{"id":21599322,"url":"https://github.com/t04glovern/deep-dune-coloring","last_synced_at":"2025-07-30T06:08:28.151Z","repository":{"id":102174699,"uuid":"177397879","full_name":"t04glovern/deep-dune-coloring","owner":"t04glovern","description":"Automatic coloring and shading of Dune coloring book using manga-style lineart model from deepcolor. Makes use of Tensorflow + cGANs","archived":false,"fork":false,"pushed_at":"2019-03-25T12:47:52.000Z","size":5453,"stargazers_count":5,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-07-19T15:44:23.217Z","etag":null,"topics":["cgan","dune","gan","tensorflow"],"latest_commit_sha":null,"homepage":"https://devopstar.com/2019/03/25/dune-coloring-book-using-cgan-tensorflow/","language":"Python","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/t04glovern.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,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null}},"created_at":"2019-03-24T10:07:45.000Z","updated_at":"2020-11-04T08:42:56.000Z","dependencies_parsed_at":null,"dependency_job_id":"aeeb34f2-f263-4007-80d5-a40082f75faa","html_url":"https://github.com/t04glovern/deep-dune-coloring","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/t04glovern/deep-dune-coloring","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/t04glovern%2Fdeep-dune-coloring","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/t04glovern%2Fdeep-dune-coloring/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/t04glovern%2Fdeep-dune-coloring/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/t04glovern%2Fdeep-dune-coloring/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/t04glovern","download_url":"https://codeload.github.com/t04glovern/deep-dune-coloring/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/t04glovern%2Fdeep-dune-coloring/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":267820861,"owners_count":24149291,"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":"2025-07-30T02:00:09.044Z","response_time":70,"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":["cgan","dune","gan","tensorflow"],"created_at":"2024-11-24T18:14:57.642Z","updated_at":"2025-07-30T06:08:28.131Z","avatar_url":"https://github.com/t04glovern.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# DeepDune Coloring\n\nAutomatic coloring and shading of Dune coloring book using manga-style lineart model from deepcolor. Makes use of Tensorflow + cGANs\n\n![example01](img/example01.png)\n\n![example02](img/example02.png)\n\n## Dune PDF\n\nFirst download a copy of the coloring book from my S3 bucket\n\n```bash\naws s3 cp s3://devopstar/resources/deep-dune-coloring/dune-coloring-book-remaster.pdf dune-coloring-book-remaster.pdf\n```\n\n### Optional - Convert the PDF into pages\n\n```bash\n./convert.sh\n```\n\nThis will dump out the Dune book images to the `dune` folder along with splitting the pages. You will need to have `imagemagick` to do this. The alternative is you can download these pages from my S3 bucket.\n\n```bash\naws s3 sync s3://devopstar/resources/deep-dune-coloring/dune dune/\n```\n\n## Deepcolor\n\nSetup Deepcolor using the handy version built by [Kevin Frans](https://github.com/kvfrans) that I've tweaked slightly and put in this repository\n\n### Setup Repo\n\nCreate the output directories that will be needed\n\n```bash\ncd deepcolor\nmkdir results\nmkdir imgs\nmkdir samples\n```\n\n### Python Environment\n\n#### Conda\n\n```bash\n## GPU\nconda create -n tensorflow_gpuenv_py27 tensorflow-gpu python=2.7 numpy\nconda activate tensorflow_gpuenv_py27\npip install opencv-python untangle bottle\n```\n\n#### Alternatives\n\nThe requirements you will need are:\n\n- Python 2.7\n- Tensorflow 1.12\n- numpy, opencv-python, untangle, bottle\n\n### Training\n\nIf you would like to train your own version you will need to download the training data from Safebooru. This can be done by running the following script.\n\n```bash\n# From within deepcolor/\npython download_images.py\n```\n\nAlternatively you can sync the training set I used down from S3 (If this gets hammers I will remove acces to it)\n\n```bash\n# From within deepcolor/\naws s3 sync s3://devopstar/resources/deep-dune-coloring/imgs imgs/\n```\n\nAt this point you can start training by running the following\n\n```bash\npython main.py train\n```\n\n### Pre-trained model\n\nIf you would like to use the pre-trained model you can pull down a copy from my S3 (If this gets hammers I will remove access to it. Contact me @nathangloverAUS on twitter if you would like access)\n\n```bash\n# From within deepcolor/\naws s3 sync s3://devopstar/resources/deep-dune-coloring/checkpoint checkpoint/\n```\n\nYou should have a folder structure as follows:\n\n```bash\n# From within deepcolor/\ncheckpoint/\n    tr/\n        checkpoint\n        model-10900500.index\n        model-10900500.data-00000-of-00001\n        model-10900500.meta\n```\n\n### Web Interface\n\nOnce you have either run the training task (and have a checkpoint folder) or have downloaded the pretrained model using the command above you should be able to run the web interface that can be used to interact with the model\n\n```bash\n# From within deepcolor/\npython server.py\n```\n\nOpen up the web interface on [http://localhost:8000](http://localhost:8000)\n\n## Attribution\n\n- [Deepcolor: automatic coloring and shading of manga-style lineart](http://kvfrans.com/coloring-and-shading-line-art-automatically-through-conditional-gans/)\n- [kvfrans/deepcolor](https://github.com/kvfrans/deepcolor)\n- [burness/tensorflow-101](https://github.com/burness/tensorflow-101)\n- [pix2pix implementation](https://github.com/yenchenlin/pix2pix-tensorflow)","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ft04glovern%2Fdeep-dune-coloring","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ft04glovern%2Fdeep-dune-coloring","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ft04glovern%2Fdeep-dune-coloring/lists"}