3 مستودعات
Awesome GitHub RepositoriesMulti-GPU Training Distributions
Distributing diffusion model training across multiple GPUs using data parallelism for faster convergence.
Distinct from Diffusion Model Training: Distinct from Diffusion Model Training: specifically covers multi-GPU distribution of the training workload, not the general training process.
Explore 3 awesome GitHub repositories matching artificial intelligence & ml · Multi-GPU Training Distributions. Refine with filters or upvote what's useful.
Awesome Multi-GPU Training Distributions GitHub Repositories
اعثر على أفضل المستودعات باستخدام الذكاء الاصطناعي.سنبحث عن أفضل المستودعات المطابقة باستخدام الذكاء الاصطناعي.
- lucidrains/dalle2-pytorch
lucidrains/DALLE2-pytorch
11,310عرض على GitHubThis is a PyTorch implementation of a text-to-image model designed for synthesizing high-fidelity images from natural language descriptions. It utilizes a diffusion image generator to transform latent embeddings into visual data through an iterative denoising process. The system employs a two-stage latent mapping process, using a CLIP-based latent prior to map text embeddings to image embeddings before decoding them into pixels. It features a cascading diffusion decoder that produces high-resolution imagery by passing low-resolution outputs through a sequence of models at increasing scales.
Distributes the training of diffusion priors and decoders across multiple GPU clusters to handle large datasets.
Pythonartificial-intelligencedeep-learningtext-to-image - lucidrains/denoising-diffusion-pytorch
lucidrains/denoising-diffusion-pytorch
10,614عرض على GitHubImplementation of Denoising Diffusion Probabilistic Model in Pytorch
Distributes diffusion model training across multiple GPUs using PyTorch's DistributedDataParallel for faster convergence.
Pythonartificial-intelligencedeep-learninggenerative-model - lucidrains/imagen-pytorch
lucidrains/imagen-pytorch
8,415عرض على GitHubThis is a PyTorch-based implementation of diffusion models for synthesizing photorealistic images and video. It provides a framework for text-to-image and text-to-video generation, as well as unconditional image synthesis. The system utilizes a cascading diffusion pipeline to produce high-resolution imagery by passing low-resolution outputs through a sequence of super-resolution models. It also includes capabilities for image inpainting, allowing the reconstruction of masked or missing regions of visual media guided by surrounding context and text prompts. The project includes tools for diff
Distributes diffusion model training across multiple GPUs using data parallelism to increase throughput.
Pythonartificial-intelligencedeep-learningimagination-machine
