Related papers: FasterDiT: Towards Faster Diffusion Transformers T…

Diffusion models produce high quality images but inference is costly due to many denoising steps and heavy matrix operations. We present DiffPro, a post-training, hardware-faithful framework that works with the exact integer kernels used in…

Layout generation is a foundation task of graphic design, which requires the integration of visual aesthetics and harmonious expression of content delivery. However, existing methods still face challenges in generating precise and visually…

Diffusion models have demonstrated exceptional capabilities in generating high-fidelity images but typically suffer from inefficient sampling. Many solver designs and noise scheduling strategies have been proposed to dramatically improve…

Diffusion Transformers have demonstrated remarkable performance in video generation. However, their long input sequences incur substantial latency due to the quadratic complexity of full attention. Various sparse attention mechanisms have…

Diffusion Transformers (DiTs) have achieved state-of-the-art performance in generative modeling, yet their high computational cost hinders real-time deployment. While feature caching offers a promising training-free acceleration solution by…

Deep learning methods for accelerated MRI achieve state-of-the-art results but largely ignore additional speedups possible with noncartesian sampling trajectories. To address this gap, we created a generative diffusion model-based…

Diffusion Transformers have become a powerful backbone for text-to-image generation, but their layered and cross-modal generation process makes safety control fundamentally different from prompt-level filtering or output-level detection.…

Diffusion models (DMs) are powerful generative models capable of producing high-fidelity images but are constrained by high computational costs due to iterative multi-step inference. While Neural Architecture Search (NAS) can optimize DMs,…

Diffusion models have been successfully adapted to text generation tasks by mapping the discrete text into the continuous space. However, there exist nonnegligible gaps between training and inference, owing to the absence of the forward…

Transfer learning of diffusion models to smaller target domains is challenging, as naively fine-tuning the model often results in poor generalization. Test-time guidance methods help mitigate this by offering controllable improvements in…

Diffusion Transformer (DiT) faces challenges when generating images with higher resolution compared at training resolution, causing especially structural degradation due to attention dilution. Previous approaches attempt to mitigate this by…

All-in-one image restoration tackles different types of degradations with a unified model instead of having task-specific, non-generic models for each degradation. The requirement to tackle multiple degradations using the same model can…

The most advanced text-to-image (T2I) models require significant training costs (e.g., millions of GPU hours), seriously hindering the fundamental innovation for the AIGC community while increasing CO2 emissions. This paper introduces…

Diffusion Transformers have recently shown remarkable effectiveness in generating high-quality 3D point clouds. However, training voxel-based diffusion models for high-resolution 3D voxels remains prohibitively expensive due to the cubic…

Diffusion Models (DMs) have demonstrated state-of-the-art performance in content generation without requiring adversarial training. These models are trained using a two-step process. First, a forward - diffusion - process gradually adds…

Diffusion models have recently shown promise in offline RL. However, these methods often suffer from high training costs and slow convergence, particularly when using transformer-based denoising backbones. While several optimization…

Diffusion model deployment has been suffering from high energy consumption and inference latency despite its superior performance in visual generation tasks. Dynamic voltage and frequency scaling (DVFS) offers a promising solution to…

Recent progress in diffusion models has significantly advanced the field of human image animation. While existing methods can generate temporally consistent results for short or regular motions, significant challenges remain, particularly…

Diffusion models have revolutionized video generation, becoming essential tools in creative content generation and physical simulation. Transformer-based architectures (DiTs) and classifier-free guidance (CFG) are two cornerstones of this…

Diffusion models have greatly improved visual generation but are hindered by slow generation speed due to the computationally intensive nature of solving generative ODEs. Rectified flow, a widely recognized solution, improves generation…