{"id":13563660,"url":"https://github.com/pixray/pixray","last_synced_at":"2025-05-16T08:05:21.547Z","repository":{"id":37509802,"uuid":"430702223","full_name":"pixray/pixray","owner":"pixray","description":null,"archived":false,"fork":false,"pushed_at":"2023-09-24T11:28:53.000Z","size":447,"stargazers_count":1038,"open_issues_count":38,"forks_count":133,"subscribers_count":16,"default_branch":"master","last_synced_at":"2025-04-08T19:25:11.761Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/pixray.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null}},"created_at":"2021-11-22T12:43:25.000Z","updated_at":"2025-04-07T11:24:41.000Z","dependencies_parsed_at":"2024-01-07T16:30:06.328Z","dependency_job_id":null,"html_url":"https://github.com/pixray/pixray","commit_stats":null,"previous_names":[],"tags_count":12,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pixray%2Fpixray","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pixray%2Fpixray/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pixray%2Fpixray/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pixray%2Fpixray/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/pixray","download_url":"https://codeload.github.com/pixray/pixray/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":254493378,"owners_count":22080126,"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","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":[],"created_at":"2024-08-01T13:01:21.851Z","updated_at":"2025-05-16T08:05:16.538Z","avatar_url":"https://github.com/pixray.png","language":"Python","funding_links":[],"categories":["Python","Image Synthesis"],"sub_categories":["AI Tools for Searching"],"readme":"# pixray\n\n![Alt text](https://user-images.githubusercontent.com/945979/132954388-1986e4c6-6996-48fd-9e91-91ec97963781.png \"deep ocean monsters #pixelart\")\n\nPixray is an image generation system. It combines previous ideas including:\n\n * [Perception Engines](https://github.com/dribnet/perceptionengines) which uses image augmentation and iteratively optimises images against an ensemble of classifiers\n * [CLIP guided GAN imagery](https://alexasteinbruck.medium.com/vqgan-clip-how-does-it-work-210a5dca5e52) from [Ryan Murdoch](https://twitter.com/advadnoun) and [Katherine Crowson](https://github.com/crowsonkb) as well as modifictions such as [CLIPDraw](https://twitter.com/kvfrans/status/1409933704856674304) from Kevin Frans\n * Useful ways of navigating latent space from [Sampling Generative Networks](https://github.com/dribnet/plat)\n * (more to come)\n\npixray it itself a python library and command line utility, but is also friendly to running on line in Google Colab notebooks.\n\nThere is currently [some documentation on options](https://dazhizhong.gitbook.io/pixray-docs/docs). Also checkout [THE DEMO NOTEBOOKS](https://github.com/pixray/pixray_notebooks) or join in the [discussion on discord](https://discord.gg/x2g9TWrNKe).\n\n## Usage\n\nBe sure to `git clone --recursive` to also get submodules.\n\nYou can install `pip install -r requirements.txt` and then `pip install basicsr` manually in a fresh python 3.8 environment (eg: using conda). After that you can use the included `pixray.py` command line utility:\n\n    python pixray.py --drawer=pixel --prompt=sunrise --outdir sunrise01\n\npixray can also be run from within your own python code, like this\n\n```python\nimport pixray\npixray.run(\"an extremely hairy panda bear\", \"vdiff\", custom_loss=\"aesthetic\", outdir=\"outputs/hairout\")\n```\n\nExamples of pixray colab notebooks can be found [in this separate repo](https://github.com/pixray/pixray_notebooks).\n\nrunning in a Docker using [Cog](https://github.com/replicate/cog) is also possible. First, [install Docker and Cog](https://github.com/replicate/cog#install), then you can use `cog run` to run Pixray inside Docker. For example: \n\n    cog run python pixray.py --drawer=pixel --prompt=sunrise --outdir sunrise01\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpixray%2Fpixray","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpixray%2Fpixray","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpixray%2Fpixray/lists"}