Consistency models achieve fast one-step generation with SOTA FID of 3.55 on CIFAR-10 and 6.20 on ImageNet 64x64 by directly mapping noise to data, outperforming prior distillation techniques.
super hub Canonical reference
GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
Canonical reference. 81% of citing Pith papers cite this work as background.
108
Pith papers citing it
Background
81% of classified citations
abstract
Diffusion models have recently been shown to generate high-quality synthetic images, especially when paired with a guidance technique to trade off diversity for fidelity. We explore diffusion models for the problem of text-conditional image synthesis and compare two different guidance strategies: CLIP guidance and classifier-free guidance. We find that the latter is preferred by human evaluators for both photorealism and caption similarity, and often produces photorealistic samples. Samples from a 3.5 billion parameter text-conditional diffusion model using classifier-free guidance are favored by human evaluators to those from DALL-E, even when the latter uses expensive CLIP reranking. Additionally, we find that our models can be fine-tuned to perform image inpainting, enabling powerful text-driven image editing. We train a smaller model on a filtered dataset and release the code and weights at https://github.com/openai/glide-text2im.
hub tools
citation-role summary
background 23
baseline 2
method 2
citation-polarity summary
claims ledger
- abstract Diffusion models have recently been shown to generate high-quality synthetic images, especially when paired with a guidance technique to trade off diversity for fidelity. We explore diffusion models for the problem of text-conditional image synthesis and compare two different guidance strategies: CLIP guidance and classifier-free guidance. We find that the latter is preferred by human evaluators for both photorealism and caption similarity, and often produces photorealistic samples. Samples from a 3.5 billion parameter text-conditional diffusion model using classifier-free guidance are favored
authors
co-cited works
representative citing papers
Rectified flow learns straight-path neural ODEs for distribution transport, yielding efficient generative models and domain transfers that work well even with a single simulation step.
Cross-attention control in text-conditioned models enables localized and global image edits by editing only the input text prompt.
Textual Inversion learns a single embedding vector from a few images to represent personal concepts inside the text embedding space of a frozen text-to-image model, enabling their composition in natural language prompts.
GLENS uses diffusion models on solver iterates to generate high-quality and diverse initial guesses for multimodal non-convex optimization, leading to faster solver convergence.
VDE accelerates rectified flow models like Flux by 3.22x with LPIPS of 0.069 via velocity decomposition into parallel/orthogonal components plus periodic full-pass anchoring.
AdaMaG is a guidance rule for generative models derived from decomposing continuity-equation effects into divergence and score-parallel terms, with a proof that divergence diverges near the manifold and a time-dependent bound that improves realism at no extra cost.
A multi-exposure video model predicts bracketed linear SDR sequences from single nonlinear SDR input, which a merging model combines into HDR video preserving shadow and highlight detail.
HIR-ALIGN augments limited target data for hyperspectral restoration by creating proxy clean images, synthesizing aligned HSIs with blur-robust diffusion and warp-based transfer, then finetuning models to lower target-domain risk.
ImageAttributionBench is a benchmark dataset demonstrating that state-of-the-art image attribution methods lack robustness to image degradation and fail to generalize to semantically disjoint domains.
RLFSeg repurposes pretrained generative models via Rectified Flow for direct latent-space image-to-mask mapping in text-based segmentation, outperforming diffusion-based methods especially in zero-shot cases.
Introduces closed-set C-Bench and open-set O-Bench for layout-guided diffusion models, a unified semantic-spatial scoring protocol, and ranks six models after generating and evaluating 319,086 images.
GENFIG1 is a new benchmark that tests whether vision-language models can create effective Figure 1 visuals capturing the central scientific idea from paper text.
FrameDiT proposes Matrix Attention for DiTs to achieve SOTA video generation with improved temporal coherence and efficiency comparable to local factorized attention.
SVG360 lifts a single SVG to a view-conditioned representation, uses spatial memory to propagate consistent parts across views, and applies structure-aware vectorization to produce editable multiview SVGs.
BeyondMimic combines compact motion tracking with a unified guided latent diffusion model to master diverse agile behaviors from human demos and solve unseen downstream tasks via test-time classifier guidance.
FaSTA* combines LLM fast planning with A* search and inductive subroutine mining to create an efficient agent for multi-turn image editing tasks.
COCO-Inpaint supplies a large-scale dataset and evaluation protocol focused on inpainting-based image forgeries to benchmark existing detection methods.
Janus decouples visual encoding into task-specific pathways inside a single autoregressive transformer to unify multimodal understanding and generation while outperforming earlier unified models.
Scaled vanilla autoregressive models based on Llama achieve 2.18 FID on ImageNet 256x256 image generation, beating popular diffusion models without visual inductive biases.
ANCHOR dataset exposes T2I model weaknesses on multi-subject abstractive captions; SAFE uses LLMs for subject extraction and embedding enhancement to improve consistency.
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.
UniSim learns a universal real-world simulator from orchestrated diverse datasets, enabling zero-shot deployment of policies trained purely in simulation.
Latent Consistency Models enable high-fidelity text-to-image generation in 2-4 steps by directly predicting solutions to the probability flow ODE in latent space, distilled from pre-trained LDMs.
citing papers explorer
-
Consistency Models
Consistency models achieve fast one-step generation with SOTA FID of 3.55 on CIFAR-10 and 6.20 on ImageNet 64x64 by directly mapping noise to data, outperforming prior distillation techniques.
-
Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
Rectified flow learns straight-path neural ODEs for distribution transport, yielding efficient generative models and domain transfers that work well even with a single simulation step.
-
Prompt-to-Prompt Image Editing with Cross Attention Control
Cross-attention control in text-conditioned models enables localized and global image edits by editing only the input text prompt.
-
An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion
Textual Inversion learns a single embedding vector from a few images to represent personal concepts inside the text embedding space of a frozen text-to-image model, enabling their composition in natural language prompts.
-
GLENS: Global Search via Learning from Solver Iterates with Diffusion Models
GLENS uses diffusion models on solver iterates to generate high-quality and diverse initial guesses for multimodal non-convex optimization, leading to faster solver convergence.
-
VDE: Training-Free Accelerating Rectified Flow Model via Velocity Decomposition and Estimation
VDE accelerates rectified flow models like Flux by 3.22x with LPIPS of 0.069 via velocity decomposition into parallel/orthogonal components plus periodic full-pass anchoring.
-
Probability-Conserving Flow Guidance
AdaMaG is a guidance rule for generative models derived from decomposing continuity-equation effects into divergence and score-parallel terms, with a proof that divergence diverges near the manifold and a time-dependent bound that improves realism at no extra cost.
-
Generating HDR Video from SDR Video
A multi-exposure video model predicts bracketed linear SDR sequences from single nonlinear SDR input, which a merging model combines into HDR video preserving shadow and highlight detail.
-
HIR-ALIGN: Enhancing Hyperspectral Image Restoration via Diffusion-Based Data Generation
HIR-ALIGN augments limited target data for hyperspectral restoration by creating proxy clean images, synthesizing aligned HSIs with blur-robust diffusion and warp-based transfer, then finetuning models to lower target-domain risk.
-
ImageAttributionBench: How Far Are We from Generalizable Attribution?
ImageAttributionBench is a benchmark dataset demonstrating that state-of-the-art image attribution methods lack robustness to image degradation and fail to generalize to semantically disjoint domains.
-
From Diffusion to Rectified Flow: Rethinking Text-Based Segmentation
RLFSeg repurposes pretrained generative models via Rectified Flow for direct latent-space image-to-mask mapping in text-based segmentation, outperforming diffusion-based methods especially in zero-shot cases.
-
Benchmarking Layout-Guided Diffusion Models through Unified Semantic-Spatial Evaluation in Closed and Open Settings
Introduces closed-set C-Bench and open-set O-Bench for layout-guided diffusion models, a unified semantic-spatial scoring protocol, and ranks six models after generating and evaluating 319,086 images.
-
GENFIG1: Visual Summaries of Scholarly Work as a Challenge for Vision-Language Models
GENFIG1 is a new benchmark that tests whether vision-language models can create effective Figure 1 visuals capturing the central scientific idea from paper text.
-
FrameDiT: Diffusion Transformer with Matrix Attention for Efficient Video Generation
FrameDiT proposes Matrix Attention for DiTs to achieve SOTA video generation with improved temporal coherence and efficiency comparable to local factorized attention.
-
SVG360: Editable Multiview Vector Graphics from a Single SVG
SVG360 lifts a single SVG to a view-conditioned representation, uses spatial memory to propagate consistent parts across views, and applies structure-aware vectorization to produce editable multiview SVGs.
-
BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusion
BeyondMimic combines compact motion tracking with a unified guided latent diffusion model to master diverse agile behaviors from human demos and solve unseen downstream tasks via test-time classifier guidance.
-
FaSTA$^*$: Fast-Slow Toolpath Agent with Subroutine Mining for Efficient Multi-turn Image Editing
FaSTA* combines LLM fast planning with A* search and inductive subroutine mining to create an efficient agent for multi-turn image editing tasks.
-
COCO-Inpaint: A Benchmark for Detecting and Localizing Inpainting-Based Image Manipulations
COCO-Inpaint supplies a large-scale dataset and evaluation protocol focused on inpainting-based image forgeries to benchmark existing detection methods.
-
Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation
Janus decouples visual encoding into task-specific pathways inside a single autoregressive transformer to unify multimodal understanding and generation while outperforming earlier unified models.
-
Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation
Scaled vanilla autoregressive models based on Llama achieve 2.18 FID on ImageNet 256x256 image generation, beating popular diffusion models without visual inductive biases.
-
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.
-
Learning Interactive Real-World Simulators
UniSim learns a universal real-world simulator from orchestrated diverse datasets, enabling zero-shot deployment of policies trained purely in simulation.
-
Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference
Latent Consistency Models enable high-fidelity text-to-image generation in 2-4 steps by directly predicting solutions to the probability flow ODE in latent space, distilled from pre-trained LDMs.
-
AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning
A single motion module trained on videos adds temporally coherent animation to any personalized text-to-image model derived from the same base without additional tuning.
-
Scalable Diffusion Models with Transformers
DiTs achieve SOTA FID of 2.27 on ImageNet 256x256 by scaling transformer-based latent diffusion models, with performance improving consistently as Gflops increase.
-
LAION-5B: An open large-scale dataset for training next generation image-text models
LAION-5B is an openly released dataset of 5.85 billion CLIP-filtered image-text pairs that enables replication of foundational vision-language models.
-
Phenaki: Variable Length Video Generation From Open Domain Textual Description
Phenaki generates arbitrary-length videos from sequences of text prompts by tokenizing videos with causal temporal attention and generating tokens with a text-conditioned masked transformer, trained jointly on images and videos.
-
Imagen Video: High Definition Video Generation with Diffusion Models
Imagen Video generates high-definition text-conditional videos via a cascade of base and super-resolution diffusion models, achieving high fidelity and controllability.
-
Human Motion Diffusion Model
MDM is a classifier-free diffusion model that generates expressive human motions by predicting clean samples rather than noise, supporting text and action conditioning and outperforming prior methods on standard benchmarks.
-
Diffusion Posterior Sampling for General Noisy Inverse Problems
Diffusion models solve noisy (non)linear inverse problems via approximated posterior sampling that blends diffusion steps with manifold gradients without strict consistency projection.
-
Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding
Imagen achieves state-of-the-art photorealistic text-to-image generation by scaling a text-only pretrained T5 language model within a diffusion framework, reaching FID 7.27 on COCO without training on it.
-
Hierarchical Text-Conditional Image Generation with CLIP Latents
A hierarchical prior-decoder model using CLIP latents generates more diverse text-conditional images than direct methods while preserving photorealism and caption fidelity.
-
Video Diffusion Models
A diffusion model for video generation extends image architectures with joint image-video training and improved conditional sampling, delivering first large-scale text-to-video results and state-of-the-art performance on video prediction and unconditional generation benchmarks.
-
High-Resolution Image Synthesis with Latent Diffusion Models
Latent diffusion models achieve state-of-the-art inpainting and competitive results on unconditional generation, scene synthesis, and super-resolution by performing the diffusion process in the latent space of pretrained autoencoders with cross-attention conditioning, while cutting computational and
-
Boosting Text-to-Image Diffusion Models via Core Token Attention-Based Seed Selection
ABSS ranks diffusion seeds by early cross-attention strength to prompt core tokens and retains only the top-k for full generation, yielding consistent gains in alignment and quality on Stable Diffusion variants.
-
Simple Approximation and Derivative Free Inference-Time Scaling for Diffusion Models via Sequential Monte Carlo on Path Measures
URGE performs unbiased inference-time scaling for diffusion models by attaching multiplicative path weights from Girsanov estimation and resampling trajectories, with a proven equivalence to prior particle-wise SMC schemes.
-
Do Less, Achieve More: Do We Need Every-Step Optimization for RL Fine-tuning of Diffusion Models?
AdaScope adaptively selects optimal RL intervention points during diffusion denoising by monitoring structural and semantic changes, delivering 66% higher performance at 59% lower cost than full-trajectory RL baselines.
-
Reduce the Artifacts Bias for More Generalizable AI-Generated Image Detection
SEF introduces GAN upsampling for diverse artifacts and expert fusion to reduce domain interference, yielding stronger generalization on 13 benchmarks for AI-generated image detection.
-
FlashClear: Ultra-Fast Image Content Removal via Efficient Step Distillation and Feature Caching
FlashClear delivers up to 122x faster object removal than prior diffusion models via adversarial step distillation and asymmetric attention caching while preserving visual quality.
-
Intermediate Representations are Strong AI-Generated Image Detectors
Intermediate layer embedding sensitivity to perturbations distinguishes AI-generated images from real ones, yielding higher AUROC on GenImage and Forensics Small benchmarks than prior methods.
-
VibeToken: Scaling 1D Image Tokenizers and Autoregressive Models for Dynamic Resolution Generations
VibeToken enables autoregressive image generation at arbitrary resolutions using 64 tokens for 1024x1024 images with 3.94 gFID, constant 179G FLOPs, and better efficiency than diffusion or fixed AR baselines.
-
Rethinking Where to Edit: Task-Aware Localization for Instruction-Based Image Editing
Task-aware localization via attention cues and feature centroids from source/target streams in IIE models improves non-edit consistency while preserving instruction following.
-
PostureObjectstitch: Anomaly Image Generation Considering Assembly Relationships in Industrial Scenarios
PostureObjectStitch generates assembly-aware anomaly images by decoupling multi-view features into high-frequency, texture and RGB components, modulating them temporally in a diffusion model, and applying conditional loss plus geometric priors to preserve correct component relationships.
-
MuPPet: Multi-person 2D-to-3D Pose Lifting
MuPPet introduces person encoding, permutation augmentation, and dynamic multi-person attention to outperform prior single- and multi-person 2D-to-3D pose lifting methods on group interaction datasets while improving occlusion robustness.
-
Controllable Image Generation with Composed Parallel Token Prediction
A new formulation for composing discrete generative processes enables precise control over novel condition combinations in image generation, cutting error rates by 63% and speeding up inference.
-
Erasure or Erosion? Evaluating Compositional Degradation in Unlearned Text-To-Image Diffusion Models
Unlearning methods that strongly erase concepts from text-to-image diffusion models consistently degrade performance on attribute binding, spatial reasoning, and counting tasks.
-
MPDiT: Multi-Patch Global-to-Local Transformer Architecture For Efficient Flow Matching and Diffusion Model
MPDiT uses a hierarchical multi-patch design in transformers to lower computation in diffusion models by handling coarse global features first then fine local details, plus faster-converging embeddings.
-
Forget-It-All: Multi-Concept Machine Unlearning via Concept-Aware Neuron Masking
FIA uses contrastive concept saliency and temporal-spatial neuron identification to build unified masks that erase multiple target concepts while preserving general generation quality in diffusion models.
-
Scaling Up AI-Generated Image Detection with Generator-Aware Prototypes
GAPL learns a compact set of canonical forgery prototypes and applies two-stage LoRA training to build a low-variance feature space that improves generalization across GAN and diffusion generators.