Qwen-Image-Edit-2511

Edit images with precise control over text, people, and products. This is Qwen’s 20 billion parameter image editing model that can combine multiple images, preserve identity, and edit text while keeping the original style intact.

What you can do

Multi-image editing

Combine multiple images in creative ways. You can merge people with other people, place people in new scenes, or add products to different contexts. The model works best with 1 to 3 input images and supports combinations like person + person, person + product, and person + scene.

Precise text editing

Add, remove, or modify text in images while preserving the original font, size, and style. The model supports both Chinese and English text editing, letting you directly edit posters, signboards, and other text-heavy images.

Semantic editing

Modify image content while preserving visual semantics. This lets you change poses, rotate objects, apply style transfers, or create variations of characters while maintaining their identity. You can transform portraits into different artistic styles or generate novel views of objects.

Appearance editing

Make surgical edits to specific regions while keeping everything else unchanged. Add or remove objects, change backgrounds, modify clothing, or adjust specific elements like the color of a single letter. The model pays attention to details like reflections and lighting consistency.

Identity preservation

Keep facial features, product identities, or character consistency intact across edits. Whether you’re editing portraits, product posters, or character designs, the model preserves what makes each subject recognizable.

How to get good results

Be specific in your prompts about what should change and what should stay the same. Instead of “make it better,” try “enhance the lighting and add warm sunset tones.”

For multi-image editing, clearly reference which elements come from which images. For example, “place the person from the first image on the left and the person from the second image on the right, standing side-by-side in a park.”

When working with people, reference specific characteristics you want to maintain like “preserve the facial features” or “keep the same hairstyle and expression.”

For text editing, mention if you want to preserve or change the font style. The model can either match existing typography or apply new styles based on your description.

For product posters, describe both the product positioning and the desired background or context.

Replicate

You can try this model on the Replicate Playground at replicate.com/playground.