# Lumina Image 2.0 AI Generator

> A compact open flow model with explicit CFG normalisation and strong prompt-to-image alignment.

Canonical URL: https://allimageai.com/models/lumina-image-2/

Website: All Image AI

Language: English

Lumina Image 2.0 is Alpha-VLLM’s compact 2.6B flow-based foundation model. Its hosted route exposes guidance, step count, negative prompts and CFG normalisation for controlled 1024-pixel generation.

## Model details

- Developer: Alpha-VLLM
- Status on All Image AI: Active
- Last verified: 2026-08-25
- Maximum output: 1K
- Modes: Text to Image, Typography
- Reference images: not supported
- Resolutions: 1K
- Aspect ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3

## Best for

- Open-model experimentation
- Illustration and graphic art
- Typography concepts
- CFG-controlled generation

## How to use

1. Write a clear prompt and exclusions.
2. Start at guidance 4 and 30 steps.
3. Fix the seed for comparisons.
4. Upscale the selected 1K render separately.

## Settings explained

### Guidance

The documented default is 4 with CFG normalisation enabled.

### Steps

30 is the upstream default; higher values add latency before they add visible detail.

## Prompt examples

### Graphic art

> Electric paint splashes in cobalt, violet and orange around the exact words “LUMINA 2”, crisp modern display type

### Landscape

> Golden sun reflected across calm open water, distant basalt cliffs, serene fine-art photograph

## Limitations

- 1024-pixel model checkpoint
- Text-to-image only
- Higher provider cost than lightweight draft models

## Pricing and credits

Credits for one image at default quality and mode. Resolution, quality, reference inputs, edit mode and output count can change the total. Check the Generate button before submitting.

| Resolution | Credits / image |
| --- | --- |
| 1K | 6 |

Failed generations cost 0 credits. Catalog availability does not guarantee runtime availability; the workspace reports whether the selected model can run.

[Credit plans](https://allimageai.com/pricing.md)

## Test results

Testing in progress. No verified benchmark scores have been published for this model.

## Commercial use and image handling

Lumina Image 2.0 is released under Apache 2.0; generated use remains subject to applicable law and site terms.

Uploads are processed by the configured inference service. You can delete a generation from your history.

## Frequently asked questions

### Why only 1K?

The official released checkpoint and model zoo target 1024-pixel generation.

### Is it an open model?

Yes. The official Alpha-VLLM implementation and weights are published under Apache 2.0.

## Release history and sources

January 25, 2025 — Weights and model code released

This date applies to the event shown. Later API access, weights and availability on All Image AI may have different dates.

- [github.com](https://github.com/Alpha-VLLM/Lumina-Image-2.0)

[Event evidence on the timeline](https://allimageai.com/timeline/#event-lumina-image-2)