CompVis/brushstroke-parameterized-style-transfer
TensorFlow implementation of our CVPR 2021 Paper "Rethinking Style Transfer: From Pixels to Parameterized Brushstrokes".
This project helps artists and graphic designers transform photographs or digital images into artistic renditions that mimic various painting styles. You provide a 'content' image (e.g., a photo of a cityscape) and a 'style' image (e.g., Van Gogh's Starry Night), and it outputs a new image that looks like the content image painted in the style of the style image. This is ideal for creatives looking to generate unique visual assets.
167 stars. No commits in the last 6 months.
Use this if you want to apply the artistic style from one image onto the content of another, with control over the brushstroke-like appearance.
Not ideal if you need pixel-perfect image replication or simple photo filters rather than artistic style synthesis.
Stars
167
Forks
18
Language
Python
License
MIT
Category
Last pushed
Jul 16, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/CompVis/brushstroke-parameterized-style-transfer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
msracver/Deep-Image-Analogy
The source code of 'Visual Attribute Transfer through Deep Image Analogy'.
xunhuang1995/AdaIN-style
Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization
thiagoambiel/PortraitStylization
🖼️ PortraitStylization - A Pytorch style transfer algorithm optimized for human faces. Based on...
StacyYang/MSG-Net
Multi-style Generative Network for Real-time Transfer
ChenDarYen/ArtFusion
ArtFusion: Controllable Arbitrary Style Transfer using Dual Conditional Latent Diffusion Models