Qwen-Image Edit
Supports multiple image inputs and outputs, allowing for precise modification of text within images, addition, deletion, or movement of objects, alteration of subject actions, transfer of image styles, and enhancement of image details.

What it does
Qwen-Image Edit, in practice.
An advanced image editing model from Alibaba Cloud, offering precise control and high-quality results. Qwen-Image Edit is designed to handle common editing tasks, allowing users to modify images with natural language prompts. It supports single-image editing and multi-image blending.
- Purpose: Perform image edits using text instructions.
- Core Capability: Supports single-image editing and multi-image blending.
- Foundation: Powered by Alibaba's advanced multi-modal generative AI technology.
- Typical Output: High-quality edited image (1 per request) that blends changes with the original content.
- Use Cases: Social media content adjustment, basic photo retouching, and creative experimentation.
- Multi-image Blending:
Run Qwen-Image Edit
from $0.048/imageParameters
What you can set.
| Parameter | What it does | Options |
|---|---|---|
images | List of URLs of input images (1-3 images). Image Format: JPG, JPEG, PNG, BMP, TIFF, WEBP, GIF (first frame). Resolution: Recommended 384px - 3072px. Size Limit: Max 10MB per image. | |
prompt | Text instruction for editing. Max 800 characters. | |
negative_prompt | Description of content to exclude (max 500 characters). | |
num_images | Number of output images. Fixed at 1. | default 1 |
seed | The random seed to use for the generation. -1 means a random seed will be used. | default -1 |
Sample prompt
The prompt behind the sample.
Generate an image that matches the depth map, following this description: a dilapidated red bicycle parked on a muddy path, with a dense primeval forest in the background.
num_images: 1seed: -1FAQ
Short answers.
How much does Qwen-Image Edit cost?
Pricing starts at $0.048 per image at the base resolution; higher resolutions and longer durations cost more. Usage is billed per request from your balance — no subscription.
Does Qwen-Image Edit run uncensored here?
No. Qwen applies its own content policy to this model regardless of where it is called from. For a route without an extra platform filter use Uncensored MiniMax H3; this page lists Qwen-Image Edit for everything else it does well.
What does Qwen-Image Edit take as input?
It is a image editing model. Supports multiple image inputs and outputs, allowing for precise modification of text within images, addition, deletion, or movement of objects, alteration of subject actions, transfer of image styles, and enhancement of image details.
How do I use it?
Enter an invite code to open Chat with the model loaded, or join the waitlist. We open seats in batches and track which models are requested most.
Related