{"id":21207139,"url":"https://github.com/si-ddhartha/anigan","last_synced_at":"2026-05-18T02:05:23.600Z","repository":{"id":197145099,"uuid":"698068807","full_name":"Si-ddhartha/AniGAN","owner":"Si-ddhartha","description":"A TensorFlow implementation of Generative Adversarial Network to generate anime faces.","archived":false,"fork":false,"pushed_at":"2023-09-29T17:28:48.000Z","size":1308,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-08-09T09:02:09.847Z","etag":null,"topics":["deep-learning","gan","generative-adversarial-network","tensorflow"],"latest_commit_sha":null,"homepage":"https://anigan.onrender.com/","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Si-ddhartha.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2023-09-29T04:56:31.000Z","updated_at":"2023-10-05T13:57:00.000Z","dependencies_parsed_at":"2023-10-11T09:12:50.730Z","dependency_job_id":null,"html_url":"https://github.com/Si-ddhartha/AniGAN","commit_stats":{"total_commits":4,"total_committers":1,"mean_commits":4.0,"dds":0.0,"last_synced_commit":"1de873d9d5b46be3c96cf2c8b5c7140b0e38994b"},"previous_names":["si-ddhartha/anigan"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/Si-ddhartha/AniGAN","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Si-ddhartha%2FAniGAN","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Si-ddhartha%2FAniGAN/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Si-ddhartha%2FAniGAN/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Si-ddhartha%2FAniGAN/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Si-ddhartha","download_url":"https://codeload.github.com/Si-ddhartha/AniGAN/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Si-ddhartha%2FAniGAN/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":273381681,"owners_count":25095325,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-09-03T02:00:09.631Z","response_time":76,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["deep-learning","gan","generative-adversarial-network","tensorflow"],"created_at":"2024-11-20T20:57:52.858Z","updated_at":"2026-05-18T02:05:23.562Z","avatar_url":"https://github.com/Si-ddhartha.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# AniGAN\n\n\u003e A simple Tensorflow implementation of Generative Adversarial Networks, focusing on generating anime faces.\n\n\nAniGAN leverages the capabilities of Generative Adversarial Networks (GANs) to produce Anime faces. This project was born out of a passion for both deep learning and anime. It showcases the potential of GANs in creating stunning, high-quality images and provides a foundation for further exploration and improvement.\n\n*Some images generated by AniGAN*\n\n![gen_img](https://github.com/Si-ddhartha/AniGAN/assets/74449359/dc40747e-3f0c-4e35-ae05-e5dccff7be5d)\n\nThe model was trained on a dataset containing around 63k anime faces for **100 epochs**.\n\n**Note -:** The model's training was constrained to only 100 epochs because of resource limitations. I believe that training for a longer period will produce more refined results.\n\n## Overview\n\n- The GAN has two neural networks, the 'generator' and the 'discriminator'.  \n- The generator takes in a random vector which then uses transposed convolutions to generate an image out of it.  \n- The discriminator is a Convolutional network that then classifies whether an image is real or fake. It takes in samples of images from the dataset\n and also images generated by the generator.  \n- Both networks try to improve each other's performance through backpropagation.\n\n## Some use cases\n\n- It can help artists and designers come up with unique character concepts quickly.\n- Design custom merchandise, such as posters, prints, and apparel, featuring anime-style artwork.\n- We have the flexibility to train this identical model on various datasets, such as human faces, enabling versatile applications like data augmentation and style transfer.\n\n\nAnd lastly, I would like to say one more thing - Training GANs is **really** hard!!!\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsi-ddhartha%2Fanigan","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fsi-ddhartha%2Fanigan","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fsi-ddhartha%2Fanigan/lists"}