Image Generation

ARPG: Randomly generate high-quality images by parallel decoding, outperforming existing methods in efficiency, memory, and quality.

New ‘Silent Branding Attack’ poisons text-to-image models, embedding brand logos without text prompts, raising ethical issues for image generation tools.

SANA-Sprint: An efficient diffusion model for ultra-fast text-to-image generation with continuous-time consistency distillation, achieving state-of-the-art performance in speed and quality.

PerCoV2: Open ultra-low bit-rate perceptual image compression using implicit hierarchical masked image modeling, built on Stable Diffusion 3 for bandwidth-constrained applications.

NAR: Neighboring Autoregressive Modeling for efficient visual generation by locality-preserved, parallel decoding.

LightGen: Efficient image generation via knowledge distillation and direct preference optimization.

WISE: Evaluates world knowledge in text-to-image generation.

Seedream 2.0: A native Chinese-English bilingual image generation model that understands cultural nuances and excels in text rendering.

RayFlow: Accelerating diffusion with instance-aware adaptive flow, boosting speed & quality!

PLADIS: Sparsity boosts attention for diffusion models, enhancing text-to-image generation at inference time!

eMIGM: A unified, efficient masked image generation model achieving state-of-the-art performance with fewer resources.

EasyControl: Efficient & flexible control for Diffusion Transformers, enabling sophisticated image generation.

TDM: a new diffusion distillation paradigm unifying trajectory distillation and distribution matching, surpassing teachers in a data-free manner with state-of-the-art performance and low training cost…

ProReflow: Improves diffusion model efficiency via progressive training and direction-focused velocity alignment.

RectifiedHR: Enables training-free high-resolution image generation via energy rectification, boosting both efficiency and effectiveness.

Q-Eval-100K: A new, large dataset for evaluating visual quality and text alignment in AI-generated content.

Likelihood-based generative models get a GAN-like boost via a new Direct Discriminative Optimization, ditching the joint training complexity.

DREAM ENGINE: Text-image interleaved control made easy, unifying text and visual cues for creative image generation.

GCC: Color constancy through diffusion, inpainting a color checker for stable illumination estimation.

M3-AGIQA: A multimodal AI solution that comprehensively assesses AI-generated image quality, achieving state-of-the-art performance by distilling online MLLM capabilities into a local model.