wavespeed-ai/qwen-image/text-to-image-lora

Qwen-Image LoRa — a 20B MMDiT model for next-gen text-to-image generation with LoRA.

DocumentationDoc

prompt*

size

width

height

loras

pathscale

seed

output_format

enable_sync_mode

If set to true, the function will wait for the image to be generated and uploaded before returning the response. It allows you to get the image directly in the response. This property is only available through the API.

enable_base64_output

If enabled, the output will be encoded into a BASE64 string instead of a URL. This property is only available through the API.

Idle

Super Realism portrait of a teenager woman of African descent, serene calmness, arms crossed, illuminated by dramatic studio lighting, sunlit park in the background, adorned with delicate jewelry, three-quarter view, sun-kissed skin with natural imperfections, loose shoulder-length curls, slightly squinting eyes, environmental street portrait with text "WaveSpeedAI" on t-shirt.

Your request will cost $0.025 per run.

For $1 you can run this model approximately 40 times.

One more thing:

ExamplesView all

A sophisticated woman in her early 30s, standing on a rooftop at golden hour, soft sunset light reflecting on her flawless skin. She wears a beige silk blouse tucked into high-waisted tailored trousers, gold hoop earrings, and pointed heels. Wind tousles her hair as she gazes over a modern city skyline, holding a coffee cup in one hand. Realistic textures, cinematic lighting, warm tones, ultra-realistic detail.

An elderly man with weathered hands and deep smile lines, wearing a brown leather apron over a faded flannel shirt. He sits at a wooden workbench filled with antique tools, in a cozy sunlit workshop with dust particles glowing in the light beams. He’s carefully carving a small wooden bird. Warm tones, detailed textures on skin and clothing, lifelike realism.

A man in a suit is standing in front of the window, looking at the bright moon outside the window. The man is holding a yellowed paper with handwritten words on it: "A lantern moon climbs through the silver night, Unfurling quiet dreams across the sky, Each star a whispered promise wrapped in light, That dawn will bloom, though darkness wanders by." There is a cute cat on the windowsill.

A trendy teenage girl with pink-dyed hair and a black leather jacket walking down a neon-lit alley on a rainy night. She holds a transparent umbrella with raindrops glistening on it, and wears checkered pants with chunky boots. Reflections on the wet pavement, cinematic urban lighting, hyperreal detail in facial expression and textures.

A confident businesswoman mid-stride outside a glass skyscraper in daylight. She's wearing a navy blue blazer over a white blouse, black pencil skirt, and carrying a sleek leather laptop bag. Hair pulled back, sunglasses on, caught mid-walk with a focused expression. Modern architecture background, strong sunlight and shadows, photo-realistic textures.

A young male chef with rolled-up sleeves, a clean white chef’s jacket, and an apron, plating a gourmet dish under focused kitchen lighting. Stainless steel kitchen environment, steam rising from a pan in the background. Tattoos on his forearms, intense concentration on his face, ingredients arranged in an elegant pattern on a dark ceramic plate.

A woman with curly hair tied loosely, wearing a paint-stained oversized white shirt, barefoot, standing in a spacious industrial loft with large windows and exposed brick walls. She’s holding a large brush, working on a colorful abstract canvas. Natural light pouring in, art supplies scattered around, expressive, richly detailed scene.

A young woman sitting alone in a laundromat at midnight, wearing headphones, staring at the rotating dryer drum, neon reflections on the glass, subtle expression of nostalgia on her face

README

Qwen-Image — a 20B MMDiT model for next-gen text-to-image generation. Especially strong at creating stunning graphic posters with native text. Now open-source.

Key Highlights:

SOTA text rendering — rivals GPT-4o in English, best-in-class for Chinese
In-pixel text generation — no overlays, fully integrated
Bilingual support, diverse fonts, complex layouts

Also excels at general image generation — from photorealistic to anime, impressionist to minimalist. A true creative powerhouse.