Add YAML metadata.
Browse files
README.md
CHANGED
|
@@ -1,3 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
# FDFO: Finite Difference Flow Optimization
|
| 2 |
|
| 3 |
This repository contains the official pretrained checkpoints for FDFO, a method for fine-tuning flow-based diffusion models using finite difference gradient estimation. We fine-tune [Stable Diffusion 3.5 Medium](https://huggingface.co/stabilityai/stable-diffusion-3.5-medium) using reward signals from VLM-based scoring and/or PickScore. Please see the [GitHub repository](https://github.com/NVlabs/finite-difference-flow-optimization) for further details.
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: other
|
| 3 |
+
license_name: nvidia-source-code-license-v1
|
| 4 |
+
license_link: https://huggingface.co/nvidia/finite-difference-flow-optimization/resolve/main/LICENSE.txt
|
| 5 |
+
pipeline_tag: text-to-image
|
| 6 |
+
library_name: diffusers
|
| 7 |
+
base_model: stabilityai/stable-diffusion-3.5-medium
|
| 8 |
+
inference: false
|
| 9 |
+
tags:
|
| 10 |
+
- text-to-image
|
| 11 |
+
- post-training
|
| 12 |
+
- reinforcement-learning
|
| 13 |
+
- stable-diffusion
|
| 14 |
+
- diffusers
|
| 15 |
+
language:
|
| 16 |
+
- en
|
| 17 |
+
---
|
| 18 |
+
|
| 19 |
# FDFO: Finite Difference Flow Optimization
|
| 20 |
|
| 21 |
This repository contains the official pretrained checkpoints for FDFO, a method for fine-tuning flow-based diffusion models using finite difference gradient estimation. We fine-tune [Stable Diffusion 3.5 Medium](https://huggingface.co/stabilityai/stable-diffusion-3.5-medium) using reward signals from VLM-based scoring and/or PickScore. Please see the [GitHub repository](https://github.com/NVlabs/finite-difference-flow-optimization) for further details.
|