https://github.com/tyshiwo1/Accelerating-T2I-AR-with-SJD

Implementation of Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding
https://github.com/tyshiwo1/Accelerating-T2I-AR-with-SJD

Last synced: 12 days ago
JSON representation

Implementation of Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding

• Host: GitHub
• URL: https://github.com/tyshiwo1/Accelerating-T2I-AR-with-SJD
• Owner: tyshiwo1
• Created: 2024-10-07T14:48:45.000Z (4 months ago)
• Default Branch: main
• Last Pushed: 2024-11-04T08:15:14.000Z (3 months ago)
• Last Synced: 2024-11-04T09:24:00.357Z (3 months ago)
• Language: Python
• Size: 729 KB
• Stars: 19
• Watchers: 1
• Forks: 0
• Open Issues: 1
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• awesome-diffusion-categorized - [Code

README

        
# Accelerating T2I-AR with SJD

Implementation of [Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding](https://arxiv.org/pdf/2410.01699)

## Performance

- Results on [Emu3](https://github.com/baaivision/Emu3) 

  

- Results on [Lumina-mGPT](https://github.com/Alpha-VLLM/Lumina-mGPT) 

  

## Run

### demos

#### Lumina-mGPT

```bash

CUDA_VISIBLE_DEVICES=0 python test_lumina_mgpt.py

```

#### Emu3

```bash

CUDA_VISIBLE_DEVICES=0 python test_emu3.py

```

#### LlamaGen

```bash

CUDA_VISIBLE_DEVICES=0 python test_llamagen.py

```

## Acknowledge

Our code is based on [Lumina-mGPT](https://github.com/Alpha-VLLM/Lumina-mGPT), [Emu3](https://github.com/Alpha-VLLM/Lumina-mGPT), [LlamaGen](https://github.com/FoundationVision/LlamaGen), and [Anole](https://github.com/GAIR-NLP/anole). We would like to express our gratitude to [Tianwei Xiong](https://github.com/SilentView) for his assistance.