DiT-MoE

Large-scale Parameter Diffusion Transformer Model

CommonProductProgrammingDeep LearningDiffusion Models

Visit

DiT-MoE is a diffusion transformer model implemented in PyTorch that can scale up to 16 billion parameters while competing with dense networks and demonstrating highly optimized inference capabilities. It represents cutting-edge technology in deep learning for handling large-scale datasets, carrying significant research and application value.

Product Finder

Product Submit

AI Models Finder

MCP Servers

MCP Client

MCP Inspector

Case Tutorials

Latest AI News

AI Daily Brief

DiT-MoE

DiT-MoE Visit Over Time

DiT-MoE Visit Trend

DiT-MoE Visit Geography

DiT-MoE Traffic Sources

DiT-MoE Alternatives

Understanding Deep Learning — Deep understanding of the principles and applications of deep learning

ml-mdm — Efficiently trains high-quality text-to-image diffusion models

DiT-MoE — Large-scale Parameter Diffusion Transformer Model

YOLO-NAS Pose — An open-source library for training PyTorch computer vision models.

zero_to_gpt — Learn deep learning from scratch and implement a GPT model

contrastors — A PyTorch-based contrastive learning toolkit.

torchao — Native PyTorch quantization and sparsity training and inference library

DiffusionRL — Large-scale Reinforcement Learning for Diffusion Models

Color-diffusion — Using diffusion models for colorizing black and white images.

DIAMOND — A reinforcement learning agent trained in a diffusion world model

LLMs-from-scratch — Deep dive into the inner workings of large language models.

ControlNets for Stable Diffusion 3.5 Large — Three ControlNet models for Stable Diffusion 3.5 Large

Diffusers Image Outpaint — Image extension using diffusion models

InspireMusic — A music, song, and audio generation toolkit based on PyTorch that supports high-quality audio generation.

Profiling Data in DeepSeek Infra — Analyzes the computation and communication overlap strategies in V3/R1, providing performance analysis data for deep learning frameworks.

DragonDiffusion — Image editing solution based on diffusion models

CS25 — Stanford University's CS25 course focuses on Transformer models, which have made a significant impact worldwide in the field of deep learning.

FreeU — A free method to improve the sampling quality of diffusion models

xinsir — Deep Learning, Representation Learning, Fine-Grained Classification

TFLearn — Advanced API simplifies TensorFlow deep learning

Fathom 2.0 — One-stop deep learning solution

d1 — Improving the reasoning capabilities of diffusion large language models using reinforcement learning.

Make-An-Audio 2 — Text-to-audio generation technology based on diffusion models

InvSR — Multi-step image super-resolution model based on diffusion inversion.

AXLearn — A unified deep learning training framework.

diffusion-e2e-ft — Fine-tuning tool for image-conditioned diffusion models

Diffusion with Forward Models — Solves random inverse problems without direct supervision.

Neuralhub — An AI deep learning platform that offers a wide range of models and tools to foster an AI innovation community

GraphCast — Deep Learning Weather Prediction Model

Civitai — A platform for stable diffusion AI art models.