Back to results
US 12,755,345 B2Granted
Texture based consistency for generative ai assets, effects and animations
AssigneeAdobe Inc.
InventorsVlad-Constantin Lungu-Stan, Adrian-Stefan Ungureanu-Contes, Ionuţ Mironicǎ
Life of this patent
Estimating the term…
Abstract
A method, apparatus, non-transitory computer readable medium, and system for image processing include obtaining an input texture image and a plurality of image masks, generating a plurality of image assets corresponding to the plurality of image masks based on the input texture image, and generating a combined asset including the plurality of image assets. The plurality of image assets have a consistent texture based on the input texture image.
Claims20
A method comprising:
- obtaining an input texture image, a plurality of input images, and a plurality of image masks, wherein the input texture image depicts a texture, each of the plurality of input images depicts a same image element at a different location, and each of the plurality of image masks indicates the location of the image element in a corresponding input image;
- generating, using an image generation model, a plurality of image assets corresponding to the plurality of input images based on the input texture image and the plurality of image masks, wherein each of the plurality of image assets depicts the texture from the input texture image in a border region of the image element;
- and
- generating a combined asset including the plurality of image assets, wherein the combined asset comprises a texture effect video depicting an animation including the texture from the input texture image in the border region adjacent to the image element.
1 more element
A method comprising:
- obtaining an input texture image, a plurality of glyph images, and a plurality of image masks, wherein the input texture image depicts a texture, each of the plurality of glyph images depicts a different text character, and each of the plurality of image masks indicates a shape of the text character in a corresponding glyph image;
- generating, using an image generation model, a plurality of image assets corresponding to the plurality of glyph images based on the input texture image and the plurality of image masks, wherein each of the plurality of image assets depicts the texture from the input texture image in a border region of the text character;
- and
- generating a combined asset including the plurality of image assets, wherein the combined asset comprises text including the texture from the input texture image in the border region adjacent to the different text characters from the plurality of glyph images.
1 more element
A system comprising:
- a memory component;
- and
- a processing device coupled to the memory component, the processing device configured to perform operations comprising:
- obtaining an input texture image, a plurality of input images, and a plurality of image masks, wherein the input texture image depicts a texture, each of the plurality of input images depicts a same image element at a different location, and each of the plurality of image masks indicates the location of the image element in a corresponding input image;
- generating, using an image generation model, a plurality of image assets corresponding to the plurality of input images based on the input texture image and the plurality of image masks, wherein each of the plurality of image assets depicts the texture from the input texture image in a border region of the image element;
- and
- generating a combined asset including the plurality of image assets, wherein the combined asset comprises a texture effect video depicting an animation including the texture from the input texture image in the border region adjacent to the image element.
4 more elements
Dependencies are inferred from the claim text.