Library/FastPhotoStyleForked

NVIDIA/FastPhotoStyle

FastPhotoStyle

Style transfer, deep learning, feature transform

View on GitHub↗Upstream NVIDIA/FastPhotoStyle↗

Builder

NVIDIA

NVIDIA • big-tech

Stars

11,181

Using upstream star count

Forks

1,193

Using upstream fork count

Open Issues

Activity Score

0/100

0 commits in 30d

Created

Feb 14, 2018

Project creation date

README Summary

FastPhotoStyle is NVIDIA's implementation of a fast photorealistic style transfer algorithm that can transfer the style of a reference photo to a content photo while preserving photorealism. The method uses a novel feature transform technique that combines deep learning with traditional image processing to achieve high-quality results in seconds rather than minutes.

AI Dev Skills

Unmapped

Neural Style TransferConvolutional Neural NetworksFeature Space TransformationComputer VisionDeep Learning Model ImplementationImage ProcessingPyTorch Implementation

Taxonomy

AI Trends

Generative AI Creative AI

Deployment Context

Self-hosted

Industries

Creative Technology Digital Media Photography Entertainment

Modalities

Image

Skill Areas

Neural Style Transfer Convolutional Neural Networks Feature Space Transformation Computer Vision Deep Learning Model Implementation Image Processing PyTorch Implementation

Use Cases

Photorealistic Style Transfer Artistic Image Enhancement Creative Content Generation Image Style Transformation

Recent Activity

Updated 2 years ago

7 Days

30 Days

90 Days

Quality

research

Quality: medium
Maturity: research

PM Skills

Data & EvaluationCost & Efficiency

Languages

Python100.0%

Timeline

Project created: Feb 14, 2018
Forked: Mar 14, 2026
Your last push: 2 years ago
Upstream last push: 2 years ago
Tracked since: Jun 7, 2023

Similar Repos

pgvector cosine similarity · $0

Loading…