AI Crop Preferences

under \[dt nexus > preferences] you will find a few options that guide the universal behavior of ai crop in all modes apply crops to variants the crop(s) generated by ai crop can be applied as additional variants or on the existing variants add new variants additional variant(s) will be created (and placed after all current variants) for the output they will be identical to the first variant other than the crop and rotation applied ("clone variant" in capture one terminology) in most cases one variant is added, but in the case of page splitting two variants are added replace current variants the output will replace exisiting variant(s) in most cases the first variant is replaced, but in the case of page splitting the second variant is also replaced (or a second variant is created if none exists) selecting variant by position when doing page splitting, or using add new variants, it can be helpful to know the below tools that allow you to select variants by their position in capture one you can right click on a thumbnail of any particular variant and use the select by same > variant position to select all images of a particular variant to remove all non first variants you can use select by same > variant position on a first variant of any image, and then use command + i (or select > invert selection ), and then hit delete apply color labels to crops failures only when ai crop cannot process a file, or does not have confidence in its results, it will assign the failure color tag otherwise no change in color tag is made failures and successes ai crop always assigns a color tag to images it processes – either the success color tag for confident results, or the failure color tag for everything else never ai crop never changes the color tag of images the color of the success color tag and failure color tag can also be assigned one possible workflow is to use yellow to indicate ai crop success and orange as failure, and then "upgrade" or "downgrade" the color tag during qc red confirmed failure during qc orange ai crop suspects a failure yellow ai crop claims a success green confirmed success during qc note that in 0 5 0 beta we have not yet refined the rules by which ai crop fails items, and have not provided a way for the user to understand why an image was failed as one example, crops that do not contain the dead center of the frame are always failed for now, please take the color tags with a grain of salt; we will continue working on this throughout the beta