Generative artificial intelligence visual effect generator
A method and system for enhancing text with image-based visual effects is presented. An initial text prompt including a phrase for display is submitted to a language model. The language model outputs a candidate prompt. The candidate prompt may be further modified to create an image prompt. The image prompt is submitted to an image generating model which produces an image. A visual effect of the display phrase based on the image is displayed.
1 . A method of visually enhancing text comprising:
receiving, by one or more processors, a set of text including a display phrase;
generating, by the one or more processors, a candidate prompt based on the set of text, wherein the candidate prompt differs from the set of text;
converting, by the one or more processors, the candidate prompt into an image prompt by removing one or more words from the candidate prompt;
submitting the image prompt into an image generating model to generate an image; and
rendering the display phrase with a visual effect of the generated image.
2 . The method of claim 1 , further comprising:
placing the display phrase in a template;
adding other information from the set of text to complete the template; and
using the completed template as the candidate prompt.
3 . The method of claim 1 , wherein converting the candidate prompt into the image prompt comprises:
submitting the candidate prompt to a large language model configured to produce, using the candidate prompt, an output phrase that excludes the one or more words; and
creating the image prompt based on the output phrase.
4 . The method of claim 1 , wherein rendering the display phrase with a visual effect comprises rendering the display phrase as a transparent stencil over the generated image.
5 . The method of claim 1 , wherein rendering the display phrase with a visual effect comprises imprinting the display phrase into the generated image.
6 . The method of claim 1 , wherein rendering the display phrase with a visual effect comprises both modifying the display phrase and modifying a background using the generated image.
7 . The method of claim 1 , further comprising:
generating a plurality of images prior to receiving the image prompt;
upon receipt of the image prompt, matching the image prompt with an image of the plurality of images by determining a similarity between an embedding of each of the plurality of images and an embedding of the image prompt, and returning images with a similarity greater than a threshold value.
8 . The method of claim 7 , wherein the plurality of generated images with text visual effects are ranked based on a visual appeal score.
9 . The method of claim 1 , wherein rendering the display phrase with a visual effect comprises:
forming the display phrase into a mask delineated by boundaries; and
generating the image within the boundaries of the mask.
10 . The method of claim 9 , further comprising selecting a font for the display phrase, wherein the mask boundaries are defined by a plurality of non-overlapping same-sized patches at a plurality of locations.
11 . An artificial intelligence system comprising:
one or more memory devices; and
one or more processors configured to execute code including a set of instructions, wherein execution of the set of instructions causes the one or more processors to perform operations comprising:
receiving, by the one or more processors, a set of text including a display phrase;
generating, by the one or more processors, a candidate prompt based on the set of text, wherein the candidate prompt differs from the set of text;
converting, by the one or more processors, the candidate prompt into an image prompt by removing one or more words from the candidate prompt;
submitting the image prompt into an image generating model to generate an image; and
rendering the display phrase with a visual effect of the generated image.
12 . The system of claim 11 , wherein the one or more processors further perform operations comprising:
placing the display phrase in a template;
adding other information from the set of text to complete the template; and
using the completed template as the candidate prompt.
13 . The system of claim 11 , wherein converting the candidate prompt into the image prompt comprises:
submitting the candidate prompt to a large language model configured to produce, using the candidate prompt, an output phrase that excludes the one or more words; and
creating the image prompt based on the output phrase.
14 . The system of claim 11 , wherein rendering the display phrase with a visual effect comprises rendering the display phrase as a transparent stencil over the generated image.
15 . The system of claim 11 , wherein rendering the display phrase with a visual effect comprises imprinting the display phrase into the generated image.
16 . The system of claim 11 , wherein rendering the display phrase with a visual effect comprises both modifying the display phrase and modifying a background using the generated image.
17 . The system of claim 11 , wherein the one or more processors further perform operations comprising:
generating a plurality of images prior to receiving the image prompt;
upon receipt of the image prompt, matching the image prompt with an image of the plurality of images by determining a similarity between an embedding of each of the plurality of images and an embedding of the image prompt, and returning images with a similarity greater than a threshold value.
18 . The system of claim 17 , wherein the plurality of generated images with text visual effects are ranked based on a visual appeal score.
19 . The system of claim 11 , wherein rendering the display phrase with a visual effect comprises:
forming the display phrase into a mask delineated by boundaries; and
generating the image within the boundaries of the mask.
20 . The system of claim 19 , wherein the one or more processors further perform operations comprising selecting a font for the display phrase, wherein the mask boundaries are defined by a plurality of non-overlapping same-sized patches at a plurality of locations.