H2O Image Styling Art Studio

Create images/art and have fun.

Web app built using H2O SDK, Realtime Web Apps and Dashboards for Python and R. Currently, the Art Studio supports the following options for image generation,

1. Image restoration: using GFP-GAN for face restoration
2. Image Styling: Using StyleGAN2 with Adaptive Discriminator Augmentation
3. Image Editing: For facial images using landmark detection for image alginment and editing StyleGAN2 latent space
4. Image Prompt: Create art using Text-to-Image generation with Stable Diffusion

Features

• Ability to upload an image and detect emotion

Neutral	Happy	Sad

• Image Restoration

• Image styling

• Image editing

• Image Prompt

More faces

Find more faces here or upload your own and have fun

References/Credits

1. GFPGAN: https://github.com/TencentARC/GFPGAN

@InProceedings{wang2021gfpgan,
    author = {Xintao Wang and Yu Li and Honglun Zhang and Ying Shan},
    title = {Towards Real-World Blind Face Restoration with Generative Facial Prior},
    booktitle={The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
    year = {2021}
}

2. StyleGAN2-ADA: https://github.com/NVlabs/stylegan2-ada-pytorch

@inproceedings{Karras2020ada,
  title     = {Training Generative Adversarial Networks with Limited Data},
  author    = {Tero Karras and Miika Aittala and Janne Hellsten and Samuli Laine and Jaakko Lehtinen and Timo Aila},
  booktitle = {Proc. NeurIPS},
  year      = {2020}
}

3. Latent Space Exploration with StyleGAN2: https://github.com/AmarSaini/Epoching-Blog/blob/master/_notebooks/2020-08-10-Latent-Space-Exploration-with-StyleGAN2.ipynb
4. Latent Diffusion Models: https://arxiv.org/abs/2112.10752

https://github.com/huggingface/diffusers; https://github.com/CompVis/stable-diffusion; https://github.com/runwayml/stable-diffusion; https://stability.ai/blog/stable-diffusion-public-release; https://github.com/LAION-AI/

@misc{von-platen-etal-2022-diffusers,
  author = {Patrick von Platen and Suraj Patil and Anton Lozhkov and Pedro Cuenca and Nathan Lambert and Kashif Rasul and Mishig Davaadorj and Thomas Wolf},
  title = {Diffusers: State-of-the-art diffusion models},
  year = {2022},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/huggingface/diffusers}}
}