Downloads · 30 days
0
watercolor-brush
Druudik1/watercolor-brush
watercolor-brush is a machine learning model from Druudik1. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
This repository contains trained ColorMaskNeuralRenderer that learned to mimic WatercolorBrush (these are components of my Stylized Neural Painting paper reimplementation).
Access
Public
Updated Feb 23, 2026
Repo size
44.2 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt44.2 MB · 100%
At a glance
- License
- mit
- Access
- Public
- Created
- Feb 23, 2026
- Updated
- Feb 23, 2026
- SHA
- cb5edda5
Model card
From the Hugging Face model README
This repository contains trained ColorMaskNeuralRenderer that learned to mimic WatercolorBrush (these
are components of my Stylized Neural Painting paper reimplementation).
Use the following code snippet to load it and create the corresponding WatercolorBrush:
from huggingface_hub import hf_hub_download
from painting.brushes import WatercolorBrush, ColorMaskNeuralRenderer
# Specify your device and output canvas size.
device = "cuda"
out_canvas_size = 512
brush = WatercolorBrush(canvas_size=out_canvas_size, device=device)
differentiable_brush = ColorMaskNeuralRenderer(
brush_params_count=brush.brush_params_count,
color_params_indices=[7, 8, 9],
canvas_size=128,
device=device,
)
weights = hf_hub_download(repo_id="Druudik1/watercolor-brush", filename="neural_renderer.pt")
differentiable_brush.load_state_dict(
torch.load(weights, map_location=device, weights_only=True)
)
- License
- mit
- Created
- Feb 23, 2026
- Updated
- Feb 23, 2026