paper-with-me

Papers

Scalable Diffusion Models with Transformers

2022-12-19 · ICCV 2023 1 · William Peebles, Saining Xie

We explore a new class of diffusion models based on the transformer architecture. We train latent diffusion models of images, replacing the commonly-used U-Net backbone with a transformer that operates on latent patches. We analyze the scalability of our Diffusion Transformers (DiTs) through the lens of forward pass complexity as measured by Gflops. We find that DiTs with higher Gflops -- through increased transformer depth/width or increased number of input tokens -- consistently have lower FID. In addition to possessing good scalability properties, our largest DiT-XL/2 models outperform all prior diffusion models on the class-conditional ImageNet 512x512 and 256x256 benchmarks, achieving a state-of-the-art FID of 2.27 on the latter.

📄 PDF Abstract BibTeX arXiv:2212.09748

Code (13)

facebookresearch/DiT 공식 구현 pytorch
FineDiffusion/FineDiffusion pytorch
MindSpore-scientific/code-5/tree/main/Scalable-Sharpness-Aware-Minimization mindspore
VachanVY/diffusion-transformer pytorch
chuanyangjin/fast-dit pytorch
huggingface/diffusers jax
hustvl/dig pytorch
locuslab/get pytorch
milmor/diffusion-transformer pytorch
milmor/diffusion-transformer-keras tf
mindspore-lab/mindone mindspore
nyu-systems/grendel-gs pytorch
senmaoy/RAT-Diffusion pytorch

Tasks

Image Generation

Methods 이 논문이 사용한 방법론

Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
Concatenated Skip Connection A Concatenated Skip Connection is a type of skip connection that seeks to reuse features by concatenating them to new layers, allowing more information to be retained from…
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Transformer A Transformer is a model architecture that eschews recurrence and instead relies entirely on an [attention…
U-Net 설명 없음
Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers

2024-01-16 · Nanye Ma, Mark Goldstein, Michael S. Albergo, Nicholas M. Boffi 외

We present Scalable Interpolant Transformers (SiT), a family of generative models built on the backbone of Diffusion Transformers (DiT). The interpolant framework, which allows for connecting two distributions in a more …

Image Generation

Scaling Diffusion Mamba with Bidirectional SSMs for Efficient Image and Video Generation

2024-05-24 · Shentong Mo, Yapeng Tian

In recent developments, the Mamba architecture, known for its selective state space approach, has shown potential in the efficient modeling of long sequences. However, its application in image generation remains underexp…

Image GenerationMambaVideo Generation

Scalable High-Resolution Pixel-Space Image Synthesis with Hourglass Diffusion Transformers

2024-01-21 · Katherine Crowson, Stefan Andreas Baumann, Alex Birch, Tanishq Mathew Abraham 외

We present the Hourglass Diffusion Transformer (HDiT), an image generative model that exhibits linear scaling with pixel count, supporting training at high-resolution (e.g. $1024 \times 1024$) directly in pixel-space. Bu…

Image Generation

PDE-SSM: A Spectral State Space Approach to Spatial Mixing in Diffusion Transformers

2026-03-14 · Eshed Gal, Moshe Eliasof, Siddharth Rout, Eldad Haber arxiv

The success of vision transformers-especially for generative modeling-is limited by the quadratic cost and weak spatial inductive bias of self-attention. We propose PDE-SSM, a spatial state-space block that replaces atte…

DiT-Head: High-Resolution Talking Head Synthesis using Diffusion Transformers

2023-12-11 · Aaron Mir, Eduardo Alonso, Esther Mondragón

We propose a novel talking head synthesis pipeline called "DiT-Head", which is based on diffusion transformers and uses audio as a condition to drive the denoising process of a diffusion model. Our method is scalable and…

Denoising