This is to assist image generation models apply random keywords within a prompt; in this instance the color of something.

Here are some examples:

1. A red coffee mug

2. A pewter coffee mug

3. A vermilion coffee mug

It should be saved as a .txt file in the wildcards directory if generating images locally in Fooocus, and wildcards_official for Ruined Fooocus.

For A1111: This is a Wildcard collection, it requires an additional extension in Automatic 1111 to work on that platform. (See the guidance to the right on this page).

Usage: Simply put two underscores around the filename prefix. i.e.(__extended-color__).

For example "A __extended-color__ coffee mug."

This will then cause one of the items in the list to be inserted into the prompt. For example "A red coffee mug", next prompt in the batch could be "A slate gray coffee mug".

Keep in mind that your checkpoint or lora may not recognize the color and will produce a 'default' response, and images generated are highly dependent on the checkpoint and lora training material; larger scale checkpoints are likely to produce more hits than the more specific ones.

Comments, suggestions, amendments and inclusions most welcome in the comments.

Please note that this is an extension of the extended-color wildcard file provided by Fooocus, so you can safely overwrite it.