Providing a ui input generation interface for drafting text descriptions used by an ai image generation model

A method for generating an image using an image generation artificial intelligence (IGAI) process, comprising:

• receiving a first user prompt from a user at a user interface of a client device, the first user prompt received in a form of a source image;
• analyzing the source image to identify image features contained within and to generate a first text prompt defining the image features, the first text prompt representing metadata of the source image;
• receiving a second user prompt from the user, the second user prompt received in a form of a second text prompt provided at the user interface;
• aggregating the first text prompt and the second text prompt to generate an aggregated user prompt;
• analyzing the aggregated user prompt to identify keywords and a sequence of the keywords included therein;
• providing keyword variations to one or more keywords included in the aggregated user prompt, at the user interface for user selection;
• receiving user selection of a keyword variation to the one or more keywords included in the aggregated user prompt, the user selection of the keyword variation used to replace the one or more keywords included in the aggregated user prompt to generate an adjusted prompt;
• and
• dynamically updating the source image in accordance to the adjusted prompt, the dynamic adjusting includes identifying an image feature representing the one or more keywords in the adjusted prompt and influencing a change in the identified image feature of the source image such that the identified image feature reflects a style specified by the keywords of the second user prompt, the updated source image providing a visual representation of the adjusted prompt is forwarded to the client device for rendering, in response to receiving the first and the second user prompts from the user,
• wherein operations of the method are performed by the IGAI process executing on a processor of a server.