$\textbf{Lumina-T2X}$ : Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformers
[📄 Lumina-T2X arXiv] [📽️ Video Introduction of Lumina-T2X] [👋 join our WeChat]
[🤖️ Lumina-T2I 5B Checkpoints] [🤖️ Lumina-Next-T2I 2B Checkpoints (recommend)]
[🕹️ GUI Demo for Lumina-T2I 5B model (node1)]
[🔮 GUI Demo for Lumina-Next-T2I 2B model (node2)] [🔮 GUI Demo for Lumina-Next-T2I 2B model (node3)]
- [2024-05-12] 🤩🤩🤩 We excitedly released our
Lumina-Next-T2Imodel (checkpoint) which uses a 2B Next-DiT model as the backbone and Gemma-2B as the text encoder. Try it out at demo1 & demo2. - [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-T2Ifor text-to-image generation.
Warning
Since we are updating the code frequently, please pull the latest code:
git pull origin main
In order to quickly get you guys using our model, we built different versions of the GUI demo site.
[node1]
For more details about training and inference, please refer to Lumina-T2I and Lumina-Next-T2I
- Lumina-T2I (Demos✅, Training✅, Inference✅, Checkpoints✅)
- Lumina-T2V (Demos✅)
- Lumina-T2A (Demos✅)
- Web Demo
- Cli Demo
We introduce the
🌟 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:
-
$\textbf{Lumina-T2X}$ 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. - 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.
video_720p_1.mp4
video_720p_2.mp4
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.
video_tokyo_woman.mp4
360P Videos:
video_360p.mp4
multi_view.mp4
Note
Attention: Mouse over the playbar and click the audio button on the playbar to unmute it.
Prompt: Semiautomatic gunfire occurs with slight echo
Generated Audio:
semiautomatic_gunfire_occurs_with_slight_echo.mp4
Groundtruth:
semiautomatic_gunfire_occurs_with_slight_echo_gt.mp4
Prompt: A telephone bell rings
Generated Audio:
a_telephone_bell_rings.mp4
Groundtruth:
a_telephone_bell_rings_gt.mp4
Prompt: An engine running followed by the engine revving and tires screeching
Generated Audio:
an_engine_running_followed_by_the_engine_revving_and_tires_screeching.mp4
Groundtruth:
an_engine_running_followed_by_the_engine_revving_and_tires_screeching_gt.mp4
Prompt: Birds chirping with insects buzzing and outdoor ambiance
Generated Audio:
birds_chirping_repeatedly.mp4
Groundtruth:
birds_chirping_repeatedly_gt.mp4
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}
}