liuchanglab commited on
Commit
461ad0d
·
verified ·
1 Parent(s): 6fd7c15

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +0 -10
README.md CHANGED
@@ -2,7 +2,6 @@
2
 
3
 
4
  # MammothModa2: A Unified AR-Diffusion Framework for Multimodal Understanding and Generation
5
- <img src='./doc/logo.png' alt="MammothModa Logo" width="100" style="max-width: 100px; height: auto;">
6
 
7
  [![GitHub](https://img.shields.io/badge/MammothModa2-GitHub-blue)](https://github.com/bytedance/mammothmoda)
8
  [![Project Page](https://img.shields.io/badge/MammothModa2-Project_Page-green)](https://mammothmoda2.github.io/)
@@ -23,15 +22,6 @@ MammothModa2 (Mammoth2) is a unified autoregressive-diffusion (AR-Diffusion) fra
23
 
24
  Trained with roughly 60M supervised generation samples and no reliance on pre-trained generators, Mammoth2 demonstrates that a carefully coupled AR-Diffusion architecture can provide high-fidelity generation and editing while maintaining strong multimodal comprehension within a single, parameter- and data-efficient model.
25
 
26
- ## Show cases
27
- <!-- <div align="center">
28
- <img src='./mammoth.png' alt="MammothModa Overview" width="80%">
29
- </div> -->
30
-
31
- <div align="center">
32
- <img src='./doc/mammoth.png' alt="MammothModa2 Show cases" style="max-width: 80%; height: auto;">
33
- </div>
34
-
35
  ## 🎉 News
36
  - 2025-12-10: 🔥MammothModa2-Dev models are now available at [HuggingFace](https://huggingface.co/bytedance-research/MammothModa2-Dev).
37
  - 2025-10-01: 🔥MammothModa2-Preview models are now available at [HuggingFace](https://huggingface.co/bytedance-research/MammothModa2-Preview). **Note: To use the Preview version, please switch to the `qwen25vl` branch.**
 
2
 
3
 
4
  # MammothModa2: A Unified AR-Diffusion Framework for Multimodal Understanding and Generation
 
5
 
6
  [![GitHub](https://img.shields.io/badge/MammothModa2-GitHub-blue)](https://github.com/bytedance/mammothmoda)
7
  [![Project Page](https://img.shields.io/badge/MammothModa2-Project_Page-green)](https://mammothmoda2.github.io/)
 
22
 
23
  Trained with roughly 60M supervised generation samples and no reliance on pre-trained generators, Mammoth2 demonstrates that a carefully coupled AR-Diffusion architecture can provide high-fidelity generation and editing while maintaining strong multimodal comprehension within a single, parameter- and data-efficient model.
24
 
 
 
 
 
 
 
 
 
 
25
  ## 🎉 News
26
  - 2025-12-10: 🔥MammothModa2-Dev models are now available at [HuggingFace](https://huggingface.co/bytedance-research/MammothModa2-Dev).
27
  - 2025-10-01: 🔥MammothModa2-Preview models are now available at [HuggingFace](https://huggingface.co/bytedance-research/MammothModa2-Preview). **Note: To use the Preview version, please switch to the `qwen25vl` branch.**