✦

qwen2-1/text-to-image

Name: Qwen Image 2.1 API
Brand: Alibaba

Commercial usePart of the Alibaba API family — browse all models →

Access Qwen Image 2.1 API on ModelFold for efficient image generation and editing. Get affordable pricing, free credits, and simple API integration.

Model Type:

Pricing: 11 credits / image.

Playground

Pre-filled from the model spec — run it as-is, or tweak any field first.

Ready

Prompt

Create a horizontal 3:2 botanical art poster photographed directly from above. On a rich cobalt-blue matte surface, arrange fresh flowers into the exact readable phrase "ModelFold AI". The letters themselves are physical floral sculptures, not printed text and not typography placed over an image.

Build the letterforms from densely arranged coral-orange ranunculus, pale peach carnations, and small cream chrysanthemums. Use flower heads of different sizes to create deliberate thick and thin strokes while preserving clean, recognizable letter shapes. Preserve the exact capitalization: uppercase K, lowercase i and e, followed by a clear space, then uppercase A and I. Keep the counters and gaps open so the phrase reads immediately.

Make the floral lettering the dominant central subject, occupying roughly two-thirds of the image width. Allow a few short stems and delicate leaves to extend naturally beyond the letter edges, with just three or four loose petals nearby. Maintain generous untouched blue space around the arrangement.

Use directional morning sunlight from the upper left to reveal translucent petal edges, tightly layered blooms, and crisp but delicate shadows cast onto the blue surface. Combine the precision of a contemporary exhibition poster with the tactile beauty of real floral craftsmanship. Bold color contrast, elegant spacing, finely resolved botanical details.

Describe the image you want to generate. Any language is supported, up to 5000 characters.

Aspect ratio

Output aspect ratio. The actual pixel size also depends on the resolution tier.

Resolution

Output resolution tier. Only 1K and 2K are supported. 2K takes noticeably longer to generate.

background

Background type. transparent outputs a PNG or WebP with a real alpha channel and cannot be used with JPEG. When using transparent, describe only the subject — prompts that mention a background, scene, surface, etc. may produce a non-transparent result.

output_format

Output image format. JPEG has no alpha channel, so it cannot be combined with a transparent background.

enhance_prompt

Rewrites the prompt into a fuller scene description before generating, which noticeably improves quality. Enabled by default (also when the parameter is omitted); pass false to turn it off.

seed

The same seed with the same prompt and parameters reproduces the same image on the same model version. The seed actually used is returned with the result.

nsfw_checker

A configurable parameter. Defaults to true in the Playground.

Balance: —Cost11 credits

Result

History

Sample output for this variant — press Run to generate your own.

Explore more Image models

More AI models from Alibaba

• Alibaba

HappyHorse-1.1

Latest and popular AI models

≡

README

Complete guide to using Qwen Image 2.1

Qwen Image 2.1 API

Access Qwen Image 2.1 API on ModelFold for efficient image generation and editing. Get affordable pricing, free credits, and simple API integration.

Models and variants

Select a model type for your task. The Playground uses the selected variant’s parameters and examples.

Text To Image

Model ID: qwen2-1/text-to-image. Check this variant’s required inputs and supported reference formats before submitting.

Image To Image

Model ID: qwen2-1/image-to-image. Check this variant’s required inputs and supported reference formats before submitting.

How to use

1
Select a variant
Choose a model type at the top of this page and review its rates and input requirements. Variants may support different reference media and outputs.
2
Prepare inputs
Fill in the Playground fields, supply any required image, video or audio, and adjust the available parameters. Examples demonstrate the workflow; use reference material you have permission to use.
✓
Review the result
Sign in, submit the task, and preview or download the result when it is ready. Task status is available in your account logs. For automation, use the API example below and the model documentation.

Parameters and pricing

The price table shows current ModelFold rates. Charges depend on the selected variant and its billing parameters. Size, resolution, duration, reference media or output count affect pricing only where specified by the model’s billing rules. Review the Playground estimate and your balance before submitting. Use the model ID and fields for your selected variant. Image, video and audio tasks have different inputs. For asynchronous tasks, wait for the status update rather than resubmitting while a result is pending.

Frequently asked questions

Are examples generated automatically?⌄

Examples are static demonstration assets. Browsing the page or switching variants does not generate content. Submitting a task calls the model and consumes credits at the displayed rates.

How should I choose parameters?⌄

Choose the model type first, then provide the fields and reference material its form requires. Do not assume every variant shares the same resolutions, durations or input limits.

How can I integrate it?⌄

Create an API key in your account, then follow the API example and model documentation. Keep the key on your server, outside browser code and public repositories.

Rate card

text to image	11 credits image
image to image	6 credits image

Flat price per run — it does not change with duration.

Quick start

curl https://modelfold.ai/v1/images/generations \
  -H "Authorization: Bearer $MODELFOLD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"qwen2-1/text-to-image","prompt":"..."}'