IDSIA/fpainter
Official repository for the paper "Images as Weight Matrices: Sequential Image Generation Through Synaptic Learning Rules" (ICLR 2023)
This project offers a way to generate realistic images in a step-by-step process. It takes existing image datasets as input and produces new, unique images that match the style and content of the training data. Creative professionals, such as concept artists, game developers, or marketers, who need to quickly create a variety of images for prototypes or campaigns, would find this useful.
No commits in the last 6 months.
Use this if you need to generate a large number of diverse, high-quality images from scratch, based on examples you provide.
Not ideal if you need to edit existing images or perform specific object-based manipulations within an image.
Stars
12
Forks
3
Language
Python
License
—
Category
Last pushed
Jun 11, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/IDSIA/fpainter"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
galilai-group/stable-pretraining
Reliable, minimal and scalable library for pretraining foundation and world models
CognitiveAISystems/MAPF-GPT
[AAAI-2025] This repository contains MAPF-GPT, a deep learning-based model for solving MAPF...
UKPLab/gpl
Powerful unsupervised domain adaptation method for dense retrieval. Requires only unlabeled...
larslorch/avici
Amortized Inference for Causal Structure Learning, NeurIPS 2022
svdrecbd/mhc-mlx
MLX + Metal implementation of mHC: Manifold-Constrained Hyper-Connections by DeepSeek-AI.