Available now

Qwen Add Background: background generation

By Alibaba

Qwen Add Background takes an object shot on a white or plain background and places it in a realistic scene that you describe.

Model ID
Maker
Alibaba

Input

Fields marked * are required. Review the price before generating.

Provide an image with a white or clean background.

Uploading a file needs an account. Create account

JPEG, PNG, WebP · up to 25 MB

If not provided, the size of the final input image will be used.

Describe the background/scene you want to add behind the object. The model will remove the white background and add the specified environment.

Example prompt. Edit it or write your own.

Additional settings

The CFG (Classifier Free Guidance) scale. Controls how closely the model follows the prompt.

The number of inference steps to perform.

Acceleration level for image generation. 'regular' balances speed and quality.

Random seed for reproducibility. Same seed with same prompt will produce same result.

The scale factor for the LoRA model. Controls the strength of the LoRA effect.

Price$0.06 / megapixel

You sign up first. Your settings are kept.

About this model

Overview

Upload a product or object photo with a clean background and write the setting you want behind it. The white background is replaced with that scene, and each run returns one to four images.

It is a LoRA on Qwen Image Edit Plus. The LoRA scale sets how strongly the effect is applied, and a negative prompt keeps unwanted elements out.

What you can build

  • Lifestyle scenes from plain packshots
  • Seasonal backdrops for one product photo
  • Store listing images in several settings

Prompting tips

  • Name the surface the object stands on as well as the room, for example a marble counter in a bright kitchen.
  • Describe the light, such as soft morning sun from the left, so the scene matches the product's shading.
  • Start from a sharp cutout on pure white; shadows and clutter in the source can end up in the scene.

What to check

Check subject edges, contact shadows and scale against the new background.

Inputs

  • Images (required): The URLs of the images to edit. Provide an image with a white or clean background.
  • Image Size (optional): The size of the generated image. If not provided, the size of the final input image will be used. Options: Square HD, Square, Portrait 4:3, Portrait 16:9, Landscape 4:3, Landscape 16:9.
  • Guidance Scale (optional): The CFG (Classifier Free Guidance) scale. Controls how closely the model follows the prompt. From 0 to 20.
  • Number of Inference Steps (optional): The number of inference steps to perform. From 2 to 50.
  • Acceleration (optional): Acceleration level for image generation. 'regular' balances speed and quality. Options: none, regular.
  • Negative Prompt (optional): The negative prompt for the generation.
  • Seed (optional): Random seed for reproducibility. Same seed with same prompt will produce same result.
  • Output Format (optional): The format of the output image. Options: png, jpeg, webp.
  • Number of Images (optional): Number of images to generate. From 1 to 4.
  • Prompt (optional): Describe the background/scene you want to add behind the object. The model will remove the white background and add the specified environment.
  • Lora Scale (optional): The scale factor for the LoRA model. Controls the strength of the LoRA effect. From 0 to 4.

Output and limits

  • Image sizes: Square HD (1024×1024), Square (512×512), Portrait 4:3 (768×1024), Portrait 16:9 (576×1024), Landscape 4:3 (1024×768), Landscape 16:9 (1024×576).
  • File formats: PNG, JPEG, WEBP.
  • Up to 4 images per run.
  • Small or dense text in the image can come out misspelled.
  • Hands, crowds and complex poses can show artifacts; generate a few variations and pick the best.
  • Some prompts or outputs can be refused by safety checks.

Price guide

  • 1 megapixel: $0.06 / megapixel