| --- |
| pipeline_tag: unconditional-image-generation |
| --- |
| |
| # Model Card for FFHQ 64x64 R3GAN Model |
|
|
| This model card provides details about the R3GAN model trained on the FFHQ-64 dataset found in the NeurIPS 2024 paper: https://arxiv.org/abs/2501.05441 |
|
|
| ## Model Details |
|
|
| The model achieves 1.95 Frechet Inception Distance-50k on class conditional FFHQ-64 generation. |
|
|
| ### Model Description |
|
|
| This model is a generative adversarial network (GAN) based on the R3GAN architecture, specifically trained to synthesize high-quality and realistic images from the ImageNet dataset. |
|
|
| - **Developed by:** Brown University and Cornell University |
| - **Funded by:** National Science Foundation and National Institute of Health (See paper for funding details) |
| - **Shared by:** [Optional: Specify sharer if different from developer] |
| - **Model type:** Generative Adversarial Network |
| - **Language(s) (NLP):** N/A |
| - **License:** [Specify License, e.g., MIT, Apache 2.0, or a custom license] |
| - **Finetuned from model:** N/A |
|
|
| ### Model Sources |
|
|
| - **Repository:** https://github.com/brownvc/R3GAN/ |
| - **Paper:** https://arxiv.org/pdf/2501.05441 |
| - **Demo:** [Optional: Provide a link to a demo or example usage] |
|
|
| ## Uses |
|
|
| ### Direct Use |
|
|
| This model can be used to generate high-resolution images similar to those in the FFHQ dataset. Its primary application includes research in generative models and image synthesis. |
|
|
| ### Downstream Use |
|
|
| The model can be fine-tuned for specific subsets of the FFHQ dataset or other similar datasets for domain-specific image generation tasks. |
|
|
| ### Out-of-Scope Use |
|
|
| The model should not be used for generating deceptive or misleading content, malicious purposes, or tasks where realistic image synthesis could cause harm. |
|
|
| ## Bias, Risks, and Limitations |
|
|
| The model inherits biases present in the FFHQ dataset, including potential overrepresentation or underrepresentation of certain classes. Users should critically evaluate and mitigate biases before deploying the model. |
|
|
| ### Recommendations |
|
|
| - Avoid using the model for sensitive applications without thorough bias evaluation. |
| - Ensure appropriate credit is given when publishing or sharing generated images. |
|
|
| ## How to Get Started with the Model |
|
|
| Below is an example of how to use the model for image generation: |
| - Will add later |
