Image Generation

Textoon: Generating vivid 2D cartoon characters from text descriptions in under a minute, revolutionizing animation workflow.

SynthLight: A novel diffusion model relights portraits realistically by learning to re-render synthetic faces, generalizing remarkably well to real photographs.

Scaling visual tokenizers dramatically improves image and video generation, achieving state-of-the-art results and outperforming existing methods with fewer computations by focusing on decoder scaling…

Boosting diffusion model performance at inference time, this research introduces a novel framework that goes beyond simply increasing denoising steps. By cleverly searching for better noise candidates…

AnyStory: A unified framework enables high-fidelity personalized image generation for single and multiple subjects, addressing subject fidelity challenges in existing methods.

R3GAN: A modernized GAN baseline achieves state-of-the-art results with a simple, stable loss function and modern architecture, debunking the myth that GANs are hard to train.

This paper unveils critical thresholds for efficient visual autoregressive model computation, proving sub-quartic time is impossible beyond a certain input matrix norm while establishing efficient app…

Through-The-Mask uses mask-based motion trajectories to generate realistic videos from images and text, overcoming limitations of existing methods in handling complex multi-object motion.

MagicFace achieves high-fidelity facial expression editing via AU control, preserving identity and background using a diffusion model and ID encoder, significantly outperforming existing methods.

LightningDiT resolves the optimization dilemma in latent diffusion models by aligning latent space with pre-trained vision models, achieving state-of-the-art ImageNet 256x256 generation with over 21x …

VisionReward, a novel reward model, surpasses existing methods by precisely capturing multi-dimensional human preferences for image and video generation, enabling more accurate and stable model optimi…

Edicho: a novel training-free method for consistent image editing across diverse images, achieving precise consistency by leveraging explicit correspondence.

3to4D: Animate any 3D object with text prompts, preserving visual quality and achieving realistic motion!

VideoMaker achieves high-fidelity zero-shot customized video generation by cleverly harnessing the inherent power of video diffusion models, eliminating the need for extra feature extraction and injec…

Distilled Decoding (DD) drastically speeds up image generation from autoregressive models by using flow matching to enable one-step sampling, achieving significant speedups while maintaining acceptabl…

CLEAR: Conv-Like Linearization boosts pre-trained Diffusion Transformers, achieving 6.3x faster 8K image generation with minimal quality loss.

UIP2P: Unsupervised instruction-based image editing achieves high-fidelity edits by enforcing Cycle Edit Consistency, eliminating the need for ground-truth data.

Boosting autoregressive visual generation speed by 3.6-9.5x, this research introduces parallel processing while preserving model simplicity and generation quality.

Affordance-Aware Object Insertion uses a novel Mask-Aware Dual Diffusion model & SAM-FB dataset to realistically place objects in scenes, considering contextual relationships.

FashionComposer revolutionizes fashion image creation through flexible composition of garments, faces, and poses.