AI Object Eraser
Remove unwanted objects, people, text and distractions from your photos with AI.
Remove unwanted objects, people, text and distractions from your photos with AI.

Use AI to work on damaged, blurry or aged photos. Generated details may differ from the original, especially where the source image has lost information.

Use AI to remove watermarks, logos or other unwanted elements from an image. Only edit images you have permission to modify.

Remove watermarks from generated images using advanced AI inpainting technology.

Extend the edges of an image with AI-generated content designed to blend with the original.
Use AI Object Eraser to try removing unwanted elements from a photo. Describe what you want removed, and the selected model will generate a fill based on the surrounding image. Results can vary, particularly with complex backgrounds.
Describe what you want removed and let the selected AI model generate an edit. You do not need photo-editing software, but results may need review.
The model uses nearby textures, patterns and lighting as context when generating a fill. Results may vary.
Say what you want removed, then review the generated image.
You can name several objects in one prompt. Results depend on the image and selected model.
Available resolutions depend on the selected model. Nano Banana Pro offers 1K, 2K and 4K options.
1. Sign in and upload a photo. 2. Choose a supported model and check its credit cost. 3. Describe what you want removed and generate the edit. 4. Review and download the result if it works for you.
Start with a clear, well-lit photo. Describe the object and its location precisely, and leave enough surrounding context for the model to work with. Detailed or patterned backgrounds can be harder to fill; review the result carefully.
You can ask it to remove unwanted objects, people, text, non-logo watermarks, blemishes, power lines, bins, photobombers and other distracting elements. Results depend on the image and selected model.
It can attempt to fill the removed area using the surrounding image as context. Results vary, especially with intricate textures, patterns or lighting.
You can describe several objects in one prompt. Whether they are all removed as intended depends on the image and selected model.
The selected model generates a fill for the edited area, so the result may differ from the original and details can change. A clear, high-resolution source image can give the model more context.
New users may receive credits to try the tool. Sign in to check your balance, the selected model and its credit cost. Plan features and access vary; see the plan details for current terms.
Output resolution depends on the selected model and its available settings. For example, Nano Banana Pro offers 1K, 2K and 4K options; other models may differ.
Generation time varies with the selected model, image and demand. Check the task status or History for updates.
Whether you can use an edited image commercially depends on the selected model's terms and any rights in the source image. Check the applicable terms before use.

GPT Image 2 is an OpenAI image model for generating and editing images. It can render text in multiple languages and ...

Generate and edit images with Nano Banana Pro. Sign-in and account credits are required; review the displayed cost be...
Create videos from text prompts, animate an image or use video input in supported modes. Choose a generation mode and...

Create videos from text prompts or images with Sora 2. Choose from the available options, then review the displayed c...
ByteDance's AI video model combines text, images, video clips and audio in one prompt. Use its @-reference system to ...