$5 free credits when you sign up Claim now
Whisper Large V3 CT2 now available Test it!
MiniMax H3 now available! Test it!
GPT1.5 and GPT2.0 available now for Premium users Test it!

Generate Images from Text

Test AI image generation for free, then deploy via API.

Loading models…

FLUX.2 Klein 4B BF16

256–1024px resolution (16px steps). Default: 1024×1024, 4 steps. Guidance: 1.0 (fixed). Unified model for generation and multi-reference editing. Sub-second inference.

Model details
FLUX.2 Klein 4B BF16 sample

A cinematic, hyper-realistic eye-level shot through a rainy coffee shop window at night. Condensation on the glass is partially wiped away to reveal the handwritten text 'KLEIN 4B' clearly written in the moisture. Throug… A cinematic, hyper-realistic eye-level shot through a rainy coffee shop window at night. Condensation on the glass is partially wiped away to reveal the handwritten text 'KLEIN 4B' clearly written in the moisture. Through the clear glass, a warm, cozy interior is visible with soft bokeh lights. Outside, reflections of blue and pink neon city lights dance on the wet glass droplets. Incredible texture detail on the water drops and glass surface. 8k resolution, shot on 35mm lens, f/1.4, street photography style.

GPT Image 2

· Experimental · Partner model · Premium · Generate from a description, with a reasoning pass ahead of generation. The gain is clearest on prompts with several interacting constraints — a layout with specified positions, a scene with a set number of objects, or a design that has to carry a specific line of text. Output runs from 512px up to 2048px.

Model details
GPT Image 2 sample

A detailed technical cutaway illustration of a mechanical wristwatch movement, precise line-and-wash rendering on cream paper, the mainspring barrel, escapement, balance wheel and gear train all visible and individually… A detailed technical cutaway illustration of a mechanical wristwatch movement, precise line-and-wash rendering on cream paper, the mainspring barrel, escapement, balance wheel and gear train all visible and individually labelled with fine leader lines, an ornate title block at the lower right reading "CALIBRE 7 - EXPLODED VIEW", draughtsman precision, muted sepia and slate palette

GPT Image 1.5

Experimental · Partner model · Premium Generate from a plain-language description. GPT Image 1.5 follows long, compound instructions closely and renders legible text inside the image — useful for mockups, ad creative and anything carrying a label, sign or headline in frame.

Model details
GPT Image 1.5 sample

A red fox sitting in a snowy forest at sunset A red fox sitting in a snowy forest at sunset

Z-Anime

INT8 quantized. Resolution 128–2048 px (16 px steps). 4–16 inference steps. Default: 768x768, 8 steps. Tuned with Z-Image Base for anime-style images. Recognizes several iconic characters from well-known anime.

Model details
Z-Anime sample

A colossal serpent kaiju of living forest rising from a devastated jungle valley, its enormous body and rearing coils woven entirely from braided vines, dark green scales, twisted roots, and clusters of living trees grow… A colossal serpent kaiju of living forest rising from a devastated jungle valley, its enormous body and rearing coils woven entirely from braided vines, dark green scales, twisted roots, and clusters of living trees growing across its hide, with small bonsai-like canopies sprouting from its back and shoulders. Its serpentine head looms in the upper portion of the frame, mouth slightly open to reveal pale fangs, a single piercing red eye glowing with quiet menace, leaf-shaped crests framing its skull like a feathered crown. Around it, towering plumes of cream and pale gold dust clouds billow upward from the ruined ground, broken trees and gnarled debris scatter the dark earth in the foreground, and silhouetted bats and birds wheel through a luminous pale-green sky. Dramatic low-angle composition, deep moss-green, ivory color palette, soft volumetric light filtering through the haze, cinematic kaiju scale, wallpaper quality, highly detailed environment, professional anime illustration

Z-Image-Turbo INT8

INT8 quantized. 128–2048px resolution (16px steps). 1–50 inference steps. Default: 768×768, 8 steps. Fastest option for production.

Model details
Z-Image-Turbo INT8 sample

Hyperrealistic portrait photograph of a beautiful young woman, natural skin texture with subtle freckles, piercing green eyes with realistic light reflections, soft volumetric lighting from golden hour sun, wispy strands… Hyperrealistic portrait photograph of a beautiful young woman, natural skin texture with subtle freckles, piercing green eyes with realistic light reflections, soft volumetric lighting from golden hour sun, wispy strands of auburn hair catching the light, shallow depth of field, shot on Hasselblad medium format camera, 85mm lens, professional fashion photography, magazine cover quality, photorealistic skin pores and fine details, natural makeup, serene confident expression

FLUX.1 schnell

256–2048px resolution (128px steps). 1–10 inference steps. Default: 768×768, 4 steps. No guidance needed. Optimized for speed.

Model details
FLUX.1 schnell sample

Ethereal bioluminescent forest at twilight, ancient massive trees with glowing cyan and purple fungi growing on bark, fireflies creating streams of golden light, misty atmosphere with rays of moonlight filtering through… Ethereal bioluminescent forest at twilight, ancient massive trees with glowing cyan and purple fungi growing on bark, fireflies creating streams of golden light, misty atmosphere with rays of moonlight filtering through canopy, crystal-clear stream reflecting the magical lights, ultra-detailed fantasy landscape, cinematic composition, volumetric fog, dreamlike atmosphere

  • Free tier available
  • No credit card required

Get More AI Power
Pay Less

Join developers & vibe coders building AI apps with deAPI. No credit card, zero setup headaches — just pure, instant AI magic.

Need enterprise pricing or SLA?

Talk to Sales