Colab notebook for openai/glide-text2im.

Last update: Oct 19, 2022

Overview

GLIDE text2im on Colab

This repository provides a Colab notebook to produce images conditioned on text prompts with GLIDE [1].

Usage

Run text2im.ipynb

Tip: press <Ctrl+F9> to run everything.

Results

The process is based on the small, filtered-data GLIDE model, with classifier-free guidance.

Results consist of 64x64 images, and the corresponding 256x256 upsampled versions.

Expected run-time: 2m30s (for the one-time set-up), 1 min (64x64 sampling), 30 sec (256x256 upsampling).

_{Several uncurated samples obtained with the same prompt: "a magnificent French rooster singing".}

Safety considerations

The small model has 300 million parameters, compared to the unreleased 3.5 billion parameter model.

As described in Appendix F.1, the training dataset was filtered so that it would not contain:

images of humans and human-like objects,
images of violent objects,
two prevalent hate symbols in America (swastika and confederate flag).

References

[1] Alex Nichol, Prafulla Dhariwal, Aditya Ramesh, et al. GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models. arXiv preprint 2112.10741. 2021.

Colab notebook for openai/glide-text2im.

Related tags

Overview

GLIDE text2im on Colab

Usage

Results

Safety considerations

References

Owner

Wok

GCC: Graph Contrastive Coding for Graph Neural Network Pre-Training @ KDD 2020

The "breathing k-means" algorithm with datasets and example notebooks

A Comprehensive Empirical Study of Vision-Language Pre-trained Model for Supervised Cross-Modal Retrieval

Code for paper: Towards Tokenized Human Dynamics Representation

Joint Gaussian Graphical Model Estimation: A Survey

Code for Understanding Pooling in Graph Neural Networks

A Benchmark For Measuring Systematic Generalization of Multi-Hierarchical Reasoning

Code for a seq2seq architecture with Bahdanau attention designed to map stereotactic EEG data from human brains to spectrograms, using the PyTorch Lightning.

A simple, clean TensorFlow implementation of Generative Adversarial Networks with a focus on modeling illustrations.

DeepProbLog is an extension of ProbLog that integrates Probabilistic Logic Programming with deep learning by introducing the neural predicate.

IPATool-py: download ipa easily

RRxIO - Robust Radar Visual/Thermal Inertial Odometry: Robust and accurate state estimation even in challenging visual conditions.

CVPR 2021: "The Spatially-Correlative Loss for Various Image Translation Tasks"

Yolo ros - YOLO-ROS for HUAWEI ATLAS200

[ICML'21] Estimate the accuracy of the classifier in various environments through self-supervision

DrWhy is the collection of tools for eXplainable AI (XAI). It's based on shared principles and simple grammar for exploration, explanation and visualisation of predictive models.

Official implementation of NeurIPS 2021 paper "Contextual Similarity Aggregation with Self-attention for Visual Re-ranking"

A curated list of awesome projects and resources related fastai

Locally cache assets that are normally streamed in POPULATION: ONE

HEAM: High-Efficiency Approximate Multiplier Optimization for Deep Neural Networks