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.
hub Canonical reference
SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations
Canonical reference. 82% of citing Pith papers cite this work as background.
92
Pith papers citing it
301
external citations · Pith
Background
82% of classified citations
abstract
Guided image synthesis enables everyday users to create and edit photo-realistic images with minimum effort. The key challenge is balancing faithfulness to the user input (e.g., hand-drawn colored strokes) and realism of the synthesized image. Existing GAN-based methods attempt to achieve such balance using either conditional GANs or GAN inversions, which are challenging and often require additional training data or loss functions for individual applications. To address these issues, we introduce a new image synthesis and editing method, Stochastic Differential Editing (SDEdit), based on a diffusion model generative prior, which synthesizes realistic images by iteratively denoising through a stochastic differential equation (SDE). Given an input image with user guide of any type, SDEdit first adds noise to the input, then subsequently denoises the resulting image through the SDE prior to increase its realism. SDEdit does not require task-specific training or inversions and can naturally achieve the balance between realism and faithfulness. SDEdit significantly outperforms state-of-the-art GAN-based methods by up to 98.09% on realism and 91.72% on overall satisfaction scores, according to a human perception study, on multiple tasks, including stroke-based image synthesis and editing as well as image compositing.
hub tools
citation-role summary
background 9
baseline 1
method 1
citation-polarity summary
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.
Counterfactually fair image classifiers need not satisfy group fairness when a latent attribute G correlates with the sensitive attribute; reducing reliance on G (via CKD) restores both.
PhyEditBench is a new benchmark for physics-aware image editing with real and synthetic instances plus a training-free PhyWorld baseline that uses test-time scaling to outperform SOTA models.
Sparse Context achieves 2-4x faster inference in reference-conditioned diffusion models by fine-tuning with random token dropping and applying task-aware selection at inference time, without loss of visual quality.
A weakly-supervised image quality transfer method generates synthetic distorted DWI images from quality labels to train improved distortion correction models for prostate MRI.
Jeffrey guidance applies Jeffrey's rule of conditioning to diffusion models to target prescribed marginal distributions while preserving conditional structure, demonstrated via embedding matching and fairness enforcement.
Consistent-Inversion introduces reverse consistency guidance that corrects early target denoising steps by checking reversibility toward the source inversion trajectory under the original prompt.
A transformer model predicts in vivo hip and knee contact forces from uncalibrated monocular video at accuracy matching subject-specific musculoskeletal simulations under leave-one-subject-out validation.
Chameleon proposes the first large-scale cross-domain compositing dataset and a disentangled encoder plus gated diffusion transformer that outperforms prior in-domain and cross-domain methods on plausibility and fidelity.
Presents Decoupled Time Guidance (DTG) for training-free generative video super-resolution by temporally decoupling conditional and unconditional diffusion signals.
Orthogonal Negative Guidance subtracts only the orthogonal component of negative-prompt attention features from positive ones in FLUX models to suppress concepts while preserving semantics and quality.
DeltaCam models relative changes in camera intrinsics via Δ-parameterized neural adaptors in video diffusion models trained on synthetic data to enable controllable generation and real-world transfer.
StableHand introduces a quality-aware flow matching framework conditioned on predicted four-channel per-frame hand observation quality to estimate dual-hand world-space motion from egocentric video, achieving SOTA results with 20-25% W-MPJPE reduction on HOT3D and ARCTIC benchmarks.
Object functionalization is cast as neural graph completion over a functional graph of parts, contacts, and motions, followed by geometry realization that also rectifies erroneous motions, demonstrated on furniture with a new paired dataset.
HL-OutPaint enables high-resolution outpainting of long video sequences via a coarse-to-fine pipeline that first builds Global Coarse Guidance through global-local frame swapping then synthesizes details.
A planner-orchestrator system learns long-horizon image editing by maximizing outcome-based rewards from a vision-language judge and refining plans from successful trajectories.
AID amortizes guidance for diffusion inpainting by training a reusable module via an auxiliary Gaussian formulation and continuous-time actor-critic algorithm, improving quality-speed trade-off with under 1% overhead.
Proposes V2V-Zero, a training-free framework replacing text conditioning with VLM final-layer hidden states from visual pages, achieving 0.85 on GenEval and 32.7/100 on new Simple-V2V Bench across models including video extension.
RevealLayer decomposes natural images into multiple RGBA layers using diffusion models with region-aware attention, occlusion-guided adaptation, and a composite loss, outperforming prior methods on a new benchmark dataset.
OT-Bridge Editor uses geometrically constrained entropic optimal transport to synthesize CAG images with precise stenosis, improving downstream detection by 27.8% on ARCADE and 23.0% on a multi-center dataset.
Wasserstein Lagrangian Mechanics formalizes second-order dynamics in Wasserstein space and provides an algorithm to learn them from observed marginals without specifying the Lagrangian, outperforming gradient flows on various dynamics.
ResetEdit embeds a recoverable discrepancy signal during image generation in diffusion models to reconstruct an approximate original latent for high-fidelity text-guided editing.
GeoEdit constructs local tangent frames from small perturbations to initial noise, enabling Jacobian-free on-manifold edits in diffusion models via alternating tangent steps and diffusion projections.
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.
-
Do Counterfactually Fair Image Classifiers Satisfy Group Fairness? -- A Theoretical and Empirical Study
Counterfactually fair image classifiers need not satisfy group fairness when a latent attribute G correlates with the sensitive attribute; reducing reliance on G (via CKD) restores both.
-
PhyEditBench: A Real-World Multi-Stage Benchmark for Physics-Aware Image Editing
PhyEditBench is a new benchmark for physics-aware image editing with real and synthetic instances plus a training-free PhyWorld baseline that uses test-time scaling to outperform SOTA models.
-
Keep The Essentials: Efficient Reference Conditioned Generation via Token Dropping
Sparse Context achieves 2-4x faster inference in reference-conditioned diffusion models by fine-tuning with random token dropping and applying task-aware selection at inference time, without loss of visual quality.
-
Learning to Distort: Weakly-Supervised Image Quality Transfer for Prostate DWI Correction
A weakly-supervised image quality transfer method generates synthetic distorted DWI images from quality labels to train improved distortion correction models for prostate MRI.
-
Towards More General Control of Diffusion Models Using Jeffrey Guidance
Jeffrey guidance applies Jeffrey's rule of conditioning to diffusion models to target prescribed marginal distributions while preserving conditional structure, demonstrated via embedding matching and fairness enforcement.
-
Consistent-Inversion: Reverse Consistency Guidance for Structure-Preserving Visual Editing
Consistent-Inversion introduces reverse consistency guidance that corrects early target denoising steps by checking reversibility toward the source inversion trajectory under the original prompt.
-
From Pixels to Newtons: Predicting In Vivo Joint Contact Forces from Monocular Video
A transformer model predicts in vivo hip and knee contact forces from uncalibrated monocular video at accuracy matching subject-specific musculoskeletal simulations under leave-one-subject-out validation.
-
Chameleon: Style-Content Disentangled Framework for Cross-Domain Object Compositing
Chameleon proposes the first large-scale cross-domain compositing dataset and a disentangled encoder plus gated diffusion transformer that outperforms prior in-domain and cross-domain methods on plausibility and fidelity.
-
DTG-Restore: Training-Free Diffusion Refinement for Generative Video Super-Resolution
Presents Decoupled Time Guidance (DTG) for training-free generative video super-resolution by temporally decoupling conditional and unconditional diffusion signals.
-
Orthogonal Negative Guidance in Attention Feature Space for Text-to-Image Generation
Orthogonal Negative Guidance subtracts only the orthogonal component of negative-prompt attention features from positive ones in FLUX models to suppress concepts while preserving semantics and quality.
-
DeltaCam: Differential Intrinsic Camera Modeling for Video Generation
DeltaCam models relative changes in camera intrinsics via Δ-parameterized neural adaptors in video diffusion models trained on synthetic data to enable controllable generation and real-world transfer.
-
StableHand: Quality-Aware Flow Matching for World-Space Dual-Hand Motion Estimation from Egocentric Video
StableHand introduces a quality-aware flow matching framework conditioned on predicted four-channel per-frame hand observation quality to estimate dual-hand world-space motion from egocentric video, achieving SOTA results with 20-25% W-MPJPE reduction on HOT3D and ARCTIC benchmarks.
-
Functionalization via Structure Completion and Motion Rectification
Object functionalization is cast as neural graph completion over a functional graph of parts, contacts, and motions, followed by geometry realization that also rectifies erroneous motions, demonstrated on furniture with a new paired dataset.
-
HL-OutPaint: Coarse-to-Fine Video Outpainting for High-Resolution Long-Range Videos
HL-OutPaint enables high-resolution outpainting of long video sequences via a coarse-to-fine pipeline that first builds Global Coarse Guidance through global-local frame swapping then synthesizes details.
-
From Plans to Pixels: Learning to Plan and Orchestrate for Open-Ended Image Editing
A planner-orchestrator system learns long-horizon image editing by maximizing outcome-based rewards from a vision-language judge and refining plans from successful trajectories.
-
Amortized Guidance for Image Inpainting with Pretrained Diffusion Models
AID amortizes guidance for diffusion inpainting by training a reusable module via an auxiliary Gaussian formulation and continuous-time actor-critic algorithm, improving quality-speed trade-off with under 1% overhead.
-
Beyond Text Prompts: Visual-to-Visual Generation as A Unified Paradigm
Proposes V2V-Zero, a training-free framework replacing text conditioning with VLM final-layer hidden states from visual pages, achieving 0.85 on GenEval and 32.7/100 on new Simple-V2V Bench across models including video extension.
-
RevealLayer: Disentangling Hidden and Visible Layers via Occlusion-Aware Image Decomposition
RevealLayer decomposes natural images into multiple RGBA layers using diffusion models with region-aware attention, occlusion-guided adaptation, and a composite loss, outperforming prior methods on a new benchmark dataset.
-
Geometrically Constrained Stenosis Editing in Coronary Angiography via Entropic Optimal Transport
OT-Bridge Editor uses geometrically constrained entropic optimal transport to synthesize CAG images with precise stenosis, improving downstream detection by 27.8% on ARCADE and 23.0% on a multi-center dataset.
-
A Call to Lagrangian Action: Learning Population Mechanics from Temporal Snapshots
Wasserstein Lagrangian Mechanics formalizes second-order dynamics in Wasserstein space and provides an algorithm to learn them from observed marginals without specifying the Lagrangian, outperforming gradient flows on various dynamics.
-
ResetEdit: Precise Text-guided Editing of Generated Image via Resettable Starting Latent
ResetEdit embeds a recoverable discrepancy signal during image generation in diffusion models to reconstruct an approximate original latent for high-fidelity text-guided editing.
-
GeoEdit: Local Frames for Fast, Training-Free On-Manifold Editing in Diffusion Models
GeoEdit constructs local tangent frames from small perturbations to initial noise, enabling Jacobian-free on-manifold edits in diffusion models via alternating tangent steps and diffusion projections.
-
StyleID: A Perception-Aware Dataset and Metric for Stylization-Agnostic Facial Identity Recognition
StyleID supplies human-perception-aligned benchmarks and fine-tuned encoders that improve facial identity recognition robustness across stylization types and strengths.
-
Latent Fourier Transform
LatentFT uses latent-space Fourier transforms and frequency masking in diffusion autoencoders to enable timescale-specific manipulation of musical structure in generative models.
-
UniEditBench: A Unified and Cost-Effective Benchmark for Image and Video Editing via Distilled MLLMs
UniEditBench unifies image and video editing evaluation with a nine-plus-eight operation taxonomy and cost-effective 4B/8B distilled MLLM evaluators that align with human judgments.
-
Your Pre-trained Diffusion Model Secretly Knows Restoration
Pre-trained diffusion models inherently support image restoration that can be unlocked by optimizing prompt embeddings at the text encoder output using a diffusion bridge formulation, achieving competitive results on models like WAN and FLUX without fine-tuning.
-
In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer
ICEdit achieves state-of-the-art instructional image editing in Diffusion Transformers via in-context generation, requiring only 0.1% of prior training data and 1% trainable parameters.
-
VIPaint: Image Inpainting with Pre-Trained Diffusion Models via Variational Inference
VIPaint uses hierarchical variational inference to optimize a non-Gaussian Markov approximation of the diffusion posterior, enabling better inpainting and inverse problems with pre-trained and latent diffusion models.
-
DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation
DreamGaussian creates high-quality textured 3D meshes from single-view images in 2 minutes via generative Gaussian Splatting with mesh extraction and UV refinement.
-
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
-
GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
A 3.5-billion-parameter diffusion model with classifier-free guidance generates images preferred over DALL-E by human raters and can be fine-tuned for text-guided inpainting.
-
PRISM: Latent Composition Consistency for Single-Image Reflection Removal
Pretrained VAE latents have far lower transmission–reflection coherence than pixels, so flow matching on FLUX plus cycle and contrastive losses can separate both layers in one pass.
-
Generative Refinement for Low-Budget Black-Box Optimization
SPARROW is a black-box optimization method that treats a fixed generative sampler as a structured proposal operator and applies rank-based selection over evaluated candidates to achieve low-budget optimization with asymptotic convergence guarantees over the sampler support.
-
GeoEdit: Geometry-Aware Object Editing via Dual-Branch Denoising
GeoEdit introduces a Lift-Manipulate-Render-Denoise pipeline with dual-branch denoising and variance-homogeneous injection for 3D-consistent object editing in single photos.
-
MirrorPPR: Exemplar-Based Portrait Photo Retouching
MirrorPPR extracts retouching operations from exemplar pairs via a dedicated extractor and transfers them to query images through a LoRA-adapted Diffusion Transformer, enabled by a new 47-million-pair dataset and self-augmentation for alignment.
-
DanceOPD: On-Policy Generative Field Distillation
Hard-routed, single low-noise on-policy velocity matching composes conflicting image-generation capabilities into one flow student better than joint training, merging, or dense OPD baselines.
-
SpatialFlow-GRPO: Where Spatial Credit Drives Image Editing
SpatialFlow-GRPO adds region-level reward feedback and spatial alignment to Flow-GRPO-style RL for image editing, reporting gains on GEdit-Bench, ImgEdit-Bench, and a new MultiEditBench.
-
VT-DUDA: Visual Token Conditioning for Diffusion-guided Unsupervised Domain Adaptation
VT-DUDA proposes visual token conditioning from source images concatenated with text embeddings in latent diffusion models to improve synthetic target-style data generation for unsupervised domain adaptation.
-
Scaling Parallel Sequence Models to Foundation-Scale Vision Encoders
C-GSPN scales 2D spatial propagation to foundation vision encoders via a fast CUDA kernel, compressed blocks, and two-stage distillation, matching ViT performance with 15% fewer parameters and 4x block speedup at 2K resolution.
-
AnchorSteer: Self-Discovered Concept Injection for Structure-Preserving Music Editing
AnchorSteer couples self-discovered semantic concept vectors with structural anchoring in diffusion models to achieve controllable music editing with preserved structure.
-
Audio Pirates: Black-box Audio Watermark Removal via Diffusion Priors
DiffErase removes black-box audio watermarks via diffusion priors by adding intermediate noise and regenerating with a pretrained model, preserving quality across audio domains.
-
RT-Lynx: Putting the GEMM Sparsity In a Right Way for Diffusion Models
RT-Lynx shifts DiT sparsity from weights to activations, reports up to 1.55x linear-layer speedup while preserving generation quality across multiple diffusion models.
-
Variance Reduction for Expectations with Diffusion Teachers
CARV amortizes upstream diffusion teacher costs over noise resamples with timestep importance sampling and stratified-inverse-CDF sampling, delivering 2-3x effective compute gains in text-to-3D experiments and order-of-magnitude variance cuts in single-step distillation.
-
Are Watermarked Images Editable? SafeMark for Watermark-Preserving Text-Guided Image Editing
SafeMark integrates a thresholded watermark-decoding loss into diffusion editors to enable text-guided edits that preserve embedded watermarks with high bit accuracy.
-
MIRAGE: Robust multi-modal architectures translate fMRI-to-image models from vision to mental imagery
MIRAGE achieves state-of-the-art mental image reconstruction from fMRI on the NSD-Imagery benchmark by using a linear backbone with multi-modal text and image features fed to a diffusion model.
-
ACE-LoRA: Adaptive Orthogonal Decoupling for Continual Image Editing
ACE-LoRA introduces adaptive orthogonal decoupling and rank-invariant compression for continual image editing in diffusion models, plus the CIE-Bench benchmark.
-
Contrastive-SDXL: Annotation-Preserving Night-Time Augmentation for Pedestrian Detection
Contrastive-SDXL augments daytime images into realistic night-time versions using SDXL-Turbo with LoRA and multi-level DINOv2 contrastive losses, yielding 6-7% lower miss rate on pedestrian detection versus daytime-only training.
-
Score-Based Generative Modeling through Anisotropic Stochastic Partial Differential Equations
Anisotropic SPDEs preserve geometric data structure over longer timescales in score-based generative modeling, yielding better image quality than standard SDE baselines and flow matching in unconditional and conditional tasks.