Edit an image with text instructions
PromptWrite a short instruction describing how to edit the image. (ex: "swap X by Y", "add X", "what would it look like if it were snowing?")
CountNumber of images to generate
Image guidanceAdjusts how much the AI tries to retain the content of the original image. Higher values encourages to generate images that are closely linked to the source image, usually at the expense of lower image quality.
Negative promptDescribe what you DON'T want in the generated image
GuidanceAdjusts how much the AI tries to fit the prompt (higher = stricter, lower = more freedom). The sweet spot is between 6-10, extreme values may produce more artifacts.
StepsNumber of sampling steps. More steps = more details but also longer computation time.
SamplerDefines the sampling method used to generate the image.
SeedUnique image seed number. If not provided, the image will be random.
UpscaleUpscale the image by this factor using the Real-ESRGAN model. Currently only a factor of 2 is supported.
FormatThe encoding format of the generated image.
An error has occurred. This application may need to be reloaded.