Skip to content

Latest commit

 

History

History
115 lines (91 loc) · 6.13 KB

README.md

File metadata and controls

115 lines (91 loc) · 6.13 KB
Raw

🚀 CoDe: Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient

Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient
Zigeng Chen, Xinyin Ma, Gongfan Fang, Xinchao Wang
Learning and Vision Lab, National University of Singapore
🥯[Paper]🎄[Project Page]


1.7x Speedup and 0.5x memory consumption on ImageNet-256 generation. Top: original VAR-d30; Bottom: CoDe N=8. Speed ​​measurement does not include vae decoder

💡 Introduction

We propose Collaborative Decoding (CoDe), a novel decoding strategy tailored for the VAR framework. CoDe capitalizes on two critical observations: the substantially reduced parameter demands at larger scales and the exclusive generation patterns across different scales. Based on these insights, we partition the multi-scale inference process into a seamless collaboration between a large model and a small model.This collaboration yields remarkable efficiency with minimal impact on quality: CoDe achieves a 1.7x speedup, slashes memory usage by around 50%, and preserves image quality with only a negligible FID increase from 1.95 to 1.98. When drafting steps are further decreased, CoDe can achieve an impressive 2.9x acceleration, reaching over 41 images/s at 256x256 resolution on a single NVIDIA 4090 GPU, while preserving a commendable FID of 2.27. figure figure

🔥Updates

  • 🔥 November 28, 2024: Our paper is available now!
  • 🔥 November 27, 2024: Our model weights are avalible at 🤗 huggingface here
  • 🔥 November 27, 2024: Code repo is released! Arxiv paper will come soon!

🔧 Installation

  1. Install torch>=2.0.0.
  2. Install other pip packages via pip3 install -r requirements.txt.

💻 Model Zoo

We provide drafter VAR models and refiner VAR models, which are on or can be downloaded from the following links:

Draft step Refine step reso. FID IS Drafter VAR🤗 Refiner VAR🤗
9 steps 1 steps 256 1.94 296 drafter_9.pth refiner_9.pth
8 steps 2 steps 256 1.98 302 drafter_8.pth refiner_8.pth
7 steps 3 steps 256 2.11 303 drafter_7.pth refiner_7.pth
6 steps 4 steps 256 2.27 397 drafter_6.pth refiner_6.pth

Note: The VQVAE vae_ch160v4096z32.pth is also needed.

⚡ Inference

Original VAR Inference:

CUDA_VISIBLE_DEVICES=0 python infer_original.py --model_depth 30

🚀 Training-free CoDe:

CUDA_VISIBLE_DEVICES=0 python infer_CoDe.py --drafter_depth 30 --refiner_depth 16 --draft_steps 8 --training_free

🚀 Speciliazed Fine-tuned CoDe:

CUDA_VISIBLE_DEVICES=0 python infer_CoDe.py --drafter_depth 30 --refiner_depth 16 --draft_steps 8
  • drafter_depth: The depth of the large drafter transformer model.
  • refiner_depth: The depth of the small refiner transformer model.
  • draft_steps: Number of steps for the drafting stage.
  • training_free: Enabling training-free CoDe or inference with specialized finetuned CoDe.

⚡ Sample & Evaluations

Sampling 50000 images (50 per class) with CoDe

CUDA_VISIBLE_DEVICES=0 python sample_CoDe.py --drafter_depth 30 --refiner_depth 16 --draft_steps 8 --output_path <img_save_path>

The generated images are saved as both .PNG and .npz. Then use the OpenAI's FID evaluation toolkit and reference ground truth npz file of 256x256 to evaluate FID, IS, precision, and recall.

🚀 Visualization Results

Quanlitative Results

figure

Zero-short Inpainting&Editing (N=8)

figure

Acknowlegdement

Thanks to VAR for their wonderful work and codebase!

Citation

If our research assists your work, please give us a star ⭐ or cite us using:

@misc{2411.17787,
Author = {Zigeng Chen and Xinyin Ma and Gongfan Fang and Xinchao Wang},
Title = {Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient},
Year = {2024},
Eprint = {arXiv:2411.17787},
}