Qwen Image 2.0 Edit is an advanced image-editing model with improved quality and better understanding of instructions. Up to 2k. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Siap
/filters:quality(85)/examples/4fde2dd1ffee4af38c1593e33ddcf61d/1783683596765191929_inwFPoxH.webp)
$0.03per run·~33 / $1
/filters:quality(82)/examples/4fde2dd1ffee4af38c1593e33ddcf61d/1783683596765191929_inwFPoxH.webp)
STYLE: Emphasize photographic qualities like camera settings, depth of field, and lighting. A candid, high-resolution group photo captured with a wide-angle lens, shallow depth of field, and natural ambient lighting. The individuals in Figure 1 and Figure 2 are positioned in a tight, casual formation, smiling slightly or looking toward the camera with relaxed expressions. Their clothing and background suggest a real-world, outdoor setting with soft bokeh and diffused daylight. The composition is centered, with natural depth of field emphasizing the group while blurring the periphery. Shot on film simulation with subtle grain, warm color grading, and realistic lens distortion to enhance authenticity.
/filters:quality(82)/examples/fead03a922cfdf3c5799cd508b049a09/1783683599776514949_hKEOX6fp.webp)
STYLE: Emphasize photographic qualities like camera settings, depth of field, and lighting. A vibrant, sunlit beach scene captured with a wide-angle lens, shallow depth of field, and natural golden-hour lighting. A young man in casual beachwear—linen short-sleeve shirt left slightly unbuttoned, rolled-up chino shorts, and leather flip-flops—stands barefoot on soft sand, smiling confidently at the camera. His hair is lightly tousled by the sea breeze, with a pair of aviator sunglasses resting on his head, and his expression radiates ease and carefree energy. The background features blurred turquoise waves and distant palm trees, creating a dreamy bokeh effect. Shot in candid-style beach photography with warm tones, high dynamic range, and realistic textures. Medium shot, eye-level, capturing his full upper body and surroundings with a natural, inviting atmosphere.
/filters:quality(82)/examples/b0ab31a6dad53fb98c599880421c9c5f/1-37aa4fc5c95d.webp)
Move the dancer onto a grand theater stage during a performance. Keep her pose and grey leotard, but add a dramatic single spotlight from above, dark velvet curtains, floating dust in the light beam and a soft haze, cinematic stage photography.
/filters:quality(82)/examples/95ad5f93771463afb0b9d9d3a55a1548/1-c401b3fbbf1f.webp)
Turn this photo into a food magazine cover. Keep the pancakes as the hero image, add the magazine title "SUNDAY BRUNCH" in bold serif at the top, and cover lines "50 Easy Weekend Recipes" and "The Perfect Fluffy Stack" on the side, clean modern layout.
/filters:quality(82)/examples/f16b531f4b73e82351fa13a714d577a6/1-87ba829d5fac.webp)
Place the fennec fox from Figure 1 sitting on the grassy cliff in front of the lighthouse from Figure 2, looking out at the ocean at sunset, warm golden light and long shadows, photorealistic.
Qwen Image 2.0 Edit is an image-editing model for transforming existing images with natural-language instructions. Upload 1 to 3 reference images, describe the edit you want, and generate a refined image while preserving the visual context from your inputs.
Instruction-based image editing Modify, restyle, or enhance uploaded images using a simple text prompt.
Multi-image input Supports up to 3 input images for edits, references, or visual context.
Strong prompt understanding Follows detailed Chinese or English editing instructions for targeted changes.
High-resolution workflow Supports images from 384 to 3072 pixels on each dimension, with output up to 2k.
Reproducible results Set a seed when you need repeatable generations.
| Parameter | Required | Description |
|---|---|---|
| prompt | Yes | Text instruction describing the desired edit. Supports Chinese and English, up to 800 characters. |
| images | Yes | Input images for editing. Upload 1 to 3 images, each 384-3072px per dimension. |
| seed | No | Random seed for reproducibility (-1 for random, 0-2147483647 for a fixed seed). |
| Output | Cost |
|---|---|
| Per image edit | $0.03 |
prompt and images are required.images accepts 1 to 3 images.Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/qwen-image-2.0/edit with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Qwen Image 2.0 Edit below.
set -euo pipefail
: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"
REQUEST_BODY=$(cat <<'JSON'
{
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"images": [
"https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
]
}
JSON
)
# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
-X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/qwen-image-2.0/edit" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d "$REQUEST_BODY")
TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
printf 'Submission response did not contain a prediction id
' >&2
exit 1
fi
RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
# 2. Poll until the prediction finishes.
while true; do
RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
-H "Authorization: Bearer $WAVESPEED_API_KEY")
RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
case "$STATUS" in
completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
failed|cancelled|timeout|deleted) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
*) sleep 2 ;;
esac
doneconst submitUrl = "https://api.wavespeed.ai/api/v3/wavespeed-ai/qwen-image-2.0/edit";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');
async function requestJson(url, options = {}) {
const response = await fetch(url, options);
if (!response.ok) throw new Error(await response.text());
return response.json();
}
// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
method: "POST",
headers: {
"Authorization": `Bearer ${apiKey}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"images": [
"https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
]
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;
// 2. Poll until the prediction finishes.
while (true) {
const resultBody = await requestJson(resultUrl, {
headers: { "Authorization": `Bearer ${apiKey}` },
});
const result = resultBody.data ?? resultBody;
if (result.status === "completed") {
console.log(result.outputs);
break;
}
if (["failed", "cancelled", "timeout", "deleted"].includes(result.status)) throw new Error(JSON.stringify(result));
await new Promise(resolve => setTimeout(resolve, 2000));
}import json
import os
import time
from urllib.request import Request, urlopen
api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
"prompt": "A cinematic shot of a city at sunset, soft golden light",
"images": [
"https://interactive-examples.mdn.mozilla.net/media/cc0-images/painted-hand-298-332.jpg"
]
}
def request_json(url, data=None):
request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
with urlopen(request) as response:
return json.load(response)
# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/wavespeed-ai/qwen-image-2.0/edit", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
raise RuntimeError("Submission response did not contain a prediction id")
result_url = f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"
# 2. Poll until the prediction finishes.
while True:
result_body = request_json(result_url)
result = result_body.get("data", result_body)
status = result.get("status")
if status == "completed":
print(result.get("outputs", []))
break
if status in {"failed", "cancelled", "timeout", "deleted"}:
raise RuntimeError(result)
time.sleep(2)Qwen Image 2.0 Edit is a WaveSpeedAI model for image editing, exposed as a REST API on WaveSpeedAI. Qwen Image 2.0 Edit is an advanced image-editing model with improved quality and better understanding of instructions. Up to 2k. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing. You can call it programmatically or try it from the playground above.
POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates Python, JavaScript, and cURL examples for submitting requests and polling results. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/wavespeed-ai/qwen-image-2.0-edit.
Qwen Image 2.0 Edit starts at $0.03 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.
Key inputs: `prompt`, `images`, `seed`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/wavespeed-ai/qwen-image-2.0-edit.
Reported generation time on WaveSpeedAI is around 11 seconds per request. This is an estimate, not a latency guarantee; queue time and input settings can change the total wait. live status is visible in the prediction record.
Commercial usage rights depend on the model's license, set by its provider (WaveSpeedAI). Check the provider's applicable terms and WaveSpeedAI's Terms of Service before commercial use.