Code for instruction-tuning Stable Diffusion.
-
Updated
Feb 16, 2024 - Python
Code for instruction-tuning Stable Diffusion.
Easiest way of fine-tuning HuggingFace video classification models
Just some miscellaneous utility functions / decorators / modules related to Pytorch and Accelerate to help speed up implementation of new AI research
Optimal Sparse Decision Trees
stable diffusion, controlnet, tensorrt, accelerate
A set of scripts and configurations for pretraining of Large Language Models (LLM)
Unofficial DynaDUSt3R reimplementation trained on Stereo4D (research only).
GPT* - Training faster small transformers using ALiBi, Parallel Residual Connections and more!
Language Modeling Research Hub, a comprehensive compendium for enthusiasts and scholars delving into the fascinating realm of language models (LMs), with a particular focus on large language models (LLMs)
Train and fine-tune diffusion models. Perform image-to-image class transfer experiments.
Transformers training in a supercomputer with the 🤗 Stack and Slurm
Experience the power of the FLUX.1-dev diffusion model combined with a massive collection of 255+ community-created LoRAs! This Gradio application provides an easy-to-use interface to explore diverse artistic styles directly on top of the FLUX base model.
Communication-Efficient Diffusion Denoising Parallelization via Reuse-then-Predict Mechanism (NIPS'25)
vapoursynth version for DRBA
A pytorch example using Hugging Face Accelerate Library with DogsVsCats dataset
Scripts and extensions for Stable Diffusion
A Gradio-based demo application for comparing state-of-the-art OCR models: DeepSeek-OCR, Dots.OCR, HunyuanOCR, and Nanonets-OCR2-3B.
Visual System Integrator - Accelerate your embedded development
Simple lightweight trainer to optimise PyTorch models.
Training HuggingFace's CLMs with Accelerate
Add a description, image, and links to the accelerate topic page so that developers can more easily learn about it.
To associate your repository with the accelerate topic, visit your repo's landing page and select "manage topics."