text2image
Image generator
A model that generates image patches from natural language descriptions by iteratively drawing and attending to relevant words.
Generating Images from Captions with Attention
594 stars
27 watching
121 forks
Language: Python
last commit: almost 8 years ago
Linked from 1 awesome list
zhjohnchan/awesome-image-captioningRelated projects:
| Repository | Description | Stars |
|---|---|---|
 google/sg2im | An end-to-end neural network model that generates images from scene graphs by processing input graph information through multiple layers of networks | 1,302 |
 ibm/max-image-caption-generator | An image caption generation system utilizing machine learning models and deep neural networks. | 84 |
 google-research/parti | An autoregressive text-to-image generation model that generates photorealistic images from text prompts and leverages advances in large language models. | 1,554 |
| ibm/max-fast-neural-style-transfer | A service for generating new images by mixing the content of an input image with the style of another image. | 51 |
 pixray/pixray | An image generation system built around CLIP and GAN techniques. | 1,030 |
 kohjingyu/gill | A software framework for generating images and text using large language models | 440 |
 gligen/gligen | A system that enables new capabilities in frozen text-to-image generation models to ground on various prompts, including boxes, keypoints, and images. | 2,036 |
 carpedm20/began-pytorch | An implementation of a deep learning model for generating images from text descriptions | 262 |
 eps696/aphantasia | A text-to-image tool using CLIP and FFT/DWT parameters to generate detailed images from user-provided text prompts. | 778 |
| google-research/xmcgan_image_generation | This implementation enables text-to-image generation by leveraging cross-modal contrastive learning. | 98 |
 matryer/gopherize.me | An application that generates a custom image by overlaying images from different categories in a specific order. | 713 |
 sggts04/dankcli | A CLI tool that generates memes by adding whitespace and text to the top of an image | 55 |
 thereforegames/txt2mask | Automatically generates masks for image inpainting using natural language input | 520 |
 sudo-ai-3d/zero123plus | A 3D image generation model that takes a single image as input and produces a consistent set of multi-view images from different perspectives. | 1,794 |
 thudm/cogview | A framework for generating images from text using transformers. | 1,735 |