Generating Images From Caption And Vice Versa Via Clipguided Generative Latent Space Search

# Generating images from caption and vice versa via CLIP-Guided Generative Latent Space Search

**arXiv ID:** 2102.01645
**Authors:** Federico A. Galatolo, Mario G. C. A. Cimino, Gigliola Vaglini
**Published:** 2021-02-02T18:00:13Z
**Abstract:**
In this research work we present CLIP-GLaSS, a novel zero-shot framework to generate an image (or a caption) corresponding to a given caption (or image). CLIP-GLaSS is based on the CLIP neural network, which, given an image and a descriptive caption, provides similar embeddings. Differently, CLIP-GLaSS takes a caption (or an image) as an input, and generates the image (or the caption) whose CLIP embedding is the most similar to the input one. This optimal image (or caption) is produced via a generative network, after an exploration by a genetic algorithm. Promising results are shown, based on the experimentation of the image Generators BigGAN and StyleGAN2, and of the text Generator GPT2

## Skill Description

This skill is generated from the arXiv paper: Generating images from caption and vice versa via CLIP-Guided Generative Latent Space Search (2102.01645).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:2102.01645](http://arxiv.org/abs/2102.01645v4)