# US 2026/0065518 A1 · Upside down reinforcement learning for text-to-image generation > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2026/0065518 A1 - Document ID: US20260065518A1 - Status: Published application - Kind: A1 - Application number: 18/823,839 - Filed: 2024-09-04 - Published: 2026-03-05 - Earliest claimed: 2024-09-04 - Assignees: Adobe Inc. - Applicants: Adobe Inc. - Inventors: Vinh Ngoc Khuc; Fengbin Chen; Pranav Vineet Aggarwal; Han Guo; Ajinkya Gorakhnath Kale - Web page: https://patentgrep.com/patent/US20260065518A1 ## CPC - G06T 11/00: Two-dimensional [2D] image generation - G06T 7/0002: {Inspection of images, e.g. flaw detection} - G06T 11/60: Creating or editing images; Combining images with text - G06T 2200/24: involving graphical user interfaces [GUIs] - G06T 2207/20081: Training; Learning - G06T 2207/20084: Artificial neural networks [ANN] - G06T 2207/30168: Image quality inspection - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract A method, apparatus, non-transitory computer readable medium, and system for image processing include obtaining an input prompt including an image quality level and a description of an object, generating an image embedding based on the input prompt, where the image embedding represents the object and the image quality level in a vector space, and generating a synthetic image based on the image embedding, where the synthetic image depicts the object and has the image quality level. ## Claims ### Claim 1 A method comprising: obtaining an input prompt including an image quality level and a description of an object; generating, using a diffusion prior model, an image embedding based on the input prompt, wherein the image embedding represents the object and the image quality level in a vector space; and generating, using an image generation model, a synthetic image based on the image embedding, wherein the synthetic image depicts the object and has the image quality level. ### Claim 2 (depends on 1) The method of claim 1, wherein obtaining the input prompt comprises: obtaining a preliminary prompt and an indication of the image quality level; and generating the input prompt based on the preliminary prompt and the indication. ### Claim 3 (depends on 1) The method of claim 1, wherein obtaining the input prompt comprises: obtaining a style input, wherein the input prompt includes a value indicating a level of a style corresponding to the style input. ### Claim 4 (depends on 1) The method of claim 1, further comprising: generating a text embedding based on the input prompt, wherein the image embedding is generated based on the text embedding. ### Claim 5 (depends on 1) The method of claim 1, wherein generating the synthetic image comprises: obtaining a noise map; and denoising the noise map based on the image embedding to generate the synthetic image. ### Claim 6 (depends on 1) The method of claim 1, wherein: the diffusion prior model is trained to generate image embeddings using a training set comprising a training image and a training prompt that includes the image quality level. ### Claim 7 A method comprising: obtaining a training set comprising a training image and a training prompt that includes an image quality level; generating, using an image generation model, a synthetic image based on the training prompt; and training, using the training set and the synthetic image, a diffusion prior model to generate an image embedding that represents the image quality level. ### Claim 8 (depends on 7) The method of claim 7, wherein obtaining the training set comprises: obtaining a preliminary prompt and the image quality level; and generating the training prompt based on the preliminary prompt and the image quality level. ### Claim 9 (depends on 7) The method of claim 7, wherein obtaining the training set comprises: obtaining a style input, wherein the training prompt includes a value indicating a level of a style corresponding to the style input. ### Claim 10 (depends on 7) The method of claim 7, wherein obtaining the training set comprises: computing the image quality level based on the training image. ### Claim 11 (depends on 7) The method of claim 7, wherein training the diffusion prior model comprises: generating a text embedding based on the training prompt; generating an estimated image embedding based on the text embedding; and generating the synthetic image based on the estimated image embedding. ### Claim 12 (depends on 7) The method of claim 7, wherein training the diffusion prior model comprises: computing a diffusion loss based on the synthetic image; and updating parameters of the diffusion prior model based on the diffusion loss. ### Claim 13 (depends on 7) The method of claim 7, wherein: the diffusion prior model is trained separately from the image generation model. ### Claim 14 An apparatus comprising: at least one processor; at least one memory storing instructions executable by the at least one processor; a diffusion prior model comprising parameters stored in the at least one memory and trained to generate an image embedding based on an input prompt including an image quality level and a description of an object, wherein the image embedding represents the object and the image quality level in a vector space; and an image generation model comprising parameters stored in the at least one memory and configured to generate a synthetic image based on the image embedding, wherein the synthetic image depicts the object and has the image quality level. ### Claim 15 (depends on 14) The apparatus of claim 14, further comprising: a text encoder configured to generate a text embedding based on the input prompt, wherein the image embedding is generated based on the text embedding. ### Claim 16 (depends on 14) The apparatus of claim 14, further comprising: an aesthetic classifier configured to compute the image quality level. ### Claim 17 (depends on 14) The apparatus of claim 14, further comprising: a style classifier configured to compute a value indicating a level of a style, wherein the input prompt includes the level of the style. ### Claim 18 (depends on 14) The apparatus of claim 14, wherein: the diffusion prior model includes a diffusion model. ### Claim 19 (depends on 14) The apparatus of claim 14, wherein: the image generation model includes a diffusion model. ### Claim 20 (depends on 14) The apparatus of claim 14, further comprising: a user interface configured to obtain a preliminary prompt, wherein the input prompt is based on the preliminary prompt and the image quality level.