Image Generation

FouRA: a novel low-rank adaptation method improves text-to-image generation by learning projections in the Fourier domain and using an adaptive rank selection strategy, addressing LoRA’s limitations o…

FlowTurbo: Blazing-fast, high-quality flow-based image generation via a velocity refiner!

ICTM efficiently solves linear inverse problems using flow priors by iteratively optimizing local MAP objectives, outperforming other flow-based methods.

NEMO pinpoints & deactivates neurons memorizing training data in diffusion models, boosting privacy & image diversity.

FasterDiT accelerates Diffusion Transformers training 7x without architecture modification by analyzing SNR probability density functions and implementing a new supervision method.

Faster Diffusion achieves significant speedups in diffusion model inference by cleverly reusing encoder features and enabling parallel processing, eliminating the need for computationally expensive di…

FastDrag: One-step image manipulation using generative models, drastically improving editing speed without sacrificing quality.

Conditional Conjugate Integrators (CCI) drastically accelerate sampling in iterative refinement models for inverse problems, achieving high-quality results with only a few steps.

FashionR2R leverages diffusion models to realistically translate rendered fashion images into photorealistic counterparts, enhancing realism and preserving fine-grained clothing textures.

FairQueue improves fair text-to-image generation by addressing prompt learning’s quality issues through prompt queuing and attention amplification.

This paper presents a novel neural network architecture that simultaneously learns to generate and segment images in an unsupervised manner, achieving accurate results across multiple datasets without…

Face2QR: A unified framework generates aesthetically pleasing, scannable QR codes that faithfully preserve facial features, solving the conflict between aesthetics, identity, and scannability.

LOCO Edit achieves precise, localized image editing in diffusion models via a single-step, training-free method leveraging low-dimensional semantic subspaces.

This paper theoretically proves the existence and uniqueness of fixed points in DDIM inversion, optimizing the loss function for improved image editing and extending this approach to unsupervised imag…

FlowDCN: A purely convolutional generative model achieves state-of-the-art image generation speed and quality at arbitrary resolutions, surpassing transformer-based models.

This research introduces adversarial concept preservation, a novel method for safely erasing undesirable concepts from diffusion models, outperforming existing techniques by preserving related sensiti…

This paper introduces a novel post-processing technique that significantly boosts the perceptual quality of images generated by consistency models using a joint classifier-discriminator adversarially …

EfficientNAT: a novel approach to token-based image synthesis boosts performance and slashes computational costs by cleverly disentangling and optimizing spatial-temporal interactions between image to…

EM Distillation (EMD) efficiently trains one-step diffusion models by using an Expectation-Maximization approach, achieving state-of-the-art image generation quality and outperforming existing methods…

The Efficient Diffusion Transformer (EDT) framework significantly speeds up and improves image generation by leveraging a lightweight architecture, human-like sketching-inspired Attention Modulation M…