mlsanityData to 7 Oct 2026

Personalizing Text-to-Image Generation via Aesthetic Gradients

arXiv 2209.12330 ↗First posted 25 Sep 2022cs.CV cs.LGcited by 13

On the map: Diffusion models → Image generation, text-to-image and editing

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

Key facts. Cited by 13 papers in the map (data through 7 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.

Builds on

7 of 9 references.

Closest ancestors · 2

Same direction, newest first

  1. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation25 Aug
  2. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models20 Dec

Other references · 5

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,231
  4. 2019Cyclical Stochastic Gradient MCMC for Bayesian Deep Learningcited by 203
  5. 2018Stochastic Gradient MCMC with Repulsive Forcescited by 18

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 3; 2025: 4; 2026: 1.

13 papers.

Sort:

By area:

  1. 2023Text-to-image Diffusion Models in Generative AI: A Surveycited by 264
  2. 2024MIKE: A New Benchmark for Fine-grained Multimodal Entity Knowledge Editingcited by 25
  3. 2024DiffClass: Diffusion-Based Class Incremental Learningcited by 23
  4. 2025Personalized Image Generation with Deep Generative Models: A Decade Surveycited by 20
  5. 2023Translation-Enhanced Multilingual Text-to-Image Generationcited by 9
  6. 2023The Big Data Myth: Using Diffusion Models for Dataset Generation to Train Deep Detection Modelscited by 7
  7. 2023ZYN: Zero-Shot Reward Models with Yes-No Questions for RLAIFcited by 4
  8. 2025CompArt: Operationalizing Aesthetic Alignment in Text-to-Image Generation via Principles of Artcited by 2
  9. 2025Anti-Aesthetics: Protecting Facial Privacy against Customized Text-to-Image Synthesiscited by 2
  10. 2023Fast Adaptation with Bradley-Terry Preference Models in Text-To-Image Classification and Generationcited by 1
  11. 2025Deciphering Personalization: Towards Fine-Grained Explainability in Natural Language for Personalized Image Generation Modelscited by 1
  12. 2024Dialogue with the Machine and Dialogue with the Art World: Evaluating Generative AI for Culturally-Situated Creativitycited by 0
1 more
  1. 2026Hierarchical Anti-Aesthetics: Protecting Facial Privacy against Customized Diffusion Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023ViCo: Plug-and-play Visual Condition for Personalized Text-to-image Generation
  2. 2024Powerful and Flexible: Personalized Text-to-Image Generation via Reinforcement Learning
  3. 2025Preserve and Personalize: Personalized Text-to-Image Diffusion Models without Distributional Drift
  4. 2024Fast Personalized Text-to-Image Syntheses With Attention Injection
  5. 2024Playground v2.5: Three Insights towards Enhancing Aesthetic Quality in Text-to-Image Generation
  6. 2025Personalized Text-to-Image Generation with Auto-Regressive Models
  7. 2024PaRa: Personalizing Text-to-Image Diffusion via Parameter Rank Reduction
  8. 2026AccelAes: Accelerating Diffusion Transformers for Training-Free Aesthetic-Enhanced Image Generation