Image Generation

RelaCtrl: Relevance-guided control boosts diffusion transformer efficiency, cutting parameters by intelligently allocating resources.

Diffusion-Sharpening enhances diffusion model fine-tuning by optimizing sampling trajectories, achieving faster convergence and high inference efficiency without extra NFEs, leading to improved alignm…

VidCRAFT3 enables high-quality image-to-video generation with precise control over camera movement, object motion, and lighting, pushing the boundaries of visual content creation.

MRS: a novel, training-free sampler, drastically speeds up controllable image generation using Mean Reverting Diffusion, achieving 10-20x speedup across various tasks.

Magic141 generates one-minute video clips in under a minute by cleverly factorizing the generation task and employing optimization techniques.

CustomVideoX: Zero-shot personalized video generation, exceeding existing methods in quality & consistency via 3D reference attention and dynamic adaptation.

Animate Anyone 2 creates high-fidelity character animations by incorporating environmental context, resulting in seamless character-environment integration and more realistic object interactions.

Dual Caption Preference Optimization (DCPO) significantly boosts diffusion model image quality by using paired captions to resolve data distribution conflicts and irrelevant prompt issues.

Goku: a novel family of joint image-and-video generation models uses rectified flow Transformers, achieving industry-leading performance with a robust data pipeline and training infrastructure.

On-device Sora makes high-quality, diffusion-based text-to-video generation possible on smartphones, overcoming computational and memory limitations through novel techniques.

OmniHuman-1: Scaling up one-stage conditioned human animation through novel mixed-condition training.

LayerTracer innovatively synthesizes cognitive-aligned layered SVGs via diffusion transformers, bridging the gap between AI and professional design standards by learning from a novel dataset of sequen…

Boosting Diffusion Bridge Models: A new distillation technique accelerates inference speed by 4x to 100x, sometimes even improving image quality!

Researchers significantly enhance latent consistency models’ performance by introducing Cauchy loss, mitigating outlier effects, and employing novel training strategies, thus bridging the gap with dif…

DIFFSPLAT repurposes 2D image diffusion models to natively generate high-quality 3D Gaussian splats, overcoming limitations in existing 3D generation methods.

Researchers significantly enhanced autoregressive image generation by integrating chain-of-thought reasoning strategies, achieving a remarkable +24% improvement on the GenEval benchmark.

TokenVerse: Extract & combine visual concepts from multiple images for creative image generation!

GPS-guided image generation is here! This paper leverages GPS data to create highly realistic images reflecting specific locations, even reconstructing 3D models from 2D photos.

EMO2 achieves realistic audio-driven avatar video generation by employing a two-stage framework: first generating hand poses directly from audio and then using a diffusion model to synthesize full-bod…

X-Dyna: a novel diffusion-based pipeline generates realistic human image animation using a zero-shot approach by integrating a Dynamics-Adapter for dynamic detail preservation, exceeding state-of-the-…