Generate images from texts. In Russian. In PaddlePaddle

Last update: Oct 18, 2022

Related tags

Overview

ruDALL-E PaddlePaddle

ruDALL-E in PaddlePaddle.

Install:

pip install rudalle_paddle==0.0.1rc1

Run with free v100 on AI Studio.

Original Pytorch version Readme:

ruDALL-E

Generate images from texts

🤗 HF Models:

ruDALL-E Malevich (XL)

Minimal Example:

generation by ruDALLE:

from rudalle_paddle.pipelines import generate_images, show, super_resolution, cherry_pick_by_clip
from rudalle_paddle import get_rudalle_model, get_tokenizer, get_vae, get_realesrgan, get_ruclip
from rudalle_paddle.utils import seed_everything

# prepare models
device = 'cuda'
dalle = get_rudalle_model('Malevich', pretrained=True, fp16=True, device=device)
realesrgan = get_realesrgan('x4', device=device)
tokenizer = get_tokenizer()
vae = get_vae().to(device)
ruclip, ruclip_processor = get_ruclip('ruclip-vit-base-patch32-v5')
ruclip = ruclip.to(device)

text = 'изображение радуги на фоне ночного города'

seed_everything(42)
pil_images = []
scores = []
for top_k, top_p, images_num in [
    (2048, 0.995, 3),
    (1536, 0.99, 3),
    (1024, 0.99, 3),
    (1024, 0.98, 3),
    (512, 0.97, 3),
    (384, 0.96, 3),
    (256, 0.95, 3),
    (128, 0.95, 3), 
]:
    _pil_images, _scores = generate_images(text, tokenizer, dalle, vae, top_k=top_k, images_num=images_num, top_p=top_p)
    pil_images += _pil_images
    scores += _scores

show(pil_images, 6)

auto cherry-pick by ruCLIP:

top_images, clip_scores = cherry_pick_by_clip(pil_images, text, ruclip, ruclip_processor, device=device, count=6)
show(top_images, 3)

super resolution:

sr_images = super_resolution(top_images, realesrgan)
show(sr_images, 3)

text, seed = 'красивая тян из аниме', 6955

Image Prompt

see jupyters/ruDALLE-image-prompts-A100.ipynb

text, seed = 'Храм Василия Блаженного', 42
skyes = [red_sky, sunny_sky, cloudy_sky, night_sky]

🚀 Contributors 🚀

@neverix thanks a lot for contributing for speed up of inference
@oriBetelgeuse thanks a lot for easy API of generation using image prompt

Large-scale open domain KNOwledge grounded conVERsation system based on PaddlePaddle

Knover Knover is a toolkit for knowledge grounded dialogue generation based on PaddlePaddle. Knover allows researchers and developers to carry out eff

607 Dec 31, 2022

🔥🔥High-Performance Face Recognition Library on PaddlePaddle & PyTorch🔥🔥

face.evoLVe: High-Performance Face Recognition Library based on PaddlePaddle & PyTorch Evolve to be more comprehensive, effective and efficient for fa

3.1k Jan 2, 2023

🔥🔥High-Performance Face Recognition Library on PaddlePaddle & PyTorch🔥🔥

face.evoLVe: High-Performance Face Recognition Library based on PaddlePaddle & PyTorch Evolve to be more comprehensive, effective and efficient for fa

3.1k Jan 4, 2023

Classical OCR DCNN reproduction based on PaddlePaddle framework.

Paddle-SVHN Classical OCR DCNN reproduction based on PaddlePaddle framework. This project reproduces Multi-digit Number Recognition from Street View I

1 Nov 12, 2021

A PaddlePaddle implementation of Time Interval Aware Self-Attentive Sequential Recommendation.

TiSASRec.paddle A PaddlePaddle implementation of Time Interval Aware Self-Attentive Sequential Recommendation. Introduction 论文：Time Interval Aware Sel

2 Nov 28, 2021

buildseg is a building extraction plugin of QGIS based on PaddlePaddle.

buildseg buildseg is a building extraction plugin of QGIS based on PaddlePaddle. TODO Extract building on 512x512 remote sensing images. Extract build

11 Sep 26, 2022

YOLOv5🚀 reproduction by Guo Quanhao using PaddlePaddle

YOLOv5-Paddle YOLOv5 🚀 reproduction by Guo Quanhao using PaddlePaddle 支持AutoBatch 支持AutoAnchor 支持GPU Memory 快速开始使用AIStudio高性能环境快速构建YOLOv5训练(PaddlePa

20 Nov 14, 2022

A PaddlePaddle implementation of STGCN with a few modifications in the model architecture in order to forecast traffic jam.

About This repository contains the code of a PaddlePaddle implementation of STGCN based on the paper Spatio-Temporal Graph Convolutional Networks: A D

1 Jan 11, 2022

buildseg is a building extraction plugin of QGIS based on PaddlePaddle.

buildseg buildseg is a Building Extraction plugin for QGIS based on PaddlePaddle. How to use Download and install QGIS and clone the repo : git clone

39 Dec 9, 2022

Comments

Other playable models-Text2Image
playable models

dalle-mini & craiyon https://github.com/borisdayma/dalle-mini

CogView2 https://github.com/THUDM/CogView2

待添加

No pretrained models

imagen https://github.com/lucidrains/imagen-pytorch

文心 ERNIE-ViLG https://wenxin.baidu.com/wenxin/modelbasedetail/ernie_vilg/

待添加
opened by Wulx2050 3

Generate images from texts. In Russian. In PaddlePaddle

Related tags

Overview

ruDALL-E PaddlePaddle

ruDALL-E

Generate images from texts

🤗 HF Models:

Minimal Example:

generation by ruDALLE:

auto cherry-pick by ruCLIP:

super resolution:

Image Prompt

🚀 Contributors 🚀

You might also like...

Large-scale open domain KNOwledge grounded conVERsation system based on PaddlePaddle

🔥🔥High-Performance Face Recognition Library on PaddlePaddle & PyTorch🔥🔥

🔥🔥High-Performance Face Recognition Library on PaddlePaddle & PyTorch🔥🔥

Classical OCR DCNN reproduction based on PaddlePaddle framework.

A PaddlePaddle implementation of Time Interval Aware Self-Attentive Sequential Recommendation.

buildseg is a building extraction plugin of QGIS based on PaddlePaddle.

YOLOv5🚀 reproduction by Guo Quanhao using PaddlePaddle

A PaddlePaddle implementation of STGCN with a few modifications in the model architecture in order to forecast traffic jam.

buildseg is a building extraction plugin of QGIS based on PaddlePaddle.

Comments

Other playable models-Text2Image

Releases(v0.0.1rc1)

v0.0.1rc1(Nov 22, 2021)

Owner

AgentMaker

Pseudo-mask Matters in Weakly-supervised Semantic Segmentation

A Differentiable Recipe for Learning Visual Non-Prehensile Planar Manipulation

Minimal implementation of Denoised Smoothing: A Provable Defense for Pretrained Classifiers in TensorFlow.

Adversarial Learning for Modeling Human Motion

Official PyTorch Implementation of SSMix (Findings of ACL 2021)

Official PyTorch implementation of "Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image", ICCV 2019

Retrieval.pytorch - The code we used in [2020 DIGIX]

Implementation of Neonatal Seizure Detection using EEG signals for deploying on edge devices including Raspberry Pi.

Multi Agent Path Finding Algorithms

Let Python optimize the best stop loss and take profits for your TradingView strategy.

This project aims to explore the deployment of Swin-Transformer based on TensorRT, including the test results of FP16 and INT8.

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

A Python reference implementation of the CF data model

ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentation

Show-attend-and-tell - TensorFlow Implementation of "Show, Attend and Tell"

VLG-Net: Video-Language Graph Matching Networks for Video Grounding

Pytorch implementation for "Open Compound Domain Adaptation" (CVPR 2020 ORAL)

Package for extracting emotions from social media text. Tailored for financial data.

Process JSON files for neural recording sessions using Medtronic's BrainSense Percept PC neurostimulator

Notification Triggers for Python