• [2024-05-10] 🔥🔥🔥 We released the technical report on arXiv.
• [2024-05-09] 🚀🚀🚀 We released Lumina-T2A (Text-to-Audio) Demos. Examples
• [2024-04-29] 🔥🔥🔥 We released the 5B model checkpoint and demo built upon it for text-to-image generation.
• [2024-04-25] 🔥🔥🔥 Support 720P video generation with arbitrary aspect ratio. Examples 🚀🚀🚀
• [2024-04-19] 🔥🔥🔥 Demo examples released.
• [2024-04-05] 😆😆😆 Code released for Lumina-T2I.
• [2024-04-01] 🚀🚀🚀 We release the initial version of Lumina-T2I for text-to-image generation.

In order to quickly get you guys using our model, we built different versions of the GUI demo site.

[node1]

[node1] [node2]

For more details about training and inference, please refer to Lumina-T2I README.md

• Lumina-T2I (Training, Inference, Checkpoints)
• Lumina-T2V
• Web Demo
• Cli Demo

• Lumina-T2X
  • 📰 News
  • 🚀 Quick Start
  • 📑 Open-source Plan
  • 📜 Index of Content
  • Introduction
  • 📽️ Demo Examples
    • Text-to-Image Generation
    • Text-to-Video Generation
    • Text-to-3D Generation
    • More examples
  • ⚙️ Diverse Configurations

We introduce the $\textbf{Lumina-T2X}$ family, a series of text-conditioned Diffusion Transformers (DiT) capable of transforming textual descriptions into vivid images, dynamic videos, detailed multi-view 3D images, and synthesized speech. At the core of Lumina-T2X lies the Flow-based Large Diffusion Transformer (Flag-DiT)—a robust engine that supports up to 7 billion parameters and extends sequence lengths to 128,000 tokens. Drawing inspiration from Sora, Lumina-T2X integrates images, videos, multi-views of 3D objects, and speech spectrograms within a spatial-temporal latent token space, and can generate outputs at any resolution, aspect ratio, and duration.

🌟 Features:

• Flow-based Large Diffusion Transformer (Flag-DiT): Lumina-T2X adopts the flow matching formulation and is equipped with many advanced techniques, such as RoPE, RMSNorm, and KQ-norm, demonstrating faster training convergence, stable training dynamics, and a simplified pipeline.
• Any Modalities, Resolution, and Duration within One Framework:
  1. $\textbf{Lumina-T2X}$ can encode any modality, including mages, videos, multi-views of 3D objects, and spectrograms into a unified 1-D token sequence at any resolution, aspect ratio, and temporal duration.
  2. By introducing the [nextline] and [nextframe] tokens, our model can support resolution extrapolation, i.e., generating images/videos with out-of-domain resolutions not encountered during training, such as images from 768x768 to 1792x1792 pixels.
• Low Training Resources: Our empirical observations indicate that employing larger models, high-resolution images, and longer-duration video clips can significantly accelerate the convergence speed of diffusion transformers. Moreover, by employing meticulously curated text-image and text-video pairs featuring high aesthetic quality frames and detailed captions, our $\textbf{Lumina-T2X}$ model is learned to generate high-resolution images and coherent videos with minimal computational demands. Remarkably, the default Lumina-T2I configuration, equipped with a 5B Flag-DiT and a 7B LLaMA as the text encoder, requires only 35% of the computational resources compared to Pixelart-$\alpha$.

720P Videos:

Prompt: The majestic beauty of a waterfall cascading down a cliff into a serene lake.

Prompt: A stylish woman walks down a Tokyo street filled with warm glowing neon and animated city signage. She wears a black leather jacket, a long red dress, and black boots, and carries a black purse. She wears sunglasses and red lipstick. She walks confidently and casually. The street is damp and reflective, creating a mirror effect of the colorful lights. Many pedestrians walk about.

360P Videos:

Prompt: Semiautomatic gunfire occurs with slight echo

Generated Audio:

Groundtruth:

Prompt: A telephone bell rings

Generated Audio:

Groundtruth:

Prompt: An engine running followed by the engine revving and tires screeching

Generated Audio:

Groundtruth:

Prompt: Birds chirping with insects buzzing and outdoor ambiance

Generated Audio:

Groundtruth:

We support diverse configurations, including text encoders, DiTs of different parameter sizes, inference methods, and VAE encoders. Additionally, we offer features such as 1D-RoPE, image enhancement, and more.

@article{gao2024luminat2x,
      title={Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformers}, 
      author={Peng Gao and Le Zhuo and Ziyi Lin and Chris Liu and Junsong Chen and Ruoyi Du and Enze Xie and Xu Luo and Longtian Qiu and Yuhang Zhang and Chen Lin and Rongjie Huang and Shijie Geng and Renrui Zhang and Junlin Xi and Wenqi Shao and Zhengkai Jiang and Tianshuo Yang and Weicai Ye and He Tong and Jingwen He and Yu Qiao and Hongsheng Li},
      journal={arXiv preprint arXiv:2405.05945},
      year={2024}
}