by Microsoft
MAI-Image 2.7
Microsoft precision-tier image generation & editing — design-ready visuals, up to 5 refs, transparent PNG
mai-image-2.7Generate images with this model.
/api/v1/images/generationsGET /api/v1/models?type=image{
"model": "mai-image-2.7",
"prompt": "A serene mountain landscape at golden hour",
"size": "1024x1024",
"n": 1,
"reference_image": "https://example.com/reference.jpg"
}curl -X POST https://kunya.ai/api/v1/images/generations \
-H "Authorization: Bearer kunya_YOUR_API_KEY" \
-H "Content-Type: application/json"
-d '{"model":"mai-image-2.7","prompt":"A serene mountain landscape at golden hour","size":"1024x1024","n":1,"reference_image":"https://example.com/reference.jpg"}'Alibaba (Qwen)
Fast, lower-cost Qwen Image 2.1 — generation & editing with up to 4 reference images
API DocumentationMiniMax
Faster MiniMax H3 Image — text-to-image & multi-ref editing up to 16 refs, native 1K–4K (up to ~16 MP)
API DocumentationOpenAI
OpenAI flagship image quality — detailed compositions, SVG/GIF, precise edits
API DocumentationMidjourney
Midjourney V8.1 — latest MJ route with HD/2K output, Omni Reference (--oref), Style Reference (--sref), and post-gen actions (variation, remix, canvas, retexture, remove background). 4 images per request.
API Documentation