Update README.md

README.md

@@ -1,198 +1,57 @@
 ---
-library_name: diffusers
+library_name: ImageReFL
 ---
 
-# Model Card for Model ID
-
-<!-- Provide a quick summary of what the model is/does. -->
+# ImageReFL
 
+Recent advances in diffusion models have led to impressive image generation capabilities, but aligning these models with human preferences remains challenging. Reward-based fine-tuning using models trained on human feedback improves alignment but often harms diversity, producing less varied outputs. In this work, we address this trade-off with two contributions. First, we introduce \textit{combined generation}, a novel sampling strategy that applies a reward-tuned diffusion model only in the later stages of the generation process, while preserving the base model for earlier steps. This approach mitigates early-stage overfitting and helps retain global structure and diversity. Second, we propose \textit{ImageReFL}, a fine-tuning method that improves image diversity with minimal loss in quality by training on real images and incorporating multiple regularizers, including diffusion and ReFL losses. Our approach outperforms conventional reward tuning methods on standard quality and diversity metrics. A user study further confirms that our method better balances human preference alignment and visual diversity.
 
 
 ## Model Details
 
-### Model Description
-
-<!-- Provide a longer summary of what this model is. -->
-
-This is the model card of a 🧨 diffusers model that has been pushed on the Hub. This model card has been automatically generated.
+This implementation is based on [Stable Diffusion 1.5](https://huggingface.co/stable-diffusion-v1-5/stable-diffusion-v1-5) and was trained using the reward model [HPSv2.1](https://github.com/tgxs002/HPSv2) with the ImageReFL algorithm.
+Inference uses the combined generation approach described in the ImageReFL paper.
 
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
-- **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
-- **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
 
 ### Model Sources [optional]
 
-<!-- Provide the basic links for the model. -->
-
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
-
-## Uses
-
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
-### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[More Information Needed]
-
-### Downstream Use [optional]
-
-<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
-
-[More Information Needed]
-
-### Out-of-Scope Use
-
-<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
-
-[More Information Needed]
-
-## Bias, Risks, and Limitations
-
-<!-- This section is meant to convey both technical and sociotechnical limitations. -->
-
-[More Information Needed]
-
-### Recommendations
-
-<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
-
-Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+- **Repository:** [https://github.com/ControlGenAI/ImageReFL]
+- **Paper [optional]:** [https://arxiv.org/abs/2304.05977]
 
 ## How to Get Started with the Model
 
-Use the code below to get started with the model.
-
-[More Information Needed]
-
-## Training Details
-
-### Training Data
-
-<!-- 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. -->
-
-[More Information Needed]
-
-### Training Procedure
-
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
-
-#### Preprocessing [optional]
-
-[More Information Needed]
-
-
-#### Training Hyperparameters
-
-- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
-
-#### Speeds, Sizes, Times [optional]
-
-<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
-
-[More Information Needed]
-
-## Evaluation
-
-<!-- This section describes the evaluation protocols and provides the results. -->
-
-### Testing Data, Factors & Metrics
-
-#### Testing Data
-
-<!-- This should link to a Dataset Card if possible. -->
-
-[More Information Needed]
-
-#### Factors
-
-<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
-
-[More Information Needed]
-
-#### Metrics
-
-<!-- These are the evaluation metrics being used, ideally with a description of why. -->
-
-[More Information Needed]
-
-### Results
-
-[More Information Needed]
-
-#### Summary
-
-
-
-## Model Examination [optional]
-
-<!-- Relevant interpretability work for the model goes here -->
-
-[More Information Needed]
-
-## Environmental Impact
-
-<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
-
-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).
-
-- **Hardware Type:** [More Information Needed]
-- **Hours used:** [More Information Needed]
-- **Cloud Provider:** [More Information Needed]
-- **Compute Region:** [More Information Needed]
-- **Carbon Emitted:** [More Information Needed]
-
-## Technical Specifications [optional]
-
-### Model Architecture and Objective
-
-[More Information Needed]
-
-### Compute Infrastructure
-
-[More Information Needed]
-
-#### Hardware
-
-[More Information Needed]
-
-#### Software
-
-[More Information Needed]
-
-## Citation [optional]
-
-<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
-
-**BibTeX:**
-
-[More Information Needed]
-
-**APA:**
-
-[More Information Needed]
-
-## Glossary [optional]
-
-<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
-
-[More Information Needed]
-
-## More Information [optional]
-
-[More Information Needed]
-
-## Model Card Authors [optional]
-
-[More Information Needed]
-
-## Model Card Contact
-
-[More Information Needed]
+Model support classical Stable Diffusion inference, but with few addititonal paramters:
+
+* `original_unet_steps` regulates the number of diffusion steps performed with the original U-Net model. The recommended number is 30 for models based on SD 1.5, and 35 for models based on SDXL.
+
+Example of inference:
+
+```
+from diffusers import DiffusionPipeline
+
+pipe = DiffusionPipeline.from_pretrained(
+    "ControlGenAI/ImageReFL_PickScore_SD",
+    trust_remote_code=True
+).to(device)
+
+prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
+image = pipe(
+prompt,
+original_unet_steps=30
+).images[0]
+```
+
+## Citation
+
+If you use this code or our findings for your research, please cite our paper:
+```
+@misc{sorokin2025imagereflbalancingqualitydiversity,
+      title={ImageReFL: Balancing Quality and Diversity in Human-Aligned Diffusion Models},
+      author={Dmitrii Sorokin and Maksim Nakhodnov and Andrey Kuznetsov and Aibek Alanov},
+      year={2025},
+      eprint={2505.22569},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV},
+      url={https://arxiv.org/abs/2505.22569},
+}
+```