Available now

Qwen Remove Element: object removal

By Alibaba

Qwen Remove Element takes out the objects, people or text you name in a photo and leaves the rest of the image as it was.

Model ID
Maker
Alibaba

Input

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

The image containing elements to remove.

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.

Specify what element(s) to remove from the image (objects, people, text, etc.). The model will cleanly remove the element while maintaining consistency of the rest of the image.

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 an image and write what to remove, for example "the man in the background" or "the caption at the bottom". Each run returns up to four images in square, portrait or landscape sizes. A LoRA scale sets how strongly the removal effect is applied.

What you can build

  • Photos without tourists, cables or clutter
  • Product shots with stickers or labels taken off
  • Screenshots and images with captions removed

Prompting tips

  • Name each thing to remove plainly, with its place in the frame when there are several.
  • List several elements in one prompt when they should all go, such as "the bin and the parked bike".

What to check

Check the filled area and nearby subjects for unwanted replacements or leftover shadows.

Inputs

  • Images (required): The URL of the image containing elements to remove.
  • 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): Specify what element(s) to remove from the image (objects, people, text, etc.). The model will cleanly remove the element while maintaining consistency of the rest of the image.
  • 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