About 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 |
| Multilingual | Yes |
*Quantization is specific to the inference provider and the model may be offered with different quantization levels by other providers.
Ready to build with Qwen Image - 2512?
Try Qwen Image - 2512 in the Workbench to prompt it, compare outputs, and iterate on prompts without writing any code. When you're ready to ship, call the same model from our API and build your own apps on top of it.
curl -sSf -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
}'Request parameters
Every field Qwen Image - 2512 accepts in the request body. See the API reference for response formats.
https://hub.oxen.ai/api/ai/images/generate| Field | Type | Required | Default | Description |
|---|---|---|---|---|
prompt | string | Yes | — | Prompt for generated image |
negative_prompt | string | No | — | Negative prompt for generated image |
aspect_ratio | string | No | "16:9" | 1:116:99:164:33:43:22:3 |
image_size | string | No | "optimize_for_quality" | Image size for the generated imageoptimize_for_qualityoptimize_for_speed |
num_inference_steps | integer | No | 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 | No | 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 | integernullable | No | — | Random seed. Set for reproducible generation |
output_format | string | No | "webp" | Format of the output imageswebpjpgpng |
output_quality | integer | No | 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 | No | false | Disable safety checker for generated images. |