LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models
Reviewed by Pithpith:XR7ZCHU7open to challenge →
read the original abstract
Recent advancements in text-to-image diffusion models have yielded impressive results in generating realistic and diverse images. However, these models still struggle with complex prompts, such as those that involve numeracy and spatial reasoning. This work proposes to enhance prompt understanding capabilities in diffusion models. Our method leverages a pretrained large language model (LLM) for grounded generation in a novel two-stage process. In the first stage, the LLM generates a scene layout that comprises captioned bounding boxes from a given prompt describing the desired image. In the second stage, a novel controller guides an off-the-shelf diffusion model for layout-grounded image generation. Both stages utilize existing pretrained models without additional model parameter optimization. Our method significantly outperforms the base diffusion model and several strong baselines in accurately generating images according to prompts that require various capabilities, doubling the generation accuracy across four tasks on average. Furthermore, our method enables instruction-based multi-round scene specification and can handle prompts in languages not supported by the underlying diffusion model. We anticipate that our method will unleash users' creativity by accurately following more complex prompts. Our code, demo, and benchmark are available at: https://llm-grounded-diffusion.github.io
This paper has not been read by Pith yet.
Forward citations
Cited by 15 Pith papers
-
OneHOI: Unifying Human-Object Interaction Generation and Editing
OneHOI unifies HOI generation and editing in one conditional diffusion transformer using role-aware tokens, structured attention, and joint training on mixed datasets to reach SOTA on both tasks.
-
Self-Correcting Text-to-Video Generation with Misalignment Detection and Localized Refinement
VideoRepair detects text-video misalignments via MLLM-generated questions and performs localized, region-preserving refinement to improve alignment in existing T2V diffusion models.
-
ANCHOR: LLM-driven Subject Conditioning for Text-to-Image Synthesis
ANCHOR dataset exposes T2I model weaknesses on multi-subject abstractive captions; SAFE uses LLMs for subject extraction and embedding enhancement to improve consistency.
-
ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment
ELLA introduces a timestep-aware semantic connector to link LLMs with diffusion models for improved dense prompt following, validated on a new 1K-prompt benchmark.
-
IV-CoT: Implicit Visual Chain-of-Thought for Structure-Aware Text-to-Image Generation
IV-CoT introduces an implicit chain-of-thought framework that decomposes visual queries into a structural-to-semantic cascade with training-only sketch supervision to improve structure-aware text-to-image generation.
-
EPIC: Efficient Predicate-Guided Inference-Time Control for Compositional Text-to-Image Generation
EPIC introduces predicate-guided inference-time search that lifts compositional T2I prompt accuracy from 34% to 71% on GenEval2 with 31-81% lower execution costs.
-
DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing
DDA-Thinker decouples planning from generation and applies dual-atomic RL with checklist-based rewards to boost reasoning in image editing, yielding competitive results on RISE-Bench and KRIS-Bench.
-
Ego-InBetween: Generating Object State Transitions in Ego-Centric Videos
EgoIn uses a fine-tuned vision-language model to infer transition steps and a conditioning module plus auxiliary supervision to generate coherent egocentric video sequences of object state changes.
-
Making Image Editing Easier via Adaptive Task Reformulation with Agentic Executions
An MLLM agent reformulates image editing tasks into executable operation sequences to improve reliability on challenging cases across existing generative backbones.
-
EPIG: Emotion-Based Prompting for Personalised Image Generation
EPIG is a training-free prompt enrichment technique using valence-arousal representations that reduces mean arousal error by 14% versus naive insertion and 12% versus LLM expansion on a 10-prompt benchmark while prese...
-
STEDiff: Strengthening Text Embedding for Text-to-Image Alignment in Diffusion Model
STEDiff improves semantic alignment in text-to-image diffusion models via training-free embedding strengthening with the [EOT] token and a spatial semantic loss, showing gains on T2I-CompBench.
-
Compositional Text-to-Image Generation Via Region-aware Bimodal Direct Preference Optimization
BiDPO extends Diffusion DPO to bimodal preferences and adds region-aware guidance, improving compositional fidelity in text-to-image generation over prior methods.
-
SOWing Information: Cultivating Contextual Coherence with MLLMs in Image Generation
SOW uses MLLMs and attention to selectively control unidirectional diffusion for pixel-level fidelity and contextual coherence in text-vision-to-image tasks.
-
The Platonic Representation Hypothesis
Representations learned by large AI models are converging toward a shared statistical model of reality.
-
PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning
A temporal pooling layer added to LLaVA smooths video feature distributions and lifts performance on dense video captioning and QA to new SOTA levels without extra parameters.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.