Alpha-VLLM/Lumina-T2X

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

2250 stars · 98 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Lumina-T2X is a unified framework for text-to-any-modality generation built on flow-based large diffusion transformers. It supports generating images, videos, audio, speech, and 3D shapes from text prompts at varying resolutions and durations.

Use cases

• generate images from text prompts
• text to video generation
• synthesize speech or audio from text
• generate 3D shapes from a text description
• train or fine-tune diffusion transformer models
• research flow-based generative models

When to choose

• you need a single framework for multiple output modalities (image, video, audio, 3D)
• you want state-of-the-art diffusion transformer research code with pretrained checkpoints
• you are doing academic research on flow-based generative models

When to avoid

• you need a production-ready, polished end-user application
• you lack a high-end GPU, as training and inference are compute-heavy
• you only need simple text-to-image via a hosted API

Facets

library · maturity active

machine-learning deep-learning image-processing video-processing speech-recognition llm-training artificial-intelligence deep-learning image-processing python diffusion-transformer text-to-image text-to-video text-to-audio flow-matching aigc multimodal-generation research video natural-language-processing gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="Alpha-VLLM/Lumina-T2X")