mlsanityData to 14 Oct 2026

Enhancing Creative Generation on Stable Diffusion-based Models

arXiv 2503.23538 ↗First posted 30 Mar 2025cs.CVcited by 13

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

Abstract (arXiv)

Recent text-to-image generative models, particularly Stable Diffusion and its distilled variants, have achieved impressive fidelity and strong text-image alignment. However, their creative capability remains constrained, as including `creative' in prompts seldom yields the desired results. This paper introduces C3 (Creative Concept Catalyst), a training-free approach designed to enhance creativity in Stable Diffusion-based models. C3 selectively amplifies features during the denoising process to foster more creative outputs. We offer practical guidelines for choosing amplification factors based on two main aspects of creativity. C3 is the first study to enhance creativity in diffusion models without extensive computational costs. We demonstrate its effectiveness across various Stable Diffusion-based models.

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 27 of its 31 references that are in the map. First posted on arXiv 30 Mar 2025.

Builds on

27 of 31 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Visual Style Prompting with Swapping Self-Attention20 Feb
  2. 2023Kandinsky: an Improved Text-to-Image Synthesis with Image Prior and Latent Diffusion5 Oct
  3. 2023ConceptLab: Creative Concept Generation using VLM-Guided Diffusion Prior Constraints3 Aug
  4. 2023Adding Conditional Control to Text-to-Image Diffusion Models10 Feb

Other references · 23

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  3. 2023GPT-4 Technical Reportcited by 18,396
  4. 2020Denoising Diffusion Implicit Modelscited by 9,781
  5. 2022Classifier-Free Diffusion Guidancecited by 5,847
  6. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  7. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,431
  8. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,424
  9. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,114
  10. 2023Adversarial Diffusion Distillationcited by 759
  11. 2023MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editingcited by 727
  12. 2022Diffusion Models already have a Semantic Latent Spacecited by 328
11 more
  1. 2023FreeDoM: Training-Free Energy-Guided Conditional Diffusion Modelcited by 294
  2. 2024SDXL-Lightning: Progressive Adversarial Diffusion Distillationcited by 266
  3. 2023P+: Extended Textual Conditioning in Text-to-Image Generationcited by 242
  4. 2023FreeU: Free Lunch in Diffusion U-Netcited by 196
  5. 2017CAN: Creative Adversarial Networks, Generating "Art" by Learning About Styles and Deviating from Style Normscited by 96
  6. 2023Concept Decomposition for Visual Exploration and Inspirationcited by 61
  7. 2021CreativeGAN: Editing Generative Adversarial Networks for Creative Design Synthesiscited by 24
  8. 2018DeSIGN: Design Inspiration from Generative Networkscited by 20
  9. 2024DisCo-Diff: Enhancing Continuous Diffusion Models with Discrete Latentscited by 20
  10. 2024Diffusion-Based Visual Art Creation: A Survey and New Perspectivescited by 17
  11. 2024ProCreate, Don't Reproduce! Propulsive Energy Diffusion for Creative Generationcited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 7; 2026: 6.

13 papers.

Sort:

By area:

  1. 2025Distribution-Conditional Generation: From Class Distribution to Creative Generationcited by 4
  2. 2025VLM-Guided Adaptive Negative Prompting for Creative Generationcited by 3
  3. 2025AGSwap: Overcoming Category Boundaries in Object Fusion via Adaptive Group Swappingcited by 2
  4. 2025GuessBench: Sensemaking Multimodal Creativity in the Wildcited by 1
  5. 2025What Do You Need for Compositional Generalization in Diffusion Planning?cited by 0
  6. 2025Diversity Has Always Been There in Your Visual Autoregressive Modelscited by 0
  7. 2025CREward: A Type-Specific Creativity Reward Modelcited by 0
  8. 2026Backdoor Sentinel: Detecting and Detoxifying Backdoors in Diffusion Models via Temporal Noise Consistencycited by 0
  9. 2026A Creative Agent is Worth a 64-Token Templatecited by 0
  10. 2026Seeking the Unfamiliar but Memorable: Conceptual Creativity as Meta-Learningcited by 0
  11. 2026Self-Creative Text-to-Object Generation using Semantic-Aware Spatial Weightingcited by 0
  12. 2026Breaking the Lock-in: Diversifying Text-to-Image Generation via Representation Modulationcited by 0
1 more
  1. 2026RankT2I: A Submodular Framework for Discovering Interpretable and Diverse Semantics in Text-to-Image Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Creative Image Generation with Diffusion Models
  2. 2025Blending Concepts with Text-to-Image Diffusion Models
  3. 2022A Survey on Generative Diffusion Model
  4. 2022The Stable Artist: Steering Semantics in Diffusion Latent Space
  5. 2024Redefining <Creative> in Dictionary: Towards an Enhanced Semantic Understanding of Creative Generation
  6. 2023Diffusion idea exploration for art generation
  7. 2024An analytic theory of creativity in convolutional diffusion models
  8. 2023Ablating Concepts in Text-to-Image Diffusion Models