Input
The prompt to generate the image with170/5000
image_url
File 1

File uploads require configured image storage. A public HTTPS image URL can be used directly.
The reference image to guide the generation
Denoising strength. 1.0 = fully remake; 0.0 = preserve original
The format of the generated image
Acceleration level for image generation. Options: 'none', 'regular', 'high'. Higher acceleration increases speed. 'regular' balances speed and quality. 'high' is recommended for images without text
The negative prompt for the generation
The same seed and the same prompt given to the same version of the model will output the same image every time
The number of inference steps to perform
The CFG (Classifier Free Guidance) scale is a measure of how close you want the model to stick to your prompt when looking for a related image to show you
The safety checker is always enabled in Playground. It can only be disabled by setting false through the API.
A configurable parameter. Defaults to true in the Playground.
Output
Examples
Explore different use cases and parameter configurations
Explore more Image to Image models
More AI models from Qwen
Latest and popular AI models
README
Complete guide to using qwen/image-to-image












