seedinteger
Random seed for reproducibility (0-2147483647).
Qwen Image 3 Text to Image
alibaba/qwen-image-3/text-to-imageQwen Image 3 by Alibaba - generate stunning images from text prompts with state-of-the-art AI. Supports multiple aspect ratios, styles, and high-resolution output for creative and commercial use.
Try the model
Playground
Input
Text prompt describing the desired image. Supports Chinese and English. Max 5000 characters.
Additional Settings More
Customize your input with more control.
The format of the generated image. Allowed values: jpeg, png.
Random seed for reproducibility (0-2147483647).
16
Range: 1 to 6.
Output resolution tier used by fal billing. Allowed values: 1K, 2K.
ResultExample
What would you like to do next?
Examples
Select an example to load its inputs and result into the playground.
- Open result ↗
Input
{ "prompt": "A cute baby koala holding a card that says \"Qwen Image 3 is now available on fal\" while on a water slide" }
Human preference
Arena
Elo ratings from blind side-by-side votes, compared with other image and video models.
Rankings sourced from Artificial Analysis Arena
- Leaderboard
- Text to Image
- Rank
- #18 of 106
- Elo
- 1070 ±12
- Gap to #1
- −152
Text-to-image arena: people pick the better of two images generated from the same prompt, without seeing the model names.
- #13FLUX 3 Image1117±12
- #14MAI-Image-2.5-Pro1114±10
- #15Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)1107±10
- #16Seedream 5.0 Pro1100±11
- #17Qwen-Image-3.0-Pro1095±12
- #18Qwen-Image-3.01070±12
- #19Qwen-Image-2.1-Pro1056±12
- #20grok-imagine-image-quality1049±9
- #21FLUX 3 Image Klein1043±12
- #22Qwen-Image-2.11042±12
Qwen Image 3 Text to Image
Qwen Image 3 (Pro) generates photorealistic images and dense layouts such as posters, infographics, and slides, with accurate Chinese and English text rendering. Up to 6 images per request at 1K or 2K.
Fields
| Field | Type | Default | Notes |
|---|---|---|---|
prompt | string, required | — | Up to 5,000 characters. |
output_format | jpeg / png | png | Output file format. |
seed | integer | random | Fix it to compare prompt changes. |
num_images | integer 1–6 | 1 | Images to generate (1–6); each is billed. |
resolution | 1K / 2K | 1K | Sets the per-image rate. |
Billing
$0.04 per image at 1K and $0.075 at 2K, Alibaba's list price for Qwen Image 3.0 Pro.
| Images | 1K | 2K |
|---|---|---|
| 1 | $0.04 | $0.075 |
| 2 | $0.08 | $0.15 |
| 4 | $0.16 | $0.30 |
| 6 | $0.24 | $0.45 |
Failed runs are not charged.
Prompting
- Quote every piece of text that must appear and say where it goes.
- For infographics and slides, describe the layout region by region.
- Name the style explicitly: photo, flat illustration, 3D render.
Limits
- Up to 6 images per request.
Also on SandBase
Related: alibaba/qwen-image-3/edit (edit with Qwen Image 3), alibaba/qwen-image-2.
Start building
Send your first request
Submit this model through the SandBase Unified Run API.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/run" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "alibaba/qwen-image-3/text-to-image",
"prompt": "A cute baby koala holding a card that says \"Qwen Image 3 is now available on fal\" while on a water slide",
"num_images": 1,
"resolution": "1K",
"output_format": "png"
}
SANDBASE_JSON
)
run_id=$(printf '%s' "$result" | jq -r .id)
for attempt in $(seq 1 120); do
status=$(printf '%s' "$result" | jq -r .status)
case "$status" in completed|failed|timeout) break ;; esac
sleep 2
result=$(curl --fail-with-body --silent \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
"https://api.sandbase.ai/v1/run/$run_id")
done
status=$(printf '%s' "$result" | jq -r .status)
[ "$status" = completed ] || { echo "Generation ended: $status" >&2; exit 1; }
printf '%s\n' "$result"2. Authentication
Create a SandBase API key and set it in your server environment. All requests use Bearer authentication.
export SANDBASE_API_KEY="YOUR_API_KEY"Keep the key on your server. Do not expose it in browser code or commit it to a repository.
3. Queue
Submit a request
POST to /v1/run with this model ID and its inputs. The request example above includes submission and polling.
Fetch request status and result
Use the returned run ID to poll until the status is completed, failed or timeout. Read output only after completed.
curl "https://api.sandbase.ai/v1/run/$RUN_ID" \
-H "Authorization: Bearer $SANDBASE_API_KEY"4. Files
Hosted files
Pass a publicly accessible file URL in the model’s image, video or audio field. Supported formats and limits are shown beside each Playground input.
Uploading images
Use the upload or replace control on supported image fields in the Playground. Video URL fields accept a hosted driving video; they do not imply video-upload support.
5. Schema
Input
promptstringrequired
Text prompt describing the desired image. Supports Chinese and English. Max 5000 characters.
num_imagesinteger
Default: 1
Minimum: 1
Maximum: 6
resolutionstring
Output resolution tier used by fal billing.
Default: "1K"
Possible values: "1K", "2K"
output_formatstring
The format of the generated image.
Default: "png"
Possible values: "jpeg", "png"
{
"model": "alibaba/qwen-image-3/text-to-image",
"prompt": "A cute baby koala holding a card that says \"Qwen Image 3 is now available on fal\" while on a water slide",
"num_images": 1,
"resolution": "1K",
"output_format": "png"
}Output
A completed run exposes its result in output. The following is the model’s saved example, not a new generation.
[
{
"source": "Alibaba Model Studio schema mirror",
"source_url": "https://www.alibabacloud.com/help/en/model-studio/",
"url": "https://static.sandbase.ai/examples/6ae3c326-6c22-4cb5-9093-753b27bd5fe1/output/d5763339-81b8-4f20-9651-3faa3df34f52.png"
}
]