lumos

<p align="center"> <img src="asset/logo.gif" height=20> </p> <div style="display:flex;justify-content: center"> <a href="https://arxiv.org/pdf/2412.07767"><img src="https://img.shields.io/static/v1?label=Paper&message=Arxiv:Lumos&color=red&logo=arxiv"></a> &ensp; <a href="https://xiaomabufei.github.io/lumos/"><img src="https://img.shields.io/static/v1?label=Project%20Page&message=Github&color=blue&logo=github-pages"></a> &ensp; </div>

🥳 What is Lumos ?

<b>TL; DR: <font color="purple">Lumos</font> is a pure vision-based generative framework, which confirms the feasibility and the scalability of learning visual generative priors. It can be efficiently adapted to visual generative tasks such as text-to-image, image-to-3D, and image-to-video generation.</b>

<details><summary>CLICK for the full abstract</summary> Although text-to-image (T2I) models have recently thrived as visual generative priors, their reliance on high-quality text-image pairs makes scaling up expensive. We argue that grasping the cross-modality alignment is not a necessity for a sound visual generative prior, whose focus should be on texture modeling. Such a philosophy inspires us to study image-to-image (I2I) generation, where models can learn from in-the-wild images in a self-supervised manner. We first develop a pure vision-based training framework, Lumos, and confirm the feasibility and the scalability of learning I2I models. We then find that, as an upstream task of T2I, our I2I model serves as a more foundational visual prior and achieves on-par or better performance than existing T2I models using only 1/10 text-image pairs for fine-tuning. We further demonstrate the superiority of I2I priors over T2I priors on some text-irrelevant visual generative tasks, like image-to-3D and image-to-video. </details>

🪄✨ Lumos Model Card

🚀 Model Structure

Lumos consists of transformer blocks for latent diffusion, which is applied for various visual generative tasks such as text-to-image, image-to-3D, and image-to-video generation.

Source code is available at https://github.com/xiaomabufei/lumos.

📋 Model Description

• Developed by: Lumos
• Model type: Diffusion-Transformer-based generative model
• License: CreativeML Open RAIL++-M License
• Model Description: Lumos-I2I is a model designed for generating images based on image prompts. It utilizes a Transformer Latent Diffusion architecture and incorporates a fixed, pretrained vision encoder (DINO). Lumos-T2I is a model that can be used to generate images based on text prompts. It is a Transformer Latent Diffusion Model that uses one fixed, pretrained text encoders (T5).
• Resources for more information: Check out our GitHub Repository and the Lumos report on arXiv.