Stars
Flux diffusion model implementation using quantized fp8 matmul & remaining layers use faster half precision accumulate, which is ~2x faster on consumer devices.
Official repository for our work on micro-budget training of large-scale diffusion models.
A general fine-tuning kit geared toward image/video/audio diffusion models.
Reference implementation for DPO (Direct Preference Optimization)
XPhoneBERT: A Pre-trained Multilingual Model for Phoneme Representations for Text-to-Speech (INTERSPEECH 2023)
Train transformer language models with reinforcement learning.
A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)
Implementation of Show, Attend and Read: A Simple and Strong Baseline for Irregular Text Recognition published in AAAI 2019 in PyTorch
PyTorch code of my ICDAR 2021 paper Vision Transformer for Fast and Efficient Scene Text Recognition (ViTSTR)
GRUEN for Evaluating Linguistic Quality of Generated Text (EMNLP 2020 Findings)
Finetune the 1.4B latent diffusion text2img-large checkpoint from CompVis using deepspeed. (work-in-progress)
High-Resolution Image Synthesis with Latent Diffusion Models
GLIDE: a diffusion-based text-conditional image synthesis model
Simple image captioning model
Implementation / replication of DALL-E, OpenAI's Text to Image Transformer, in Pytorch
🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
An open source nesting application for laser cutters, plasma cutters and other CNC machines
Simple raster image tracer and vectorizer written in JavaScript.
for splitting words into their component syllables
Progressive Growing of GANs for Improved Quality, Stability, and Variation
Implementation of Graph Convolutional Networks in TensorFlow
Free and Open source Web Builder Framework. Next generation tool for building templates without coding
High-performance JavaScript polyline simplification library
An implementation of the Graham's Scan Convex Hull algorithm in JavaScript.
Image-to-image translation with conditional adversarial nets