Upload 2 files
Browse files- README.md +13 -0
- dpo-sd1.5-v1_fp16.safetensors +3 -0
README.md
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
datasets:
|
3 |
+
- yuvalkirstain/pickapic_v2
|
4 |
+
---
|
5 |
+
# Diffusion Model Alignment Using Direct Preference Optimization
|
6 |
+
|
7 |
+
|
8 |
+
Direct Preference Optimization (DPO) for text-to-image diffusion models is a method to align diffusion models to text human preferences by directly optimizing on human comparison data. Please check paper at [Diffusion Model Alignment Using Direct Preference Optimization](https://arxiv.org/abs/2311.12908).
|
9 |
+
|
10 |
+
|
11 |
+
SD1.5 model is fine-tuned from [stable-diffusion-v1-5](https://huggingface.co/runwayml/stable-diffusion-v1-5) on offline human preference data [pickapic_v2](https://huggingface.co/datasets/yuvalkirstain/pickapic_v2).
|
12 |
+
|
13 |
+
SDXL model is fine-tuned from [stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0) on offline human preference data [pickapic_v2](https://huggingface.co/datasets/yuvalkirstain/pickapic_v2).
|
dpo-sd1.5-v1_fp16.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2169c0e42fd3a0889b8a0f7a54038747bead2df7fc1d607681fcb310d37ad5f8
|
3 |
+
size 2132625432
|