Alpha-VLLM/Lumina-T2X
A unified text-to-any-modality generation framework using flow-based large diffusion transformers.
Not currently ranked — collecting fresh signals.
star history
Lumina-T2X is a generative AI framework that transforms text descriptions into images, videos, audio, and 3D content using flow-matching diffusion transformers. It supports variable resolution and duration generation across modalities. The project includes model weights, training code, and inference pipelines. It builds on the VLLM ecosystem for efficient inference.
Frequently asked
- What is Alpha-VLLM/Lumina-T2X?
- A unified text-to-any-modality generation framework using flow-based large diffusion transformers.
- Is Lumina-T2X open source?
- Yes — Alpha-VLLM/Lumina-T2X is open source, released under the MIT license.
- What language is Lumina-T2X written in?
- Alpha-VLLM/Lumina-T2X is primarily written in Python.
- How popular is Lumina-T2X?
- Alpha-VLLM/Lumina-T2X has 2.2k stars on GitHub.
- Where can I find Lumina-T2X?
- Alpha-VLLM/Lumina-T2X is on GitHub at https://github.com/Alpha-VLLM/Lumina-T2X.