qwen-image-edit-2511

Qwen‑Image‑Edit‑2511 is an image editing model guided by text instructions. With about 20 billion parameters, it edits portraits and scenes while preserving identity and visual characteristics. It supports native output up to 2560x2560 pixels in 12 diffusion steps. Features include background changes, object addition, style transfer and detailed edits, with support for custom LoRAs.

• PROVIDER LOCATION: Non-EU
• PARAMETERS: ~20B
• MAX CONTEXT: N/A
• LICENSE: Apache 2.0
• FEATURES: Image editing with prompts, Multi-image input
• OUTPUT FORMATS: Image (PNG/JPEG)

• AI-assisted photo editing
• Background and style changes
• Post-production and creative retouching
• Visual content personalization

curl --request POST \
--url https://apiaruba.it/aiplatform/v1/images/edits \
--header 'content-type: multipart/form-data' \
--header 'x-aruba-api-key: *****' \
--form model=Qwen-Image-Edit-2511 \
--form 'prompt=genera una gift a partire dall'\''immagine caricata' \
--form 'image=@image_path'

{
"created": 1787586164,
"background": null,
"data": [
{
"b64_json": "*****",
"revised_prompt": null,
"url": null
}
],
"output_format": "png",
"quality": null,
"size": "512x512",
"usage": {
"total_tokens": 0,
"input_tokens": 0,
"input_tokens_details": {
"image_tokens": 0,
"text_tokens": 0
},
"output_tokens": 0
}
}

• Qwen‑Image‑2512

• Hugging Face
• Blog Qwen
• Demo