This project is built around the wonderful Fast.AI library. The easiest way to get started is to simply try out on Colab: (Try_it_on_Colab).ipynb Installation Details I will be constantly upgrading the project for the foreseeable future. I hope I was clear, going forward would like to improve the model further as it still struggles with random backgrounds(I'm creating a custom dataset to address this issue). For this purpose selected images from Anime sketch colorization pair were used. All my efforts are to improve the model and make line art a click away.ĪPDrawing data set consits of mostly close-up portraits so the model would struggle to recogonize cloths,hands etc. The initial efforts have helped to recognize lines, but still the model has to improve a lot with shadows and clothes. The mission was to create something that converts any personal photo into a line art. GAN did not make much of a difference so I was happy with No GAN. Generator Loss : Perceptual Loss/Feature Loss based on VGG16. Thanks to fast.ai for intrdoucing me to Progressive resizing, this helps the model to generalise better as it sees many more different images. Progressive resizing takes this idea of gradually increasing the image size, In this project the image size were gradually increased and learning rates were adjusted. Something that I got from Jason Antic's DeOldify( ), this made a huge difference, all of a sudden I started getting proper details around the facial features. Generator is pretrained UNET with spectral normalization and self-attention. The movie poster was created using ArtLine in no time, it's not as good as it should be but I'm not an artist. The combined dataset helped the model to learn the lines better. APDrawing dataset alone was not enough so I had to combine selected photos from Anime sketch colorization pair dataset. Achieving proper lines around the face, eyes, lips and nose depends on the data you give the model. ![]() ![]() Even though ( ) produced great results it had limitations like (frontal face photo similar to ID photo, preferably with clear face features, no glasses and no long fringe.) I wanted to break-in and produce results that could recognize any pose. The initial model couldn't create the sort of output I was expecting, it mostly struggled with recognizing facial features. The amazing results that the model has produced has a secret sauce to it. The model is designed to take in a portrait image and a corresponding written instruction, and then use that instruction to adjust the style of the image.īohemian rhapsody movie, Rami Malek American actorĬlick on the below image to know more about colab demo, credits to Bhavesh Bhatt for the amazing Youtube video. Exciting update ControlNet + ArtLine for portraits, Try colab!! The main aim of the project is to create amazing line art portraits. You can sponsor me to support my open source work □ sponsor
0 Comments
Leave a Reply. |