StarVector is a foundation model for SVG generation that transforms vectorization into a code generation task. Using a vision-language modeling architecture, StarVector processes both visual and te…

GroundCUA

Generating figures from research papers, using textual captions from the paper.

Pipeline to create Paper2Fig dataset, a dataset for text-to-image generation from research papers and figures (e.g., diagrams of architectures or methods in fields like Machine Learning or Computer…

Karras et al. (2022) diffusion models for 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.

Fast and memory-efficient exact attention

[NeurIPS 2023] Official implementations of "Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large Language Models"

Home of StarCoder: fine-tuning & inference!

Ongoing research training transformer models at scale

Denoising Diffusion Probabilistic Models from scratch

Implementation of GigaGAN, new SOTA GAN out of Adobe. Culmination of nearly a decade of research into GANs

Video editing with Python

Let us control diffusion models!

LAVIS - A One-stop Library for Language-Vision Intelligence

🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support

(ෆ`꒳´ෆ) A Survey on Text-to-Image Generation/Synthesis.

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

v objective diffusion inference code for PyTorch.

A microservice that interacts and fetches information about the most important companies of the world

Course content and resources for the AIAIART course.

Model API for GALACTICA

PyTorch package for the discrete VAE used for DALL·E.

Taming Transformers for High-Resolution Image Synthesis

High-fidelity performance metrics for generative models in PyTorch

OCR-VQGAN, a discrete image encoder (tokenizer and detokenizer) for figure images in Paper2Fig100k dataset. Implementation of OCR Perceptual loss for clear text-within-image generation. Fork from V…