Qwen Image - 2512

Try Qwen Image - 2512 in the Workbench

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

Model ID: qwen-image-2512 Qwen Image 2512 is a Large Vision Model. It excels in text-to-image generation with improved realism in human portraits, finer natural textures, and stronger text rendering, particularly for Chinese characters. Some other noteworthy use cases of Qwen Image 2512 include instruction-based image editing and generating structured visuals like posters or UI mockups.

Metric	Value
Parameter Count	20 billion
Mixture of Experts	Unknown
Context Length	Unknown
Multilingual	Yes
Quantized*	Unknown

*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
Async
Async with SSE

See the image generation reference for more details.

Minimal
All parameters

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-2512",
  "prompt": "A bald eagle sitting on a vast frozen lake, centered in the shot facing the camera. The eagle is in it'\''s natural habitat and being photographed from a medium distance. The background is a vast lake surrounded by a forest going up a hill. Photorealistic - it is high enough quality that it could be used for a National Geographic cover, but is just a stand alone photo without any graphics."
}'

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-2512",
  "prompt": "A bald eagle sitting on a vast frozen lake, centered in the shot facing the camera. The eagle is in it'\''s natural habitat and being photographed from a medium distance. The background is a vast lake surrounded by a forest going up a hill. Photorealistic - it is high enough quality that it could be used for a National Geographic cover, but is just a stand alone photo without any graphics.",
  "negative_prompt": " ",
  "aspect_ratio": "16:9",
  "image_size": "optimize_for_quality",
  "num_inference_steps": 30,
  "guidance": 3,
  "output_format": "webp",
  "output_quality": 80,
  "disable_safety_checker": false
}'

See the async queue reference for more details.

Minimal
All parameters

# 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-2512",
  "prompt": "A bald eagle sitting on a vast frozen lake, centered in the shot facing the camera. The eagle is in it'\''s natural habitat and being photographed from a medium distance. The background is a vast lake surrounded by a forest going up a hill. Photorealistic - it is high enough quality that it could be used for a National Geographic cover, but is just a stand alone photo without any graphics."
}' | 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."

# 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-2512",
  "prompt": "A bald eagle sitting on a vast frozen lake, centered in the shot facing the camera. The eagle is in it'\''s natural habitat and being photographed from a medium distance. The background is a vast lake surrounded by a forest going up a hill. Photorealistic - it is high enough quality that it could be used for a National Geographic cover, but is just a stand alone photo without any graphics.",
  "negative_prompt": " ",
  "aspect_ratio": "16:9",
  "image_size": "optimize_for_quality",
  "num_inference_steps": 30,
  "guidance": 3,
  "output_format": "webp",
  "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."

See the async queue reference for more details.

Minimal
All parameters

# 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-2512",
  "prompt": "A bald eagle sitting on a vast frozen lake, centered in the shot facing the camera. The eagle is in it'\''s natural habitat and being photographed from a medium distance. The background is a vast lake surrounded by a forest going up a hill. Photorealistic - it is high enough quality that it could be used for a National Geographic cover, but is just a stand alone photo without any graphics."
}' | 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 .

# 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-2512",
  "prompt": "A bald eagle sitting on a vast frozen lake, centered in the shot facing the camera. The eagle is in it'\''s natural habitat and being photographed from a medium distance. The background is a vast lake surrounded by a forest going up a hill. Photorealistic - it is high enough quality that it could be used for a National Geographic cover, but is just a stand alone photo without any graphics.",
  "negative_prompt": " ",
  "aspect_ratio": "16:9",
  "image_size": "optimize_for_quality",
  "num_inference_steps": 30,
  "guidance": 3,
  "output_format": "webp",
  "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 .

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-2512

Request parameters

Required parameters

Field	Type	Default	Description
`prompt`	`string`	`"A bald eagle sitting on a vast frozen lake, centered in the shot facing the camera. The eagle is in it's natural habitat and being photographed from a medium distance. The background is a vast lake surrounded by a forest going up a hill. Photorealistic - it is high enough quality that it could be used for a National Geographic cover, but is just a stand alone photo without any graphics."`	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`	`"webp"`	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.

Inference API

Try Qwen Image - 2512 in the Workbench

​Example request

​Fetch model details

​Request parameters

​Required parameters

​Optional parameters

Example request

Fetch model details

Request parameters

Required parameters

Optional parameters