OFA
by OFA-Sys
Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework
AI summary
Sequence-to-sequence framework
Develops a unified sequence-to-sequence learning framework to unify modalities and tasks through pretraining and fine-tuning
- stars
- 2.4K
- forks
- 248
- watching
- 21
Similar projects
Found by comparing what the projects do, not just their names.
Transformer-based OFA model
Transforms the OFA-Chinese model to work with the Hugging Face Transformers framework
haotian-liu/llava20.7K
Visual Instruction System
A system that uses large language and vision models to generate and process visual instructions
Image generator
An interactive workflow for generating high-definition images from text prompts using a human-in-the-loop approach
Image manipulator
This project provides an implementation of a method to manipulate images by driving the style with text.
Vision Model Evaluator
A tool to evaluate vision-language models by comparing their performance on various tasks such as image recognition and text generation.
Vision-Language Model
Enabling vision-language understanding by fine-tuning large language models on visual data.
Image generator
An implementation of DALL-E 2's text-to-image synthesis neural network in PyTorch
Text Recognition Benchmark
Provides a benchmarking framework and implementation for deep learning-based text recognition models
openai/clip26.5K
Image-text predictor
A neural network trained on image and text pairs to predict the most relevant text snippet given an image
Multimodal model trainer
An implementation of a multimodal LLM training paradigm to enhance truthfulness and ethics in language models
Multimodal reasoning model
An implementation of multimodal chain-of-thought reasoning in language models using a decoupled training framework for rationale generation and answer inference.
OCR system
An end-to-end OCR system implementing General OCR Theory towards a unified model
Image inpainting model
Unsupervised feature learning by image inpainting using Generative Adversarial Networks (GANs)
Facial cartoonizer
An implementation of a deep learning-based facial cartoonization system using TensorFlow
Video generator
This project generates animated videos from open-domain images by leveraging pre-trained video diffusion priors.
