DreamReader: An Interpretability Toolkit for Text-to-Image Models

Nirmalendu Prakash; Narmeen Oozeer; Michael Lan; Luka Samkharadze; Phillip Howard; Roy Ka-Wei Lee; Dhruv Nathawani; Shivam Raval

cs.LGMar 2, 2026

DreamReader: An Interpretability Toolkit for Text-to-Image Models

Authors: Nirmalendu Prakash, Narmeen Oozeer, Michael Lan, Luka Samkharadze, Phillip Howard, Roy Ka-Wei Lee, Dhruv Nathawani, Shivam Raval,

Organizations: Singapore University of Technology and Design · Martian · Thoughtworks · NVIDIA ·

Abstract

Despite the rapid adoption of text-to-image (T2I) diffusion models, causal and representation-level analysis remains fragmented and largely limited to isolated probing techniques. To address this gap, we introduce DreamReader: a unified framework that formalizes diffusion interpretability as composable representation operators spanning activation extraction, causal patching, structured ablations, and activation steering across modules and timesteps. DreamReader provides a model-agnostic abstraction layer enabling systematic analysis and intervention across diffusion architectures. Beyond consolidating existing methods, DreamReader introduces three novel intervention primitives for diffusion models: (1) representation fine-tuning (LoReFT) for subspace-constrained internal adaptation; (2) classifier-guided gradient steering using MLP probes trained on activations; and (3) component-level cross-model mapping for systematic study of transferability of representations across modalities. These mechanisms allows us to do lightweight white-box interventions on T2I models by drawing inspiration from interpretability techniques on LLMs. We demonstrate DreamReader through controlled experiments that (i) perform activation stitching between two models, and (ii) apply LoReFT to steer multiple activation units, reliably injecting a target concept into the generated images. Experiments are specified declaratively and executed in controlled batched pipelines to enable reproducible large-scale analysis. Across multiple case studies, we show that techniques adapted from language model interpretability yield promising and controllable interventions in diffusion models. DreamReader is released as an open source toolkit for advancing research on T2I interpretability.

Figures & tables

Figure 1: DreamReader provides a unified abstraction of the diffusion stack, exposing four core interpretability operators—Localization, Steering, Stitching, and Sparse Autoencoders (SAEs)—that can be composed within a shared interface. Shown above are the 4 steps in the analysis (shown here is an example for ‘Steering’).

Workflow	Unique configuration / interventions	Workflow-specific metrics & outputs
Localization	Intervention type (scaling/zeroing/corruption), strength, and timestep schedule.	Effect ranking over sites/timesteps; influence reports (e.g. which hook sites are more causal).
Steering	Method (CAA/K-Steer/LoREFT), learned direction(s), application site(s), scale(s), schedule(s).	Steering success curves vs. strength/location; reusable steering vectors and ranking plots.
Stitching	Mapper family (affine/MLP), training schedule/loss; module swapping and transfer settings.	Compatibility heatmaps (i.e. cross-layer comparison between modules); stitched vs. native comparison grids; mapper checkpoints.
SAEs	Dictionary size, sparsity/Top- $k$ , activation source (raw/residual); feature editing scale.	Dead-feature rate, sparsity stats; feature cards with top activations.

Table 1: DreamReader workflows. Shared inputs/metrics/outputs are listed in the common block; each row reports only workflow-specific configuration knobs and deliverables. Technical terms are defined in Table 4 .

Figure 2: LoREFT steering results on sample prompts for SDXL-Turbo. We steer the model to add spectacles by training a LoREFT module on cross-attention activations from different U-Net regions (down, mid, and up blocks). Steering effectiveness varies by prompt: for Simba , down-block steering succeeds, whereas for Jack Sparrow , up-block steering performs best. CLIP score measures prompt–image alignment; FID and LPIPS quantify the deviation from the baseline (unsteered) output. Results are logged and visualized with W&B.

Panel of Figure 3 — Figure 3: Steering. We use CAA to extract a steering direction from a fine-tuned SD 1.5 model using a minimal contrastive setup with two prompts (e.g., “a photo of a Black man” vs. “a photo of a man” ). We map this direction to the base model with our learned mapper and apply it during generation. The figure compares baseline samples (left) with the corresponding steered samples (right) for two example prompts.

Capability	Dream Reader (Ours)	TransformerLens	nnsight
Primary focus	Diffusion / T2I	Autoregressive LLMs	LLMs (+ diffusion)
Abstraction level	End-to-end workflows	Mechanistic primitives	Tracing/editing primitives
Tracing & editing	(steer, ablate, stitch)	Patch-only	Patch + causal
SAE support	Built-in workflow	External add-ons	External add-ons
Experiment infrastructure	YAML pipelines + standardized outputs	Python scripts	Python scripts
Visualization & reporting	Integrated tables	External tooling	External tooling

Table 2: Comparison of Dream Reader with existing interpretability libraries. “Tracing & editing” encompasses activation extraction, intervention (e.g., patching, steering, ablations), and model stitching. “Experiment infrastructure” refers to configuration-driven experiment setup and standardized output formats. TransformerLens focuses on low-level mechanistic analysis for language models, while nnsight provides a general tracing and intervention graph framework. Dream Reader differs by providing diffusion-first, workflow-oriented pipelines with integrated experiment management and reporting.

Appendix figures & tables2 assets

Supplementary material from the paper’s appendix.

Appendix

System / Paper	Interpretability Capabilities						Visualization & Workflow
	Head/Block Patching	Concept Directions	SAE Training	SAE Intervene	Model Stitching	Trained Steering (LoREFT/K-Steer)	Attention Maps	Intermed. Viz ( $\hat{x}_{0}$ /steps)	Workflow & Reports
Patch Explorer ( Grabe et al., 2025 )	✓	–	–	–	–	–	$\circ$	$\circ$	–
One-Step is Enough (SAE) ( Surkov et al., 2024 )	–	–	✓	✓	–	–	–	–	$\circ$
Cross/Self-Attn for Editing ( Liu et al., 2024 )	–	–	–	–	–	–	✓	–	–
Distilling Diversity & Control ( Gandikota and Bau, 2025 )	–	–	–	–	$\circ$	–	$\circ$	✓	$\circ$
SliderSpace ( Gandikota et al., 2025 )	–	✓	–	$\circ$	–	–	–	✓	$\circ$

Appendix

Table 3: T2I interpretability repositories summary. Left block: core interpretability capabilities; right block: visualization and workflow support. Symbols: ✓supported;

\circ

partial/limited; –not reported/applicable.

Term	Definition
Scales	Intervention strength parameters (e.g., how strongly activations are modified).
Schedules	Temporal specifications describing when an intervention is applied (e.g., which denoising steps/timesteps).
Steering vector	A learned direction in activation space that, when added to activations, steers model behavior.
Mapper	A neural network (affine/linear or MLP) transforming activations, used in steering and stitching workflows.
Feature ablation	Removing or zeroing specific features to test their causal role.
CLIP alignment	Semantic similarity between text prompt and generated image using CLIP embeddings.

Appendix

Table 4: Glossary of key terms used across DreamReader workflows.

Diffusion Models

Diffusion models learn to reverse gradual data corruption, enabling flexible generation, editing, forecasting, and inference.

See all 1,163 papers

i1: A Simple and Fully Open Recipe for Strong Text-to-Image Models
Jun 9, 2026Boya Zeng, Tianze Luo, Shu Pu +4Training Data Curation T2I Generation
Princeton University
Selective Aggregation of Attention Maps Improves Diffusion-Based Visual Interpretation
Apr 7, 2026Jungwon Park, Jungmin Ko, Dongnam Byun +1T2I Diffusion Models Cross-Attention
Department of Intelligence and Information, Seoul National University, Seoul, Republic of Korea · Interdisciplinary Program in Artificial Intelligence, Seoul National University, Seoul, Republic of Korea
Learning to Read the Contextual Tokens in Diffusion Transformers
Oct 5, 2026Omer Dahary, Etai Sella, Hadar Averbuch-Elor +2Diffusion Model Alignment Diffusion Transformer
Tel Aviv University · Cornell University

Jun 9, 2026J/K move · Enter open · S save

i1: A Simple and Fully Open Recipe for Strong Text-to-Image Models

Boya Zeng, Tianze Luo, Shu Pu, Jucheng Shen+3

Princeton University

Training Data Curation T2I Generation T2I Diffusion Models

Open paper AskPDF arXiv

Diffusion models have consistently driven progress in text-to-image generation. However, it is challenging to attribute recent progress to specific modeling and data choices: state-of-the-art open-weight models provide limited ablations, and do not disclose their training data and full training details. The research community needs fully open (weights, data, and code) models as a foundation for further research; yet existing fully open models still fall significantly short of leading models in performance. In this project, we conduct a systematic investigation of the modeling and data design choices in text-to-image diffusion training and inference with 300+ controlled experiments totaling 700K+ TPU v6e hours. Our experiments highlight several empirical findings (e.g., equal weighting is a strong default for mixing curated datasets) and simple design decisions (e.g., larger text encoder adapters improve performance with minimal added parameters) for training strong models. Guided by these insights, we train i1, a 3B-parameter text-to-image diffusion model using only publicly available datasets. i1 is competitive with leading models on five representative benchmarks (GenEval, DPG, PRISM, CVTG-2K, and LongText), and outperforms the best existing fully open model by 29.5 absolute percentage points on average. We provide the i1 checkpoints, training and inference code, and the data processing pipeline. Together, our findings and the i1 recipe establish a practical foundation for future open research in text-to-image diffusion models. Our code is available at https://github.com/zlab-princeton/i1.

Abstract

Diffusion Models

Explore similar work

i1: A Simple and Fully Open Recipe for Strong Text-to-Image Models

Selective Aggregation of Attention Maps Improves Diffusion-Based Visual Interpretation

Learning to Read the Contextual Tokens in Diffusion Transformers