Improve model card: Add pipeline tag and prominent paper/code links

#1
by nielsr HF Staff - opened
Files changed (1) hide show
  1. README.md +6 -6
README.md CHANGED
@@ -1,27 +1,28 @@
1
  ---
2
- license: apache-2.0
3
  base_model: stabilityai/stable-diffusion-xl-base-1.0
 
 
 
4
  tags:
5
  - stable-diffusion-xl
6
  - stable-diffusion
7
  - diffusers
8
- - text-to-image
9
  - inversion
10
  - dpo
11
  - fine-tuned
12
- library_name: diffusers
13
  ---
14
 
15
  # Inversion-DPO
16
 
17
  Official Inversion-DPO weights fine-tuned from Stable Diffusion XL. Only the trained UNet module is provided.
18
 
 
 
 
19
  ## Model Description
20
 
21
  This repository contains the fine-tuned UNet weights from the Inversion-DPO method, built upon Stable Diffusion XL. The model has been trained using Direct Preference Optimization (DPO) techniques combined with inversion methods to improve generation quality and alignment.
22
 
23
- **Code Repository:** https://github.com/MIGHTYEZ/Inversion-DPO
24
-
25
  ## Quick Start
26
 
27
  ```python
@@ -47,7 +48,6 @@ image = pipe(prompt).images[0]
47
  image.save("output.png")
48
  ```
49
 
50
-
51
  ## Citation
52
 
53
  If you use this model in your research, please cite our work:
 
1
  ---
 
2
  base_model: stabilityai/stable-diffusion-xl-base-1.0
3
+ library_name: diffusers
4
+ license: apache-2.0
5
+ pipeline_tag: text-to-image
6
  tags:
7
  - stable-diffusion-xl
8
  - stable-diffusion
9
  - diffusers
 
10
  - inversion
11
  - dpo
12
  - fine-tuned
 
13
  ---
14
 
15
  # Inversion-DPO
16
 
17
  Official Inversion-DPO weights fine-tuned from Stable Diffusion XL. Only the trained UNet module is provided.
18
 
19
+ **Paper**: [Inversion-DPO: Precise and Efficient Post-Training for Diffusion Models](https://huggingface.co/papers/2507.11554)
20
+ **Code Repository**: https://github.com/MIGHTYEZ/Inversion-DPO
21
+
22
  ## Model Description
23
 
24
  This repository contains the fine-tuned UNet weights from the Inversion-DPO method, built upon Stable Diffusion XL. The model has been trained using Direct Preference Optimization (DPO) techniques combined with inversion methods to improve generation quality and alignment.
25
 
 
 
26
  ## Quick Start
27
 
28
  ```python
 
48
  image.save("output.png")
49
  ```
50
 
 
51
  ## Citation
52
 
53
  If you use this model in your research, please cite our work: