AI face decoration texture generation in social media platform
A computing system provides a social media platform. The computing system includes one or more processors configured to execute instructions stored in associated memory to receive a base image including a human face and receive an image mask defining a region for inpainting to occur and a region for inpainting to not occur. The region for inpainting to not occur includes at least an eye region. The one or more processors are configured to receive a user text prompt and generate, at an artificial intelligence (AI) model, a face decoration texture using the base image, the image mask, and the user text prompt as input.
1 . A computing system providing a social media platform, the computing system comprising:
one or more processors configured to execute instructions stored in associated memory to:
receive a base image including a human face;
receive an image mask defining a region for inpainting to occur and a region for inpainting to not occur, the region for inpainting to not occur including at least an eye region;
receive a user text prompt;
generate, at an artificial intelligence (AI) model, a face decoration texture using the base image, the image mask, and the user text prompt as input; and
on a pixel-by-pixel basis:
determine a skin tone hue of a human face at a pixel;
compare a hue of a corresponding pixel of the face decoration texture to be overlaid on the human face;
if a difference between the hue of the face decoration texture and the skin tone hue is less than or equal to a threshold value, return the pixel of the face decoration texture as-is; and
if the difference is greater than the threshold value, multiply the hue of the face decoration texture and the skin tone hue and return a resulting value as the pixel of the face decoration texture.
2 . The computing system of claim 1 , wherein the AI model is a diffusion model.
3 . The computing system of claim 1 , wherein the face decoration texture is a mask and the region for inpainting to not occur further includes a mouth region.
4 . The computing system of claim 1 , wherein
the face decoration texture is makeup,
the region for inpainting to occur includes a mouth region and a region around the eye region, and
the region for inpainting to not occur further includes a region around the mouth region.
5 . The computing system of claim 1 , wherein the receiving the base image comprises receiving a selection of one of a plurality of base images.
6 . The computing system of claim 1 , wherein the one or more processors are further configured to apply the face decoration texture over the human face in a live video feed.
7 . The computing system of claim 1 , wherein the one or more processors are further configured to present a user of a client device with a plurality of blend modes for blending of the face decoration texture with the human face.
8 . The computing system of claim 1 , wherein the one or more processors are further configured to present a graphical user interface (GUI) to a user of a mobile computing device, the GUI being configured to display the face decoration texture on the human face and not display the base image.
9 . The computing system of claim 1 , wherein the one or more processors are further configured to store the face decoration texture and make the face decoration texture available to other users of the social media platform.
10 . A method for a computing system providing a social media platform, the method comprising, at one or more processors of the computing system:
receiving a base image including a human face;
receiving an image mask defining a region for inpainting to occur and a region for inpainting to not occur, the region for inpainting to not occur including at least an eye region;
receiving a user text prompt;
generating, at an artificial intelligence (AI) model, a face decoration texture using the base image, the image mask, and the user text prompt as input; and
on a pixel-by-pixel basis:
determining a skin tone hue of a human face at a pixel;
comparing a hue of a corresponding pixel of the face decoration texture to be overlaid on the human face;
if a difference between the hue of the face decoration texture and the skin tone hue is less than or equal to a threshold value, returning the pixel of the face decoration texture as-is; and
if the difference is greater than the threshold value, multiplying the hue of the face decoration texture and the skin tone hue and returning a resulting value as the pixel of the face decoration texture.
11 . The method of claim 10 , wherein the AI model is a diffusion model.
12 . The method of claim 10 , wherein the face decoration texture is a mask and the region for inpainting to not occur further includes a mouth region.
13 . The method of claim 10 , wherein
the face decoration texture is makeup,
the region for inpainting to occur includes a mouth region and a region around the eye region, and
the region for inpainting to not occur further includes a region around the mouth region.
14 . The method of claim 10 , wherein the receiving the base image comprises receiving a selection of one of a plurality of base images.
15 . The method of claim 10 , further comprising applying the face decoration texture over the human face in a live video feed.
16 . The method of claim 10 , further comprising storing the face decoration texture and making the face decoration texture available to other users of the social media platform.
17 . A non-transitory computer-readable storage medium storing a computer program which, when executed by the one or more processors, causes the one or more processors to perform the method of claim 10 .
18 . A server device providing a social media platform, the server device comprising:
one or more processors configured to execute instructions stored in associated memory to:
receive a selection of a base image including a human face;
receive a user text prompt;
generate, at an artificial intelligence (AI) model, a face decoration texture using the base image, an image mask, and the user text prompt as input, the image mask defining a region for inpainting to occur and a region for inpainting to not occur, the region for inpainting to not occur including at least an eye region; and
on a pixel-by-pixel basis:
determine a skin tone hue of a human face at a pixel;
compare a hue of a corresponding pixel of the face decoration texture to be overlaid on the human face;
if a difference between the hue of the face decoration texture and the skin tone hue is less than or equal to a threshold value, return the pixel of the face decoration texture as-is; and
if the difference is greater than the threshold value, multiply the hue of the face decoration texture and the skin tone hue and return a resulting value as the pixel of the face decoration texture.
19 . The server device of claim 18 , wherein the face decoration texture is a mask and the region for inpainting to not occur further includes a mouth region.
20 . The server device of claim 18 , wherein the receiving the base image comprises receiving a selection of one of a plurality of base images.