# Personalizing Text-to-Image Generation via Aesthetic Gradients

arXiv: https://arxiv.org/abs/2209.12330 · HTML: https://mlsanity.com/paper/2209.12330/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 7 of its 9 references that are in the map.
- First posted on arXiv 25 Sep 2022.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 7 of 7)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [Cyclical Stochastic Gradient MCMC for Bayesian Deep Learning](https://mlsanity.com/paper/1902.03932/) (2019)
- [Stochastic Gradient MCMC with Repulsive Forces](https://mlsanity.com/paper/1812.00071/) (2018)

## Built on by (most cited first, 13 of 13)

- [Text-to-image Diffusion Models in Generative AI: A Survey](https://mlsanity.com/paper/2303.07909/) (2023)
- [MIKE: A New Benchmark for Fine-grained Multimodal Entity Knowledge Editing](https://mlsanity.com/paper/2402.14835/) (2024)
- [DiffClass: Diffusion-Based Class Incremental Learning](https://mlsanity.com/paper/2403.05016/) (2024)
- [Personalized Image Generation with Deep Generative Models: A Decade Survey](https://mlsanity.com/paper/2502.13081/) (2025)
- [Translation-Enhanced Multilingual Text-to-Image Generation](https://mlsanity.com/paper/2305.19216/) (2023)
- [The Big Data Myth: Using Diffusion Models for Dataset Generation to Train Deep Detection Models](https://mlsanity.com/paper/2306.09762/) (2023)
- [ZYN: Zero-Shot Reward Models with Yes-No Questions for RLAIF](https://mlsanity.com/paper/2308.06385/) (2023)
- [CompArt: Operationalizing Aesthetic Alignment in Text-to-Image Generation via Principles of Art](https://mlsanity.com/paper/2503.12018/) (2025)
- [Anti-Aesthetics: Protecting Facial Privacy against Customized Text-to-Image Synthesis](https://mlsanity.com/paper/2504.12129/) (2025)
- [Fast Adaptation with Bradley-Terry Preference Models in Text-To-Image Classification and Generation](https://mlsanity.com/paper/2308.07929/) (2023)
- [Deciphering Personalization: Towards Fine-Grained Explainability in Natural Language for Personalized Image Generation Models](https://mlsanity.com/paper/2511.01932/) (2025)
- [Dialogue with the Machine and Dialogue with the Art World: Evaluating Generative AI for Culturally-Situated Creativity](https://mlsanity.com/paper/2412.14077/) (2024)
- [Hierarchical Anti-Aesthetics: Protecting Facial Privacy against Customized Diffusion Models](https://mlsanity.com/paper/2607.02038/) (2026)

## Abstract (arXiv)

This work proposes aesthetic gradients, a method to personalize a CLIP-conditioned diffusion model by guiding the generative process towards custom aesthetics defined by the user from a set of images. The approach is validated with qualitative and quantitative experiments, using the recent stable diffusion model and several aesthetically-filtered datasets. Code is released at https://github.com/vicgalle/stable-diffusion-aesthetic-gradients