Core concepts
img2img
img2img is shorthand for "image-to-image" - the AI workflow that transforms an existing picture using a prompt, keeping some of the original structure instead of generating from scratch.
"img2img" is just the common abbreviation of image-to-image. The two terms mean exactly the same thing, so we keep one full definition to avoid splitting it across pages.
In short: instead of starting from random noise like text-to-image, img2img starts from a partially noised version of an input image. A denoise strength setting decides how much of the original survives - low keeps it close to the source, high lets the model reinvent it freely.
For the full explanation - how denoise strength works, when to use it, and a worked example - see the canonical page: image-to-image.
Try it in the generator
Put img2img to work right now - free daily generations, commercial license included.
Related terms
- Image-to-imageImage-to-image (img2img) is the AI workflow that transforms an existing picture according to your prompt, keeping some of the original structure instead of generating from scratch.
- Text-to-imageText-to-image is the AI workflow where you type a written prompt and the model generates a brand-new image from it - no source image required.
- DenoisingDenoising is the core operation of a diffusion model: at each step it predicts and removes a little noise, gradually turning a random field into a clear image.