All Projects → zassou65535 → image_generator_2

zassou65535 / image_generator_2

Licence: other
Progressive GANによる画像生成器

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to image generator 2

Swapnet
Virtual Clothing Try-on with Deep Learning. PyTorch reproduction of SwapNet by Raj et al. 2018. Now with Docker support!
Stars: ✭ 202 (+551.61%)
Mutual labels:  image-generation
universum-contracts
text-to-image generation gems / libraries incl. moonbirds, cyberpunks, coolcats, shiba inu doge, nouns & more
Stars: ✭ 17 (-45.16%)
Mutual labels:  image-generation
progressive-growing-of-gans.pytorch
Unofficial PyTorch implementation of "Progressive Growing of GANs for Improved Quality, Stability, and Variation".
Stars: ✭ 51 (+64.52%)
Mutual labels:  progressive-gan
Pytorch Cyclegan And Pix2pix
Image-to-Image Translation in PyTorch
Stars: ✭ 16,477 (+53051.61%)
Mutual labels:  image-generation
CoCosNet-v2
CoCosNet v2: Full-Resolution Correspondence Learning for Image Translation
Stars: ✭ 312 (+906.45%)
Mutual labels:  image-generation
CycleGAN-Models
Models generated by CycleGAN
Stars: ✭ 42 (+35.48%)
Mutual labels:  image-generation
Arbitrary Text To Image Papers
A collection of arbitrary text to image papers with code (constantly updating)
Stars: ✭ 196 (+532.26%)
Mutual labels:  image-generation
netflix-show-generator
A tool for generating Netflix show image
Stars: ✭ 18 (-41.94%)
Mutual labels:  image-generation
soft-intro-vae-pytorch
[CVPR 2021 Oral] Official PyTorch implementation of Soft-IntroVAE from the paper "Soft-IntroVAE: Analyzing and Improving Introspective Variational Autoencoders"
Stars: ✭ 170 (+448.39%)
Mutual labels:  image-generation
multiple-objects-gan
Implementation for "Generating Multiple Objects at Spatially Distinct Locations" (ICLR 2019)
Stars: ✭ 111 (+258.06%)
Mutual labels:  image-generation
Graphite
Open source 2D node-based raster/vector graphics editor (Photoshop + Illustrator + Houdini = Graphite)
Stars: ✭ 223 (+619.35%)
Mutual labels:  image-generation
MoCoGAN-HD
[ICLR 2021 Spotlight] A Good Image Generator Is What You Need for High-Resolution Video Synthesis
Stars: ✭ 224 (+622.58%)
Mutual labels:  image-generation
vqgan-clip-app
Local image generation using VQGAN-CLIP or CLIP guided diffusion
Stars: ✭ 94 (+203.23%)
Mutual labels:  image-generation
Paddlegan
PaddlePaddle GAN library, including lots of interesting applications like First-Order motion transfer, wav2lip, picture repair, image editing, photo2cartoon, image style transfer, and so on.
Stars: ✭ 4,987 (+15987.1%)
Mutual labels:  image-generation
texturize
🤖🖌️ Generate photo-realistic textures based on source images. Remix, remake, mashup! Useful if you want to create variations on a theme or elaborate on an existing texture.
Stars: ✭ 495 (+1496.77%)
Mutual labels:  image-generation
Conditional Gan
Tensorflow implementation for Conditional Convolutional Adversarial Networks.
Stars: ✭ 202 (+551.61%)
Mutual labels:  image-generation
ru-dalle
Generate images from texts. In Russian
Stars: ✭ 1,606 (+5080.65%)
Mutual labels:  image-generation
sText2Image
Attribute-Guided Sketch-to-Image Generation
Stars: ✭ 67 (+116.13%)
Mutual labels:  image-generation
progressive growing of GANs
Pure tensorflow implementation of progressive growing of GANs
Stars: ✭ 31 (+0%)
Mutual labels:  progressive-gan
Anime2Sketch
A sketch extractor for anime/illustration.
Stars: ✭ 1,623 (+5135.48%)
Mutual labels:  image-generation

image_generator_2

概要

メルアイコン生成器 version2で用いたソースコードです。
詳しい解説はこちら

想定環境

python 3.7.1
pip install -r requirements.txtで環境を揃えることができます。

プログラム

  • PGGAN_train.pyは学習を実行し、学習の過程と学習結果を出力するプログラムです。
  • PGGAN_inference.pyPGGAN_train.pyが出力した学習結果をGeneratorに読み込み推論を実行、生成画像を出力するプログラムです。

使い方

  1. PGGAN_train.pyのあるディレクトリに./datasetディレクトリを作成します
  2. ./datasetディレクトリに、学習に使いたい画像を./dataset/*/*という形式で好きな数入れます(画像のファイル形式はpng)
  3. PGGAN_train.pyの置いてあるディレクトリでpython PGGAN_train.pyを実行して学習を開始します
    • 学習の過程が./output_img/pggan_train/以下に出力されます
    • 学習結果がgenerator_trained_model_cpu.pthとして出力されます
  4. PGGAN_inference.pyの置いてあるディレクトリでpython PGGAN_inference.pyを実行して推論します
    • 推論結果が./output_img/pggan_inference/以下に出力されます
    • 注意点として、PGGAN_inference.pyの置いてあるディレクトリにgenerator_trained_model_cpu.pthがなければエラーとなります

学習には環境によっては12時間以上要する場合があります。
入力された画像は256×256にリサイズされた上で学習に使われます。出力画像も256×256です。

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].