AI Image - Lumina Image 2

Kommersiële gebruik OK 380+modelle Geen watermerk nie Geen teken-op benodig
Model:
+ GPT-5, Claude, Gemini
Image model Self-hosted Apache 2.0 2.6B
Lumina Image 2 — Lumina Image 2 — Apache 2.0. DiT-based, strong prompt following, highly controllable.
~1000 Prometiumunit description in lists/per beeld
0%
Starting generation...

What is Lumina Image 2?

Lumina Image 2 — Apache 2.0. DiT-based, strong prompt following, highly controllable.

Best for: Detailed prompt-following image generation.

Why use Lumina Image 2 for image generation?

Text-to-image

Type a description, get an image. Style, aspect ratio, and batch count are all controllable from the form above.

Aspect ratios

Square, landscape, portrait, 4:3, 3:4. Pick the ratio in the form so the model frames the shot for that shape.

Batch generate

Pick 1, 2, or 4 in the count field above. For larger fan-outs use /image/generate/ which sends one prompt to multiple models in parallel.

Commercial use OK

No watermark, outputs are yours. Commercial use is in scope across every model on Free.ai.

Sample prompts

Anime girl with cherry-blossom hair standing on a Tokyo rooftop at sunset
Studio Ghibli style village by a river, warm summer afternoon, hand-drawn
Manga panel of a swordsman blocking a strike, dynamic pose, bold ink lines
Cute chibi sticker pack: 6 expressions of a sleepy raccoon barista
Fantasy battle scene, two dragons fighting above clouds, painterly anime style
Slice-of-life cafe interior at golden hour, anime aesthetic, soft bokeh

Pricing

Self-hosted on our GPUs. Generation draws from your daily free pool first; once that runs out, paid token packs start at $1 -> 750,000 tokens. Roughly ~1000 tokens per image.

Compare to alternatives

Full model reference → · See all image models → · Vergelyk beeldmodelle →

Gevorderde opsies
Resultaat
Tokens loop laag. Get More Tokens
Want better results? Premium modelle (GPT-5, Claude, Gemini) deliver higher quality. View Plans

❤️ Love Free.ai? Tell your friends!

Teken op om 'n verwysingale skakel te kry en verdien 25 000 briewe per vriend.

Wil jy meer hê? Teken gratis op vir 5K-bewyse/dag + 10K bonus
Meld aan om vry te wees

Proses jou versoek...

Lumina Image 2 — Apache 2.0. DiT-based, strong prompt following, highly controllable.

Hoe om te gebruik AI Image - Lumina Image 2

1
Tik jou invoer in

Tik teks, oplaai 'n lêer, of beskryf wat jy wil hê. Nee rekening benodig.

2
Kliek genereer

Ons kunsmatige intelligensie verwerk jou versoek in sekondes deur die beste ope-bou modelle te gebruik.

3
Aflaai klaar gemaak

Laai af, kopieer of deel jou resultaat. Vry vir persoonlike en kommersiële gebruik.

Gebruik hierdie program deur middel van API

Outomate hierdie program van jou eie kode. OpenAI- compatibleREST- end point, Beer-token auth, nee ekstra SDK benodig. Token kos ooreenstem die web koppelvlak.

curl -X POST https://api.free.ai/v1/image/generate/ \
  -H "Authorization: Bearer sk-free-..." \
  -H "Content-Type: application/json" \
  -d '{"prompt": "A sunset over mountains", "model": "sdxl"}'

AI Image - Lumina Image 2 — FAQ

Lumina Image 2 — Apache 2.0. DiT-based, strong prompt following, highly controllable.

Lumina Image 2 works well for Detailed prompt-following image generation.. Try the sample prompts above to see its strengths.

About 1,000 tokens per image. $1 buys 750,000 tokens, and a free Free.ai account includes 10,000 signup tokens plus a daily refill, so most users can try Lumina Image 2 without spending anything.

It depends on the prompt. Free.ai lets you compare Lumina Image 2 side-by-side with any other model at /image/compare/ — pick a sibling from the alternatives list to see how they differ on the same input.

Yes. Free.ai does not add watermarks and the outputs are yours to use commercially. The underlying model is Apache 2.0-licensed. See /apps/lumina-image-2/ for the full breakdown.

On Free.ai, Lumina Image 2 supports 1:1 (square), 16:9 (landscape), 9:16 (portrait), 4:3, and 3:4. Pick the ratio in the form above before generating.

Most images come back in 5-25 seconds depending on the model and current GPU load. The result appears inline; signed-in users can also Add to queue to close the tab and get notified when it lands.

Yes — pick 1, 2, or 4 in the count field. Each image deducts about 1,000 tokens. For larger batches use /image/generate/ which fans out the same prompt across multiple models in parallel.

Free.ai does not train models on your prompts. Self-hosted models stay on our GPUs. Premium models route to the upstream provider for inference. Either way we never resell your data.

Yes. POST to /v1/image/generate/ with model="lumina-image-2" and include your Bearer token. Full reference: /api/.

Lumina Image 2 is Apache 2.0-licensed with 2.6B parameters — see /apps/lumina-image-2/ for the model card and our open-source repos at github.com/freeaigit for ready-to-run scripts.

Free accounts get 10,000 signup tokens plus a daily pool. When that runs out, top up starting at $1 (750K tokens) — no subscription required.

Teken gratis op vir 10 000 tekens

Skep vrye rekening

Geen kredietkaart benodig nie

Hoe sal jy hierdie instrument uitwerk?

3.4/5 from 5 ratings

Like this tool? Share it!