Lumina Image 2
Free.ai (self-hosted)
·
image
·
~1000 Koffice FilterName image
·
2.5
van 26 gebruikers van hierdie kategorie
Lumina Image 2 is a Beeld_draadmodel gebou deur Alpha-VLLM. Sterkste by Detailed prompt-following image generation.. Self-hosted on Free.ai GPUs — runs free against your daily token pool (1,000 tokens per beeld). Released under Apache 2.0 — commercial use permitted on Free.ai.
Gebruik via API
OpenAI- versoenbaar met REST API. Genereer 'n sleutel en noem hierdie model in sekondes.
curl -X POST https://api.free.ai/v1/image/generate/ \
-H "Authorization: Bearer sk-free-..." \
-H "Content-Type: application/json" \
-d '{"model":"lumina-image-2","prompt":"your prompt here"}'Soortgelyke modelle
Vrae wat dikwels gevra word
Lumina Image 2 is a Beeld_draadmodel gebou deur Alpha-VLLM. Sterkste by Detailed prompt-following image generation.. Self-hosted on Free.ai GPUs — runs free against your daily token pool (1,000 tokens per beeld). Released under Apache 2.0 — commercial use permitted on Free.ai.
Lumina Image 2 werk goed vir Detailed prompt-following image generation.. Probeer die voorbeeld beweeg hierbo om sy sterk punte te sien.
About 1,000 tokens per image. $1 buys 750,000 tokens, and a free Free.ai account includes a 30,000-token daily refill pool, 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.Die onderliggende model is Apache 2.0-gelak. See /models/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.
Die meeste beelde kom terug in 5-25 sekondes afhangend van die model en huidige GPU las. Die resultaat verskyn inlyn; getekende-in gebruikers kan ook byvoeg om die oortjie te sluit en inkennis gestel word wanneer dit land.
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.
Ja. POST na /v1/image/generate/ met model="lumina-image-2" en sluit jou Beerbewys in. Volle verwysing: /api/.
Lumina Image 2 is Apache 2.0-licensedmet 2.6B parameters — see /models/lumina-image-2/ for the model card and our open-source repos at github.com/freeaigit for ready-to-run scripts.
Vry rekenings kry 10 000 ondertekenings en 'n daaglikse bad. Wanneer dit opraak, begin dit by $1 (5050K-bewyse) geen intekening wat nodig is nie.