EdiBERT, a generative model for image editing

Last update: Dec 07, 2022

Related tags

Overview

EdiBERT, a generative model for image editing

EdiBERT is a generative model based on a bi-directional transformer, suited for image manipulation. The same EdiBERT model, derived from a single training, can be used on a wide variety of tasks.

We follow the implementation of Taming-Transformers (https://github.com/CompVis/taming-transformers). Main modifications can be found in: taming/models/bert_transformer.py ; scripts/sample_mask_likelihood_maximization.py.

Requirements

A suitable conda environment named edibert can be created and activated with:

conda env create -f environment.yaml
conda activate edibert

FFHQ

Download FFHQ dataset (https://github.com/NVlabs/ffhq-dataset) and put it into data/ffhq/.

Training BERT

In the logs/ folder, download and extract the FFHQ VQGAN:

gdown --id '1P_wHLRfdzf1DjsAH_tG10GXk9NKEZqTg'
tar -xvzf 2021-04-23T18-19-01_ffhq_vqgan.tar.gz

Training on 1 GPUs:

python main.py --base configs/ffhq_transformer_bert_2D.yaml -t True --gpus 0,

Training on 2 GPUs:

python main.py --base configs/ffhq_transformer_bert_2D.yaml -t True --gpus 0,1

Running pre-trained BERT on composite/scribble-edited images

In the logs/ folder, download and extract the FFHQ VQGAN:

gdown --id '1P_wHLRfdzf1DjsAH_tG10GXk9NKEZqTg'
tar -xvzf 2021-04-23T18-19-01_ffhq_vqgan.tar.gz

In the logs/ folder, download and extract the FFHQ BERT:

gdown --id '1YGDd8XyycKgBp_whs9v1rkYdYe4Oxfb3'
tar -xvzf 2021-10-14T16-32-28_ffhq_transformer_bert_2D.tar.gz

folders and place them into logs.

Then, launch the following script for composite images:

python scripts/sample_mask_likelihood_maximization.py -r logs/2021-10-14T16-32-28_ffhq_transformer_bert_2D/checkpoints/epoch=000019.ckpt \
--image_folder data/ffhq_collages/ --mask_folder data/ffhq_collages_masks/ --image_list data/ffhq_collages.txt --keep_img \
--dilation_sampling 1 -k 100 -t 1.0 --batch_size 5 --bert --epochs 2  \
--device 0 --random_order \
--mask_collage --collage_frequency 3 --gaussian_smoothing_collage

Then, launch the following script for edits images:

python scripts/sample_mask_likelihood_maximization.py -r logs/2021-10-14T16-32-28_ffhq_transformer_bert_2D/checkpoints/epoch=000019.ckpt \
--image_folder data/ffhq_edits/ --mask_folder data/ffhq_edits_masks/ --image_list data/ffhq_edits.txt --keep_img \
--dilation_sampling 1 -k 100 -t 1.0 --batch_size 5 --bert --epochs 2  \
--device 0 --random_order \
--mask_collage --collage_frequency 3 --gaussian_smoothing_collage

The samples can then be found in logs/my_model/samples/. Here, the --batch_size argument corresponds to the number of EdiBERT generations per image.

Notebooks for playing with completion/denoising with BERT

Notebooks for image denoising and image inpainting can also be found in the main folder.

EdiBERT, a generative model for image editing

Related tags

Overview

EdiBERT, a generative model for image editing

Requirements

FFHQ

Training BERT

Running pre-trained BERT on composite/scribble-edited images

Notebooks for playing with completion/denoising with BERT

Owner

Annotated, understandable, and visually interpretable PyTorch implementations of: VAE, BIRVAE, NSGAN, MMGAN, WGAN, WGANGP, LSGAN, DRAGAN, BEGAN, RaGAN, InfoGAN, fGAN, FisherGAN

Super-BPD: Super Boundary-to-Pixel Direction for Fast Image Segmentation (CVPR 2020)

A Python package for performing pore network modeling of porous media

All course materials for the Zero to Mastery Machine Learning and Data Science course.

Bayes-Newton—A Gaussian process library in JAX, with a unifying view of approximate Bayesian inference as variants of Newton's algorithm.

Efficient Multi Collection Style Transfer Using GAN

DirectVoxGO reconstructs a scene representation from a set of calibrated images capturing the scene.

This is an implementation for the CVPR2020 paper "Learning Invariant Representation for Unsupervised Image Restoration"

A very lightweight monitoring system for Raspberry Pi clusters running Kubernetes.

Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.

This is a repository for a Semantic Segmentation inference API using the Gluoncv CV toolkit

Credo AI Lens is a comprehensive assessment framework for AI systems. Lens standardizes model and data assessment, and acts as a central gateway to assessments created in the open source community.

the code of the paper: Recurrent Multi-view Alignment Network for Unsupervised Surface Registration (CVPR 2021)

Models Supported: AlbUNet [18, 34, 50, 101, 152] (1D and 2D versions for Single and Multiclass Segmentation, Feature Extraction with supports for Deep Supervision and Guided Attention)

Black-Box-Tuning - Black-Box Tuning for Language-Model-as-a-Service

Integrated Semantic and Phonetic Post-correction for Chinese Speech Recognition

Towards Open-World Feature Extrapolation: An Inductive Graph Learning Approach

ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training

Official Implementation of DE-CondDETR and DELA-CondDETR in "Towards Data-Efficient Detection Transformers"

Source code for "OmniPhotos: Casual 360° VR Photography"