)] [[readme](applications/efficientvit_seg/README.md)]
+
+**Efficient semantic segmantation models with EfficientViT backbones.**
+
+![demo](assets/cityscapes_l1.gif)
+
+- [Pretrained EfficientViT Segmentation Models](applications/efficientvit_seg/README.md#pretrained-efficientvit-segmentation-models)
+- [Usage of EfficientViT Segmentation Models](applications/efficientvit_seg/README.md#usage)
+- [Evaluate EfficientViT Segmentation Models](applications/efficientvit_seg/README.md#evaluation)
+- [Visualize EfficientViT Segmentation Models](applications/efficientvit_seg/README.md#visualization)
+- [Export EfficientViT Segmentation Models](applications/efficientvit_seg/README.md#export)
+- [Reference](applications/efficientvit_seg/README.md#reference)
+
+### EfficientViT-GazeSAM [[readme](applications/efficientvit_gazesam/README.md)]
+
+**Gaze-prompted image segmentation models capable of running in real time with TensorRT on an NVIDIA RTX 4070.**
+
+![GazeSAM demo](https://huggingface.co/mit-han-lab/efficientvit-sam/resolve/main/gazesam/efficientvit_gazesam_demo.gif)
+
+## Getting Started
+
+```bash
+conda create -n efficientvit python=3.10
+conda activate efficientvit
+pip install -U -r requirements.txt
+```
+
+## Third-Party Implementation/Integration
+
+- [NVIDIA Jetson Generative AI Lab](https://www.jetson-ai-lab.com/tutorial_efficientvit.html)
+- [timm](https://github.com/huggingface/pytorch-image-models): [link](https://github.com/huggingface/pytorch-image-models/blob/main/timm/models/efficientvit_mit.py)
+- [X-AnyLabeling](https://github.com/CVHub520/X-AnyLabeling): [link](https://github.com/CVHub520/X-AnyLabeling/blob/main/anylabeling/services/auto_labeling/efficientvit_sam.py)
+- [Grounding DINO 1.5 Edge](https://github.com/IDEA-Research/Grounding-DINO-1.5-API): [link](https://arxiv.org/pdf/2405.10300)
+
+## Contact
+
+[Han Cai](http://hancai.ai/)
+
+## Reference
+
+If EfficientViT or EfficientViT-SAM or DC-AE is useful or relevant to your research, please kindly recognize our contributions by citing our paper:
+
+```bibtex
+@inproceedings{cai2023efficientvit,
+  title={Efficientvit: Lightweight multi-scale attention for high-resolution dense prediction},
+  author={Cai, Han and Li, Junyan and Hu, Muyan and Gan, Chuang and Han, Song},
+  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
+  pages={17302--17313},
+  year={2023}
+}
+```
+
+```bibtex
+@article{zhang2024efficientvit,
+  title={EfficientViT-SAM: Accelerated Segment Anything Model Without Performance Loss},
+  author={Zhang, Zhuoyang and Cai, Han and Han, Song},
+  journal={arXiv preprint arXiv:2402.05008},
+  year={2024}
+}
+```
+
+```bibtex
+@article{chen2024deep,
+  title={Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models},
+  author={Chen, Junyu and Cai, Han and Chen, Junsong and Xie, Enze and Yang, Shang and Tang, Haotian and Li, Muyang and Lu, Yao and Han, Song},
+  journal={arXiv preprint arXiv:2410.10733},
+  year={2024}
+}
+```