Diffusion Lens: Interpreting Text Encoders in Text-to-Image Pipelines (2024.acl-long)
Copied to clipboard
| Challenge: | Text-to-image diffusion models use a latent text prompt to guide image generation . however, the process by which the encoder produces the text representation is unknown . |
| Approach: | They propose a method for analyzing the text encoder of T2I models by generating images from its intermediate representations. |
| Outcome: | The proposed method provides valuable insights into the text encoder component in T2I pipelines. |
Similar Papers
Follow the Flow: On Information Flow Across Textual Tokens in Text-to-Image Models (2026.acl-long)
Copied to clipboard
| Challenge: | Prior work focused on improving alignment by refining the diffusion process, ignoring the role of the text encoder, which guides the diffusion. |
| Approach: | They investigate how semantic information is distributed across token representations in text-to-image prompts by patching techniques to uncover encoding patterns. |
| Outcome: | The proposed model can improve alignment and generation quality by modifying the diffusion stage and the cross-attention mechanism. |
Padding Tone: A Mechanistic Analysis of Padding Tokens in T2I Models (2025.naacl-long)
Copied to clipboard
| Challenge: | Text-to-image (T2I) diffusion models rely on encoded prompts to guide the image generation process. |
| Approach: | They conduct the first in-depth analysis of the role padding tokens play in T2I diffusion models by using two causal techniques to analyze how information is encoded in the representation of tokens across different components of the pipeline. |
| Outcome: | The proposed techniques reveal that padding tokens may affect the model’s output during text encoding, during the diffusion process, or be effectively ignored. |
Kandinsky 3: Text-to-Image Synthesis for Multifunctional Generative Framework (2024.emnlp-demo)
Copied to clipboard
Arkhipkin Vladimir, Viacheslav Vasilev, Andrei Filatov, Igor Pavlov, Julia Agafonova, Nikolai Gerasimenko, Anna Averchenkova, Evelina Mironova, Bukashkin Anton, Konstantin Kulikov, Andrey Kuznetsov, Denis Dimitrov
| Challenge: | Text-to-image (T2I) diffusion models are popular for image manipulation, but also for video generation. |
| Approach: | They propose a novel T2I diffusion model based on latent diffusion that extends the base model for various applications. |
| Outcome: | The proposed model achieves high quality and photorealism and is 3 times faster than the base model. |
Rapid Diffusion: Building Domain-Specific Text-to-Image Synthesizers with Fast Inference Speed (2023.acl-industry)
Copied to clipboard
Bingyan Liu, Weifeng Lin, Zhongjie Duan, Chengyu Wang, Wu Ziheng, Zhang Zipeng, Kui Jia, Lianwen Jin, Cen Chen, Jun Huang
| Challenge: | Text-to-Image Synthesis (TIS) aims to generate images based on textual inputs . but, current diffusion-based models lack entity knowledge and low inference speed . |
| Approach: | They propose a framework for training and deploying latent diffusion models with rich entity knowledge injected and optimized networks. |
| Outcome: | The proposed framework improves image quality and inference speed and can be used in industrial applications. |
DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models (2023.acl-long)
Copied to clipboard
| Challenge: | Recent advances in diffusion models have enabled high-quality image generation . generating images with desired details requires proper prompts . |
| Approach: | They analyze syntactic and semantic characteristics of diffusion models and their prompts . they pinpoint specific hyperparameter values and prompt styles that can lead to model errors . |
| Outcome: | The first large-scale text-to-image prompt dataset totals 6.5TB . it contains 14 million images generated by Stable Diffusion, 1.8 million unique prompts, and hyperparameters specified by real users. |
AcT2I: Evaluating and Improving Action Depiction in Text-to-Image Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Text-to-Image (T2I) models have been successful in generating images from textual descriptions, but they struggle to capture nuanced and implicit attributes inherent in action depiction. |
| Approach: | They propose a benchmark to evaluate the performance of T2I models in generating images from action-centric prompts. |
| Outcome: | The proposed model achieves an increase of 72% on AcT2I. |
Evaluation of Text-to-Image Generation from a Creativity Perspective (2025.findings-emnlp)
Copied to clipboard
| Challenge: | Recent studies have assessed the creativity of T2I models, but little has been done on the quality of generated images and image-text alignment. |
| Approach: | They define the creativity of T2I models and propose metrics to test reliability . they also develop a pipeline capable of transforming existing image-text datasets into benchmarks . |
| Outcome: | The proposed method tests the reliability of the metric and a fully automated pipeline capable of transforming image-text datasets into benchmarks tailored for evaluating creativity. |
T2I-ReasonBench: Benchmarking Reasoning-Informed Text-to-Image Generation (2026.findings-acl)
Copied to clipboard
| Challenge: | Text-to-image (T2I) generative models have demonstrated exceptional capability in synthesizing high-quality images from textual prompts. |
| Approach: | They propose a benchmark to explore the knowledge-driven reasoning capabilities of T2I models. |
| Outcome: | The proposed benchmark examines the knowledge-driven reasoning capabilities of T2I models. |
Multimodal Pragmatic Jailbreak on Text-to-image Models (2025.acl-long)
Copied to clipboard
Tong Liu, Zhixin Lai, Jiawen Wang, Gengyuan Zhang, Shuo Chen, Philip Torr, Vera Demberg, Volker Tresp, Jindong Gu
| Challenge: | Existing jailbreaks for diffusion-based text-to-image models generate unsafe content . experimental results show that all tested models suffer from unsafe generation . |
| Approach: | They propose a jailbreak that triggers diffusion-based text-to-image models to generate the image with visual text, resulting in unsafe content. |
| Outcome: | The proposed model generates image with visual text, but the model is unsafe under such jailbreak. |
Kandinsky: An Improved Text-to-Image Synthesis with Image Prior and Latent Diffusion (2023.emnlp-demo)
Copied to clipboard
Anton Razzhigaev, Arseniy Shakhmatov, Anastasia Maltseva, Vladimir Arkhipkin, Igor Pavlov, Ilya Ryabov, Angelina Kuts, Alexander Panchenko, Andrey Kuznetsov, Denis Dimitrov
| Challenge: | Experimental evaluations demonstrate FID score of 8.03 on the COCO-30K dataset, marking our model as the top open source performer in terms of measurable image generation quality. |
| Approach: | They propose a latent diffusion-based model that combines image prior and latent diffusive techniques to create a text-to-image architecture. |
| Outcome: | The proposed model achieves the highest FID score among open-source models . it is compared with the state-of-the-art models on the COCO-30K dataset . |