# The Hidden Language of Diffusion Models

arXiv: https://arxiv.org/abs/2306.00966 · HTML: https://mlsanity.com/paper/2306.00966/

## Key facts

- Cited by 34 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 56 of its 73 references that are in the map.
- First posted on arXiv 1 Jun 2023.

## 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, 30 of 56)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Zero-Shot Text-to-Image Generation](https://mlsanity.com/paper/2102.12092/) (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)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion](https://mlsanity.com/paper/2208.01618/) (2022)
- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Scaling Autoregressive Models for Content-Rich Text-to-Image Generation](https://mlsanity.com/paper/2206.10789/) (2022)
- [Imagic: Text-Based Real Image Editing with Diffusion Models](https://mlsanity.com/paper/2210.09276/) (2022)
- [Multi-Concept Customization of Text-to-Image Diffusion](https://mlsanity.com/paper/2212.04488/) (2022)
- [eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers](https://mlsanity.com/paper/2211.01324/) (2022)
- [Object-Centric Learning with Slot Attention](https://mlsanity.com/paper/2006.15055/) (2020)
- [GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields](https://mlsanity.com/paper/2011.12100/) (2020)
- [Extracting Training Data from Diffusion Models](https://mlsanity.com/paper/2301.13188/) (2023)
- [Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2301.13826/) (2023)
- [AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks](https://mlsanity.com/paper/1711.10485/) (2017)
- [Transformer Interpretability Beyond Attention Visualization](https://mlsanity.com/paper/2012.09838/) (2020)
- [Transformer Feed-Forward Layers Build Predictions by Promoting Concepts in the Vocabulary Space](https://mlsanity.com/paper/2203.14680/) (2022)

## Built on by (most cited first, 30 of 34)

- [VideoJAM: Joint Appearance-Motion Representations for Enhanced Motion Generation in Video Models](https://mlsanity.com/paper/2502.02492/) (2025)
- [Improving Tuning-Free Real Image Editing with Proximal Guidance](https://mlsanity.com/paper/2306.05414/) (2023)
- [Diffusion Models and Representation Learning: A Survey](https://mlsanity.com/paper/2407.00783/) (2024)
- [Still-Moving: Customized Video Generation without Customized Video Data](https://mlsanity.com/paper/2407.08674/) (2024)
- [Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic Directions](https://mlsanity.com/paper/2403.17064/) (2024)
- [PALP: Prompt Aligned Personalization of Text-to-Image Models](https://mlsanity.com/paper/2401.06105/) (2024)
- [SurrogatePrompt: Bypassing the Safety Filter of Text-to-Image Models via Substitution](https://mlsanity.com/paper/2309.14122/) (2023)
- [Diffusion Lens: Interpreting Text Encoders in Text-to-Image Pipelines](https://mlsanity.com/paper/2403.05846/) (2024)
- [textitRevelio: Interpreting and leveraging semantic information in diffusion models](https://mlsanity.com/paper/2411.16725/) (2024)
- [On Mechanistic Knowledge Localization in Text-to-Image Generative Models](https://mlsanity.com/paper/2405.01008/) (2024)
- [Emergent Visual-Semantic Hierarchies in Image-Text Representations](https://mlsanity.com/paper/2407.08521/) (2024)
- [Navigating Cultural Chasms: Exploring and Unlocking the Cultural POV of Text-To-Image Models](https://mlsanity.com/paper/2310.01929/) (2023)
- [DiffusionPID: Interpreting Diffusion via Partial Information Decomposition](https://mlsanity.com/paper/2406.05191/) (2024)
- [ConceptExpress: Harnessing Diffusion Models for Single-image Unsupervised Concept Extraction](https://mlsanity.com/paper/2407.07077/) (2024)
- [Padding Tone: A Mechanistic Analysis of Padding Tokens in T2I Models](https://mlsanity.com/paper/2501.06751/) (2025)
- [Language-Informed Visual Concept Learning](https://mlsanity.com/paper/2312.03587/) (2023)
- [Compositional Image Decomposition with Diffusion Models](https://mlsanity.com/paper/2406.19298/) (2024)
- [Words in Motion: Extracting Interpretable Control Vectors for Motion Transformers](https://mlsanity.com/paper/2406.11624/) (2024)
- [CusConcept: Customized Visual Concept Decomposition with Diffusion Models](https://mlsanity.com/paper/2410.00398/) (2024)
- [Diverse Diffusion: Enhancing Image Diversity in Text-to-Image Generation](https://mlsanity.com/paper/2310.12583/) (2023)
- [Temporal Concept Dynamics in Diffusion Models via Prompt-Conditioned Interventions](https://mlsanity.com/paper/2512.08486/) (2025)
- [Trustworthy Text-to-Image Diffusion Models: A Timely and Focused Survey](https://mlsanity.com/paper/2409.18214/) (2024)
- [FreezeAsGuard: Mitigating Illegal Adaptation of Diffusion Models via Selective Tensor Freezing](https://mlsanity.com/paper/2405.17472/) (2024)
- [Follow the Flow: On Information Flow Across Textual Tokens in Text-to-Image Models](https://mlsanity.com/paper/2504.01137/) (2025)
- [Early Estimation of Language to Latent Alignment in Diffusion Models](https://mlsanity.com/paper/2512.08505/) (2025)
- [Superscopes: Amplifying Internal Feature Representations for Language Model Interpretation](https://mlsanity.com/paper/2503.02078/) (2025)
- [The Linear Geometry of Interpretable Tokens: Jailbreaking Attacks and Defenses for Unlearned Diffusion Models](https://mlsanity.com/paper/2504.21307/) (2025)
- [Semantic Guidance Tuning for Text-To-Image Diffusion Models](https://mlsanity.com/paper/2312.15964/) (2023)
- [Understanding the Limitations of Diffusion Concept Algebra Through Food](https://mlsanity.com/paper/2406.03582/) (2024)
- [TIDE: Achieving Balanced Subject-Driven Image Generation via Target-Instructed Diffusion Enhancement](https://mlsanity.com/paper/2509.06499/) (2025)

## Abstract (arXiv)

Text-to-image diffusion models have demonstrated an unparalleled ability to generate high-quality, diverse images from a textual prompt. However, the internal representations learned by these models remain an enigma. In this work, we present Conceptor, a novel method to interpret the internal representation of a textual concept by a diffusion model. This interpretation is obtained by decomposing the concept into a small set of human-interpretable textual elements. Applied over the state-of-the-art Stable Diffusion model, Conceptor reveals non-trivial structures in the representations of concepts. For example, we find surprising visual connections between concepts, that transcend their textual semantics. We additionally discover concepts that rely on mixtures of exemplars, biases, renowned artistic styles, or a simultaneous fusion of multiple meanings of the concept. Through a large battery of experiments, we demonstrate Conceptor's ability to provide meaningful, robust, and faithful decompositions for a wide variety of abstract, concrete, and complex textual concepts, while allowing to naturally connect each decomposition element to its corresponding visual impact on the generated images. Our code will be available at: https://hila-chefer.github.io/Conceptor/