Lumina-Image 2.0: 2B Flow-Based Diffusion Transformer by Alpha-VLLM — Apache-2.0

Lumina-Image 2.0 by Alpha-VLLM is a 2B parameter flow-based diffusion transformer for text-to-image generation with unified and efficient image generation framework.

L

Lumina-Image 2.0

Text-to-Image2B ParametersFlow-BasedDiTOpen Source

Lumina-Image 2.0 is a 2 billion parameter flow-based diffusion transformer for text-to-image generation. It uses a unified and efficient image generative framework with Gemini 2B text encoder, producing high-quality images at up to 1024×1024 resolution. Repackaged for ComfyUI with BF16 weights, Gemma 2 2B text encoder, and VAE.

Hugging FaceGitHubPaperComfy-Org Repo
DeveloperAlpha-VLLM
Release Date2025-03
Architecture2B Flow-Based Diffusion Transformer
LicenseApache-2.0
Output ResolutionUp to 1024×1024
Inference Steps28-50
Guidance Scale4.0
Text EncoderGemma 2 2B

Guides and workflows related to this model series.

No articles found.