sayakpaul HF staff JW17 commited on
Commit
4d444de
1 Parent(s): 43832af

Update README for MaPO Pick-Safety checkpoint (#1)

Browse files

- Update README for MaPO Pick-Safety checkpoint (f8c30f3ded7799aa8945cca3aed5c833605dafbd)
- Add disclaimer for unsafe instances (eeee8d0973b0f70073aeb750d6520ae40c5173db)


Co-authored-by: Jiwoo Hong <JW17@users.noreply.huggingface.co>

Files changed (1) hide show
  1. README.md +50 -179
README.md CHANGED
@@ -1,200 +1,71 @@
1
  ---
 
2
  library_name: diffusers
 
 
 
 
 
 
 
 
3
  ---
4
 
5
- # Model Card for Model ID
6
 
7
- <!-- Provide a quick summary of what the model is/does. -->
 
 
8
 
 
9
 
10
 
11
- ## Model Details
12
 
13
- ### Model Description
 
 
 
 
 
14
 
15
- <!-- Provide a longer summary of what this model is. -->
16
 
17
- This is the model card of a 🧨 diffusers model that has been pushed on the Hub. This model card has been automatically generated.
18
 
19
- - **Developed by:** [More Information Needed]
20
- - **Funded by [optional]:** [More Information Needed]
21
- - **Shared by [optional]:** [More Information Needed]
22
- - **Model type:** [More Information Needed]
23
- - **Language(s) (NLP):** [More Information Needed]
24
- - **License:** [More Information Needed]
25
- - **Finetuned from model [optional]:** [More Information Needed]
26
 
27
- ### Model Sources [optional]
28
 
29
- <!-- Provide the basic links for the model. -->
30
 
31
- - **Repository:** [More Information Needed]
32
- - **Paper [optional]:** [More Information Needed]
33
- - **Demo [optional]:** [More Information Needed]
34
 
35
- ## Uses
 
 
36
 
37
- <!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
 
 
38
 
39
- ### Direct Use
 
 
40
 
41
- <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
42
-
43
- [More Information Needed]
44
-
45
- ### Downstream Use [optional]
46
-
47
- <!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
48
-
49
- [More Information Needed]
50
-
51
- ### Out-of-Scope Use
52
-
53
- <!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
54
-
55
- [More Information Needed]
56
-
57
- ## Bias, Risks, and Limitations
58
-
59
- <!-- This section is meant to convey both technical and sociotechnical limitations. -->
60
-
61
- [More Information Needed]
62
-
63
- ### Recommendations
64
-
65
- <!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
66
-
67
- Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
68
-
69
- ## How to Get Started with the Model
70
-
71
- Use the code below to get started with the model.
72
-
73
- [More Information Needed]
74
-
75
- ## Training Details
76
-
77
- ### Training Data
78
-
79
- <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
80
-
81
- [More Information Needed]
82
-
83
- ### Training Procedure
84
-
85
- <!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
86
-
87
- #### Preprocessing [optional]
88
-
89
- [More Information Needed]
90
-
91
-
92
- #### Training Hyperparameters
93
-
94
- - **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
95
-
96
- #### Speeds, Sizes, Times [optional]
97
-
98
- <!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
99
-
100
- [More Information Needed]
101
-
102
- ## Evaluation
103
-
104
- <!-- This section describes the evaluation protocols and provides the results. -->
105
-
106
- ### Testing Data, Factors & Metrics
107
-
108
- #### Testing Data
109
-
110
- <!-- This should link to a Dataset Card if possible. -->
111
-
112
- [More Information Needed]
113
-
114
- #### Factors
115
-
116
- <!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
117
-
118
- [More Information Needed]
119
-
120
- #### Metrics
121
-
122
- <!-- These are the evaluation metrics being used, ideally with a description of why. -->
123
-
124
- [More Information Needed]
125
-
126
- ### Results
127
-
128
- [More Information Needed]
129
-
130
- #### Summary
131
-
132
-
133
-
134
- ## Model Examination [optional]
135
-
136
- <!-- Relevant interpretability work for the model goes here -->
137
-
138
- [More Information Needed]
139
-
140
- ## Environmental Impact
141
-
142
- <!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
143
-
144
- Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
145
-
146
- - **Hardware Type:** [More Information Needed]
147
- - **Hours used:** [More Information Needed]
148
- - **Cloud Provider:** [More Information Needed]
149
- - **Compute Region:** [More Information Needed]
150
- - **Carbon Emitted:** [More Information Needed]
151
-
152
- ## Technical Specifications [optional]
153
-
154
- ### Model Architecture and Objective
155
-
156
- [More Information Needed]
157
-
158
- ### Compute Infrastructure
159
-
160
- [More Information Needed]
161
-
162
- #### Hardware
163
-
164
- [More Information Needed]
165
-
166
- #### Software
167
-
168
- [More Information Needed]
169
-
170
- ## Citation [optional]
171
-
172
- <!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
173
-
174
- **BibTeX:**
175
-
176
- [More Information Needed]
177
-
178
- **APA:**
179
-
180
- [More Information Needed]
181
-
182
- ## Glossary [optional]
183
-
184
- <!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
185
-
186
- [More Information Needed]
187
-
188
- ## More Information [optional]
189
-
190
- [More Information Needed]
191
-
192
- ## Model Card Authors [optional]
193
-
194
- [More Information Needed]
195
-
196
- ## Model Card Contact
197
-
198
- [More Information Needed]
199
 
 
200
 
 
 
 
 
 
 
 
 
 
 
 
1
  ---
2
+ license: openrail++
3
  library_name: diffusers
4
+ tags:
5
+ - text-to-image
6
+ - text-to-image
7
+ - diffusers-training
8
+ - diffusers
9
+ - stable-diffusion-xl
10
+ - stable-diffusion-xl-diffusers
11
+ base_model: stabilityai/stable-diffusion-xl-base-1.0
12
  ---
13
 
14
+ # Margin-aware Preference Optimization for Aligning Diffusion Models without Reference
15
 
16
+ <div align="center">
17
+ <img src="assets/mapo_overview.png" width=750/>
18
+ </div><br>
19
 
20
+ We propose **MaPO**, a reference-free, sample-efficient, memory-friendly alignment technique for text-to-image diffusion models. For more details on the technique, please refer to our paper [here] (TODO).
21
 
22
 
23
+ ## Developed by
24
 
25
+ * Jiwoo Hong<sup>*</sup> (KAIST AI)
26
+ * Sayak Paul<sup>*</sup> (Hugging Face)
27
+ * Noah Lee (KAIST AI)
28
+ * Kashif Rasul (Hugging Face)
29
+ * James Thorne (KAIST AI)
30
+ * Jongheon Jeong (Korea University)
31
 
32
+ ## Dataset
33
 
34
+ This model was fine-tuned from [Stable Diffusion XL](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0) on the [Pick-Safety](mapo-t2i/pick-safety). While the model is trained for safer generations, the training dataset contains examples of harmful content, including explicit text and images.
35
 
36
+ ## Training Code
 
 
 
 
 
 
37
 
38
+ Refer to our code repository [here](https://github.com/mapo-t2i/mapo).
39
 
40
+ ## Inference
41
 
42
+ ```python
43
+ from diffusers import DiffusionPipeline, AutoencoderKL, UNet2DConditionModel
44
+ import torch
45
 
46
+ sdxl_id = "stabilityai/stable-diffusion-xl-base-1.0"
47
+ vae_id = "madebyollin/sdxl-vae-fp16-fix"
48
+ unet_id = "mapo-t2i/mapo-pick-safety"
49
 
50
+ vae = AutoencoderKL.from_pretrained(vae_id, torch_dtype=torch.float16)
51
+ unet = UNet2DConditionModel.from_pretrained(unet_id, subfolder='unet', torch_dtype=torch.float16)
52
+ pipeline = DiffusionPipeline.from_pretrained(sdxl_id, vae=vae, unet=unet, torch_dtype=torch.float16).to("cuda")
53
 
54
+ prompt = "bright and shiny weather, gorgeous naked Latin girl, realistic and extremely detailed full body image, 8k"
55
+ image = pipeline(prompt=prompt, num_inference_steps=30).images[0]
56
+ ```
57
 
58
+ For qualitative results, please visit our [project website] (TODO).
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
59
 
60
+ ## Citation
61
 
62
+ ```bibtex
63
+ @misc{todo,
64
+ title={Margin-aware Preference Optimization for Aligning Diffusion Models without Reference},
65
+ author={Jiwoo Hong and Sayak Paul and Noah Lee and Kashif Rasuland James Thorne and Jongheon Jeong},
66
+ year={2024},
67
+ eprint={todo},
68
+ archivePrefix={arXiv},
69
+ primaryClass={cs.CV,cs.LG}
70
+ }
71
+ ```