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

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

2 Feb 2021arXiv:2102.01645archive 2025-07-28

Federico A. Galatolo, Mario G. C. A. Cimino, Gigliola Vaglini

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

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

galatolofederico/clip-glass officialmentioned in papermentioned on GitHubpytorch report
armaank/archlectures mentioned on GitHubpytorch report
yk/clip_music_video mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DescriptiveImage Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAdamBatch NormalizationBigGANConditional Batch NormalizationConvolutionDense ConnectionsEarly StoppingFeedforward NetworkGAN Hinge LossLinear LayerNon-Local BlockNon-Local OperationOff-Diagonal Orthogonal RegularizationPath Length RegularizationProjection DiscriminatorR1 RegularizationReLUResidual BlockResidual ConnectionSAGANSoftmaxSpectral NormalizationStyleGAN2TTURTruncation TrickWeight Demodulation

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections