PopNow APIpopnow.ai
Get API key

by Alibaba

Open model with 2K output and transparent backgrounds

alibaba/qwen-image-2.1/text-to-imageFrom 4 creditsper image · $0.04
Try in PlaygroundGet API key
  • Up to 2K
  • Up to 10 reference images
  • 15 aspect ratios
  • Create Image
  • Edit Image

About Qwen Image 2.1

Qwen Image 2.1 is Alibaba's newest open-weight image model, published here the day it shipped.

Call it with the model name alibaba/qwen-image-2.1/text-to-image on POST /jobs/createTask, from 4 credits per image ($0.04). New accounts get 30 free credits to try it in the Playground first.

Introduction

Qwen Image 2.1 Text to Image turns a written brief into one image per request. Alibaba's Qwen team open-weighted the model on 21 September 2026 and it went live here the same day, hosted, with no weights to download and no GPU to rent.

What sets it apart on this catalogue is not a feature — it is what is missing.

Choose a Qwen Image 2.1 mode by starting material

Starting materialMode
A written brief and nothing elseQwen Image 2.1 Text to Image
One to ten source images to work fromQwen Image 2.1 Image Editing
A brief plus your own LoRA weightsQwen Image 2.1 LoRA

Key features

Fifteen ratios, composed rather than cropped

The composition is built at the ratio you request, so a panoramic frame is genuinely staged for its width instead of arriving as the middle slice of a square.

Request parameters

ParameterRequiredDescription
seedNoReuse the same number to get a repeatable result. ≥ 0 · ≤ 2147483647
promptYesDescribe the subject, composition, lighting, and any wording to render.
backgroundNoKeep, remove or replace the background. opaque · transparent · Default: opaque
resolutionNoOutput size. Bigger sizes look sharper and cost more. 1k · 1.5k · 2k · Default: 1k
aspect_ratioNoThe shape of the frame: wide, square or tall. 1:1 · 16:9 · 9:16 · 4:3 · 3:4 · 3:2 · 2:3 · 21:9 · 9:21 · 2:1 · 1:2 · 3:1 · 1:3 · 5:4 · 4:5 · Default: 1:1
output_formatNoFile type of the result. jpeg · png · webp · Default: jpeg
enable_prompt_expansionNoLets the model add detail to a short prompt. Default: true

Pricing

Prices are in credits, the same credits you use on the website (1 credit = $0.01). The hold is taken when the task is accepted and settled to the actual charge when it finishes; failed tasks are refunded.

OptionCredits per image≈ USD
resolution 1K3.6$0.036
resolution 1.5K7.2$0.072
resolution 2K7.2$0.072

Each task is rounded up to whole credits, so one run at the lowest tier costs 4 credits per image ($0.04).

For an exact number before you run, send the same body to POST /jobs/quote.

Use cases

High-volume concept passes

Run the spread, pick the survivors, promote those to 2k.

Wide banners and phone-first verticals

3:1 and 21:9 for site headers and cinematic plates; 9:21 and 1:3 for full-bleed mobile. Staged at the ratio, not cropped to it.

Character starting frames

Generate the character here, then move to image editing and feed that frame back as a reference to hold identity while you change wardrobe, light or setting.

Prompt guide & pro tips

Pick the ratio and the tier before writing

Both decisions change the picture more than any adjective will. Choose the shape you will publish at, and stay at 1k until the composition is settled.

Put exclusions inside the prompt

There is no negative prompt on this family. With 5,000 characters available, state what belongs in the frame and then state what must not appear — duplicated limbs, extra figures, clothing you did not ask for.

Keep scenes to one or two figures at 2k

Anatomy is where this model breaks first. Single figures and pairs hold together; crowded multi-figure compositions at the top tier can duplicate or merge limbs. If a scene needs a crowd, build it by editing rather than asking for it all at once.

Treat the seed as a nudge

The same seed twice does not return the same file. Use it to keep a set coherent, and archive the asset when a frame is final.

API quick start

Call the Qwen Image 2.1 API in three steps

  1. Create an API key. Sign in to PopNow and create a key in the API console. Keys start with sk-popnow- and use the same credits as the website.
  2. Send the request. POST /jobs/createTask with model alibaba/qwen-image-2.1/text-to-image and an input object that follows the parameter table. The response returns a task ID straight away.
  3. Get the result. Poll GET /jobs/recordInfo with the task ID, or pass a callBackUrl and we post the result to it. Download the output links when the task succeeds.
# 1. Create the task. Keep the Idempotency-Key if you retry after a network error.
export IDEMPOTENCY_KEY="$(uuidgen)"
curl -X POST https://api.popnow.ai/api/v1/jobs/createTask \
  -H "Authorization: Bearer $POPNOW_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $IDEMPOTENCY_KEY" \
  -d '{
  "model": "alibaba/qwen-image-2.1/text-to-image",
  "input": {
    "prompt": "A ceramic teapot on a linen cloth, soft window light, muted palette",
    "aspect_ratio": "1:1",
    "resolution": "1k",
    "background": "opaque",
    "output_format": "jpeg"
  }
}'

# 2. Copy data.taskId from the response, then poll until state is succeeded, failed, canceled or expired.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
  -H "Authorization: Bearer $POPNOW_API_KEY"

Replace the prompt and any links with your own. The API tab has the response, polling and callback reference.

Qwen Image 2.1 API questions

How much does the Qwen Image 2.1 API cost?

Qwen Image 2.1 starts at 4 credits ($0.04) per image with Create Image, its cheapest task. Prices by option: 1K 3.6 credits per image, 1.5K 7.2 credits per image, 2K 7.2 credits per image. Credits are the same as on the website (1 credit = $0.01), new accounts get 30 free credits, and failed tasks are refunded.

What is the model name for Qwen Image 2.1 in the API?

Put alibaba/qwen-image-2.1/text-to-image for Create Image; alibaba/qwen-image-2.1/edit for Edit Image in the model field of POST /jobs/createTask.

Is this the model Alibaba just open-sourced?

Yes. Qwen-Image-2.1 was open-weighted on 21 September 2026 and went live here the same day, as a hosted API with no setup, no GPU and no weights to download.

Can I edit just one part of an image instead of the whole frame?

Yes, and we verified it. Mark the area on the reference image — a drawn circle or a painted patch — and describe the change inside it, including an instruction to remove the marking. In our test the edit landed exactly inside the marked region and the rest of the frame was untouched.

How many reference images can image editing take?

One to ten. Name in the prompt what each one contributes, because the model does not assign roles by itself. Every reference you add raises the quote, so send only the ones doing work.

Does a fixed seed reproduce the same image?

No. We sent the same prompt with the same seed twice and got two different frames. Use the seed to keep a series consistent in feel, and keep the returned asset when you need that exact image again.

Is there a negative prompt?

Not on this family. Put exclusions in the main prompt — it holds 5,000 characters, which is ample room to state both what should be in frame and what should not.

What are the limits of the Qwen Image 2.1 API?

Resolutions: 1K · 1.5K · 2K; Aspect ratios: 1:1 · 16:9 · 9:16 · 4:3 · 3:4 · 3:2 +9; Prompt length (characters): 5,000. Requests outside these limits are rejected before anything is charged.

Can I try Qwen Image 2.1 without writing code?

Yes. The Playground runs Qwen Image 2.1 on your PopNow credits, needs no API key, and shows the matching code for every run.

All Qwen Image models

Qwen Image 2.1 Turbo is faster and cheaper for drafts, and Pro adds finer portrait detail. The standard model sits between them, with masked edits and transparent cut-outs.

More about Qwen Image 2.1