Add repository model card
Browse files
README.md
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
pipeline_tag: text-to-image
|
| 4 |
+
tags:
|
| 5 |
+
- probex
|
| 6 |
+
- model-j
|
| 7 |
+
- weight-space-learning
|
| 8 |
+
- lora
|
| 9 |
+
- stable-diffusion
|
| 10 |
+
---
|
| 11 |
+
|
| 12 |
+
# Model-J: SD_200 (Bundled LoRA Models)
|
| 13 |
+
|
| 14 |
+
This repository contains **SD_200** LoRA models from the **Model-J** dataset, introduced in:
|
| 15 |
+
|
| 16 |
+
**Learning on Model Weights using Tree Experts** (CVPR 2025) by Eliahu Horwitz*, Bar Cavia*, Jonathan Kahana*, Yedid Hoshen
|
| 17 |
+
|
| 18 |
+
<p align="center">
|
| 19 |
+
🌐 <a href="https://horwitz.ai/probex" target="_blank">Project</a> | 📃 <a href="https://arxiv.org/abs/2410.13569" target="_blank">Paper</a> | 💻 <a href="https://github.com/eliahuhorwitz/ProbeX" target="_blank">GitHub</a> | 🤗 <a href="https://huggingface.co/ProbeX" target="_blank">Dataset</a>
|
| 20 |
+
</p>
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
## Overview
|
| 25 |
+
|
| 26 |
+
This repository bundles all SD_200 LoRA models into a single repo. Each model is a LoRA adapter fine-tuned on images of a specific ImageNet class using Stable Diffusion. Each model directory also contains the training images used for fine-tuning.
|
| 27 |
+
|
| 28 |
+
## Repository Structure
|
| 29 |
+
|
| 30 |
+
```
|
| 31 |
+
{split}/model_idx_{XXXX}/
|
| 32 |
+
pytorch_lora_weights.safetensors
|
| 33 |
+
training_images/
|
| 34 |
+
README.md
|
| 35 |
+
```
|
| 36 |
+
|
| 37 |
+
Splits: `train`, `val`, `test`, `val_holdout`, `test_holdout`
|
| 38 |
+
|
| 39 |
+
For detailed hyperparameters of each model, see the README.md in each model's directory or the [Model-J dataset](https://huggingface.co/datasets/ProbeX/Model-J).
|