How to run Lumina-Image 2.0 locally

Alpha-VLLM (Shanghai AI Lab) · Text → image · 2.6B params · Apache-2.0 (commercial OK)

A unified 2.6B flow-based DiT, fully Apache-licensed, delivering strong prompt-following and bilingual text at modest size.

What it costs to run — $0 markup

On your own machine — $0. Runs free if you have about 12 GB of VRAM (~12GB; uses Gemma-2-2B text encoder + FLUX 16ch VAE), via Diffusers / ComfyUI.
Rent a GPU — from $0.26/hr. Fits RTX 3090 24GB at the direct vendor price ($0 markup) — pay only for the minutes you generate.
Download the weights — free. Open weights at Alpha-VLLM/Lumina-Image-2.0.

Note: generative-media models are billed per image / per second / per minute on hosted services — not per token. Running locally or on your own rented GPU is usually far cheaper and keeps your data on your machine.

Key facts

Does	Text → image
VRAM to run	~12 GB (~12GB; uses Gemma-2-2B text encoder + FLUX 16ch VAE)
Download	~11 GB
Parameters	2.6B
License	Apache-2.0 (commercial use OK)
Run with	Diffusers / ComfyUI

Get Lumina-Image 2.0 on Hugging Face →

More image models

FLUX.1 [dev] — Text → image, ~12 GB VRAM
Stable Diffusion XL 1.0 (SDXL) — Text → image, ~8.0 GB VRAM
Stable Diffusion 1.5 — Text → image, ~4.0 GB VRAM
FLUX.1 Kontext [dev] — Image editing, ~12 GB VRAM
FLUX.1 [schnell] — Text → image, ~12 GB VRAM
Qwen-Image — Text → image, ~24 GB VRAM

Browse: all media models · chat / LLM models