Qwen Image

An image generation foundation model in the Qwen series that achieves significant advances in complex text rendering and support for a wide range of artistic…

Try Qwen Image in the Workbench

Run this model interactively, tune parameters, and compare outputs.

Model ID: qwen-image

Qwen/Qwen-Image is an image generation model that excels in complex text rendering—including for both alphabetic and logographic languages such as English and Chinese—and precise image editing.

It is particularly strong in producing images with high-fidelity embedded text, making it well-suited for tasks where maintaining the integrity and clarity of text within generated images is critical. The model also provides consistent and realistic editing capabilities, such as style transfer, object addition/removal, and detailed attribute editing, with improved preservation of identity for people and products.

Some other noteworthy features of Qwen/Qwen-Image include robust support for image understanding tasks—such as object detection, semantic segmentation, depth and edge estimation, novel view synthesis, and super-resolution—and native integration with ControlNet for enhanced conditioning and control of outputs.

Metric	Value
Parameter Count	20 billion
Mixture of Experts	No
Context Length	Unknown
Multilingual	Yes
Quantized*	No

*Quantization is specific to the inference provider and the model may be offered with different quantization levels by other providers.

Example request

Use the Workbench as a request builder: configure parameters for this model in the UI, then open the API tab to copy the exact cURL or Python call.

Sync

See the image generation reference for more details.

Minimal

cURL

curl -X POST https://hub.oxen.ai/api/ai/images/generate \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OXEN_API_KEY" \
  -d '{
  "model": "qwen-image",
  "prompt": "A beautiful landscape painting of a serene lake with mountains in the background"
}'

import os
import requests

response = requests.post(
    "https://hub.oxen.ai/api/ai/images/generate",
    headers={
        "Content-Type": "application/json",
        "Authorization": f"Bearer {os.environ['OXEN_API_KEY']}",
    },
    json={
        "model": "qwen-image",
        "prompt": "A beautiful landscape painting of a serene lake with mountains in the background"
    },
)
response.raise_for_status()
print(response.json())

All parameters

cURL

curl -X POST https://hub.oxen.ai/api/ai/images/generate \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OXEN_API_KEY" \
  -d '{
  "model": "qwen-image",
  "prompt": "A beautiful landscape painting of a serene lake with mountains in the background",
  "negative_prompt": " ",
  "aspect_ratio": "16:9",
  "image_size": "optimize_for_quality",
  "num_inference_steps": 30,
  "guidance": 3,
  "output_format": "jpg",
  "output_quality": 80,
  "disable_safety_checker": false
}'

import os
import requests

response = requests.post(
    "https://hub.oxen.ai/api/ai/images/generate",
    headers={
        "Content-Type": "application/json",
        "Authorization": f"Bearer {os.environ['OXEN_API_KEY']}",
    },
    json={
        "model": "qwen-image",
        "prompt": "A beautiful landscape painting of a serene lake with mountains in the background",
        "negative_prompt": " ",
        "aspect_ratio": "16:9",
        "image_size": "optimize_for_quality",
        "num_inference_steps": 30,
        "guidance": 3,
        "output_format": "jpg",
        "output_quality": 80,
        "disable_safety_checker": false
    },
)
response.raise_for_status()
print(response.json())

Async

See the async queue reference for more details.

Minimal

cURL

# Enqueue, capture the generation id.
GEN_ID=$(curl -s -X POST https://hub.oxen.ai/api/ai/queue \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OXEN_API_KEY" \
  -d '{
  "model": "qwen-image",
  "prompt": "A beautiful landscape painting of a serene lake with mountains in the background"
}' | jq -r '.generations[0].generation_id')

# Poll the single generation until it 404s (terminal state).
while curl -s -o /dev/null -w "%{http_code}" \
    -H "Authorization: Bearer $OXEN_API_KEY" \
    "https://hub.oxen.ai/api/ai/queue/$GEN_ID" | grep -q "^200$"; do
  sleep 5
done
echo "Done. See the 'Async with SSE' tab to receive the result URL."

import os
import time
import requests

HEADERS = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {os.environ['OXEN_API_KEY']}",
}

enqueue = requests.post(
    "https://hub.oxen.ai/api/ai/queue",
    headers=HEADERS,
    json={
        "model": "qwen-image",
        "prompt": "A beautiful landscape painting of a serene lake with mountains in the background"
    },
)
enqueue.raise_for_status()
generation_id = enqueue.json()["generations"][0]["generation_id"]

while True:
    resp = requests.get(
        f"https://hub.oxen.ai/api/ai/queue/{generation_id}",
        headers=HEADERS,
    )
    if resp.status_code == 404:
        break
    time.sleep(5)
print("Done. See the 'Async with SSE' tab to receive the result URL.")

All parameters

cURL

# Enqueue, capture the generation id.
GEN_ID=$(curl -s -X POST https://hub.oxen.ai/api/ai/queue \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OXEN_API_KEY" \
  -d '{
  "model": "qwen-image",
  "prompt": "A beautiful landscape painting of a serene lake with mountains in the background",
  "negative_prompt": " ",
  "aspect_ratio": "16:9",
  "image_size": "optimize_for_quality",
  "num_inference_steps": 30,
  "guidance": 3,
  "output_format": "jpg",
  "output_quality": 80,
  "disable_safety_checker": false
}' | jq -r '.generations[0].generation_id')

# Poll the single generation until it 404s (terminal state).
while curl -s -o /dev/null -w "%{http_code}" \
    -H "Authorization: Bearer $OXEN_API_KEY" \
    "https://hub.oxen.ai/api/ai/queue/$GEN_ID" | grep -q "^200$"; do
  sleep 5
done
echo "Done. See the 'Async with SSE' tab to receive the result URL."

import os
import time
import requests

HEADERS = {
    "Content-Type": "application/json",
    "Authorization": f"Bearer {os.environ['OXEN_API_KEY']}",
}

enqueue = requests.post(
    "https://hub.oxen.ai/api/ai/queue",
    headers=HEADERS,
    json={
        "model": "qwen-image",
        "prompt": "A beautiful landscape painting of a serene lake with mountains in the background",
        "negative_prompt": " ",
        "aspect_ratio": "16:9",
        "image_size": "optimize_for_quality",
        "num_inference_steps": 30,
        "guidance": 3,
        "output_format": "jpg",
        "output_quality": 80,
        "disable_safety_checker": false
    },
)
enqueue.raise_for_status()
generation_id = enqueue.json()["generations"][0]["generation_id"]

while True:
    resp = requests.get(
        f"https://hub.oxen.ai/api/ai/queue/{generation_id}",
        headers=HEADERS,
    )
    if resp.status_code == 404:
        break
    time.sleep(5)
print("Done. See the 'Async with SSE' tab to receive the result URL.")

Async with SSE

See the async queue reference for more details.

Minimal

cURL

# Enqueue, capture the generation id.
GEN_ID=$(curl -s -X POST https://hub.oxen.ai/api/ai/queue \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OXEN_API_KEY" \
  -d '{
  "model": "qwen-image",
  "prompt": "A beautiful landscape painting of a serene lake with mountains in the background"
}' | jq -r '.generations[0].generation_id')

# Stream the SSE channel, grab the data line that follows a
# media_generation_completed event for our id, and pretty-print it.
curl -sN -H "Authorization: Bearer $OXEN_API_KEY" https://hub.oxen.ai/api/events \
  | awk -v id="$GEN_ID" '
    /^event: media_generation_completed$/ { expect=1; next }
    /^data: / && expect {
      payload = substr($0, 7)
      if (index(payload, "\"generation_id\":\"" id "\"")) { print payload; exit }
      expect = 0
    }
  ' | jq .

import json
import os
import requests

API_KEY = os.environ["OXEN_API_KEY"]
AUTH = {"Authorization": f"Bearer {API_KEY}"}

enqueue = requests.post(
    "https://hub.oxen.ai/api/ai/queue",
    headers={**AUTH, "Content-Type": "application/json"},
    json={
        "model": "qwen-image",
        "prompt": "A beautiful landscape painting of a serene lake with mountains in the background"
    },
)
enqueue.raise_for_status()
generation_id = enqueue.json()["generations"][0]["generation_id"]

with requests.get(
    "https://hub.oxen.ai/api/events",
    headers=AUTH,
    stream=True,
) as stream:
    event_name = None
    for line in stream.iter_lines(decode_unicode=True):
        if line.startswith("event: "):
            event_name = line.removeprefix("event: ")
        elif line.startswith("data: ") and event_name == "media_generation_completed":
            payload = json.loads(line.removeprefix("data: "))
            if payload.get("generation_id") == generation_id:
                print(payload)
                break

All parameters

cURL

# Enqueue, capture the generation id.
GEN_ID=$(curl -s -X POST https://hub.oxen.ai/api/ai/queue \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $OXEN_API_KEY" \
  -d '{
  "model": "qwen-image",
  "prompt": "A beautiful landscape painting of a serene lake with mountains in the background",
  "negative_prompt": " ",
  "aspect_ratio": "16:9",
  "image_size": "optimize_for_quality",
  "num_inference_steps": 30,
  "guidance": 3,
  "output_format": "jpg",
  "output_quality": 80,
  "disable_safety_checker": false
}' | jq -r '.generations[0].generation_id')

# Stream the SSE channel, grab the data line that follows a
# media_generation_completed event for our id, and pretty-print it.
curl -sN -H "Authorization: Bearer $OXEN_API_KEY" https://hub.oxen.ai/api/events \
  | awk -v id="$GEN_ID" '
    /^event: media_generation_completed$/ { expect=1; next }
    /^data: / && expect {
      payload = substr($0, 7)
      if (index(payload, "\"generation_id\":\"" id "\"")) { print payload; exit }
      expect = 0
    }
  ' | jq .

import json
import os
import requests

API_KEY = os.environ["OXEN_API_KEY"]
AUTH = {"Authorization": f"Bearer {API_KEY}"}

enqueue = requests.post(
    "https://hub.oxen.ai/api/ai/queue",
    headers={**AUTH, "Content-Type": "application/json"},
    json={
        "model": "qwen-image",
        "prompt": "A beautiful landscape painting of a serene lake with mountains in the background",
        "negative_prompt": " ",
        "aspect_ratio": "16:9",
        "image_size": "optimize_for_quality",
        "num_inference_steps": 30,
        "guidance": 3,
        "output_format": "jpg",
        "output_quality": 80,
        "disable_safety_checker": false
    },
)
enqueue.raise_for_status()
generation_id = enqueue.json()["generations"][0]["generation_id"]

with requests.get(
    "https://hub.oxen.ai/api/events",
    headers=AUTH,
    stream=True,
) as stream:
    event_name = None
    for line in stream.iter_lines(decode_unicode=True):
        if line.startswith("event: "):
            event_name = line.removeprefix("event: ")
        elif line.startswith("data: ") and event_name == "media_generation_completed":
            payload = json.loads(line.removeprefix("data: "))
            if payload.get("generation_id") == generation_id:
                print(payload)
                break

Fetch model details

The models endpoint returns the full model object, including its json_request_schema.

curl -H "Authorization: Bearer $OXEN_API_KEY" https://hub.oxen.ai/api/ai/models/qwen-image

Request parameters

Required parameters

Field	Type	Default	Description
prompt	string	"A beautiful landscape painting of a serene lake with mountains in the background"	Prompt for generated image

Optional parameters

Field	Type	Default	Description
negative_prompt	string	" "	Negative prompt for generated image
aspect_ratio	string	"16:9"	Aspect ratio for the generated image One of: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3.
image_size	string	"optimize_for_quality"	Image size for the generated image One of: optimize_for_quality, optimize_for_speed.
num_inference_steps	integer	30	Number of denoising steps. Recommended range is 28-50, and lower number of steps produce lower quality outputs, faster. Range: 1 – 50.
guidance	number	3	Guidance for generated image. Lower values can give more realistic images. Good values to try are 2, 2.5, 3 and 3.5 Range: 0 – 10.
seed	integer	—	Random seed. Set for reproducible generation
output_format	string	"jpg"	Format of the output images One of: webp, jpg, png.
output_quality	integer	80	Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs Range: 0 – 100.
disable_safety_checker	boolean	false	Disable safety checker for generated images.