Nano Banana 2Nano Banana 2 is live
WaveSpeed.ai
ホーム/探索/Qwen Image 2 Models/wavespeed-ai/qwen-image-2.0/text-to-image
text-to-image

text-to-image

Qwen Image 2.0

wavespeed-ai/qwen-image-2.0/text-to-image

Qwen Image 2.0 is an advanced text-to-image model with enhanced image quality and improved prompt understanding. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.

Input
width
height
1024 × 1024 px
Range: 256 - 1536

Idle

A Black woman with waist-length loc'd hair caught mid-spin in a dance, her locs fanning out radially following centrifugal motion, some locs wrapped with gold thread, some with cowrie shells, some with blue beads. Individual locs are clearly separated and countable. She is wearing a flowing white dress also caught in the spin motion. Droplets of water flying off the loc tips against a dark background, lit by a single overhead spotlight creating a halo effect

このリクエストには1回あたりで$0.03の費用がかかります。

$1でおよそ33回実行できます。

もうひとつお知らせ：

サンプルすべて表示

A Black woman with waist-length loc'd hair caught mid-spin in a dance, her locs fanning out radially following centrifugal motion, some locs wrapped with gold thread, some with cowrie shells, some with blue beads. Individual locs are clearly separated and countable. She is wearing a flowing white dress also caught in the spin motion. Droplets of water flying off the loc tips against a dark background, lit by a single overhead spotlight creating a halo effect
A glass table with exactly 5 red apples arranged in a perfect pentagon pattern, reflected clearly on the glass surface below. Behind the table, a calico cat sits on the left and a golden retriever lies on the right. Through the window behind them, a crescent moon is visible in a twilight sky.
An underwater living room with a burning fireplace, the flames flickering normally despite being submerged, a leather sofa floating slightly above the sandy ocean floor, tropical fish swimming between bookshelves filled with dry intact books, caustic light patterns dancing on the ceiling
A young woman with slender fingers delicately threading a needle, the thread visibly passing through the needle's eye, her left hand holding the needle steady between thumb and index finger while her right hand pinches the thread tip. She wears a different ring on each finger — silver, gold, jade, ruby, and pearl. Soft window light from the left, shallow depth of field, shot on 85mm f/1.4
An infographic explaining responsive web design breakpoints. Side-by-side comparison showing the same website layout adapting across four devices: mobile (375px), tablet (768px), laptop (1024px), and desktop (1440px). Clean vector style with labeled arrows showing how grid columns, navigation, and content blocks reflow at each breakpoint. Dashed guide lines indicating margin, padding, and column widths. White background, purple and light gray color scheme. Modern flat UI design with device mockup frames and pixel dimension annotations. Show in all English words

README

Qwen Image 2.0 Text-to-Image

Qwen Image 2.0 is Alibaba's advanced text-to-image model that generates high-quality images from detailed text descriptions. With exceptional prompt following, flexible aspect ratios, and custom resolution support, it excels at rendering complex scenes with fine details like hair, accessories, and textures.

Why Choose This?

  • Strong prompt adherence Excels at following detailed, complex prompts with multiple elements and attributes.

  • Fine detail rendering Excellent at rendering intricate details like hair textures, jewelry, and clothing accessories.

  • Flexible aspect ratios Multiple presets including 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, and 2:3.

  • Custom resolution Adjustable width and height from 256 to 1536 pixels.

  • Prompt Enhancer Built-in tool to automatically improve your descriptions.

Parameters

ParameterRequiredDescription
promptYesText description of the desired image
sizeNoAspect ratio preset: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3
widthNoCustom width in pixels (range: 256–1536)
heightNoCustom height in pixels (range: 256–1536)
seedNoRandom seed for reproducibility (-1 for random)

How to Use

  1. Write your prompt — describe the image in detail, including specific attributes, styles, and elements.
  2. Choose size — select a preset aspect ratio or customize width/height.
  3. Use Prompt Enhancer (optional) — click to automatically refine your description.
  4. Set seed (optional) — for reproducible results.
  5. Run — submit and download your generated image.

Pricing

OutputCost
Per image$0.03

Best Use Cases

  • Detailed Character Art — Generate characters with specific attributes like hair styles, clothing, and accessories.
  • Portrait Photography — Create photorealistic portraits with fine details.
  • Fashion & Style — Visualize outfits, hairstyles, and jewelry with precision.
  • Concept Art — Render complex scenes with multiple elements.
  • Cultural & Artistic — Generate images with specific cultural elements and decorations.

Pro Tips

  • Use highly detailed prompts — the model excels at following complex descriptions with multiple attributes.
  • Describe specific details like "waist-length loc'd hair," "gold thread," "cowrie shells," or "blue beads" for precise rendering.
  • Include motion and pose descriptions for dynamic images (e.g., "caught mid-spin in a dance").
  • Match aspect ratio to your content: 1:1 for portraits, 16:9 for landscapes, 9:16 for full-body shots.
  • Use the same seed to reproduce or iterate on specific results.

Notes

  • Prompt is the only required field.
  • Resolution range: 256–1536 pixels for both width and height.
  • Default size is 1024×1024 (1:1).
  • Ensure your prompts comply with content guidelines.

Related Models