{"id":18842055,"url":"https://github.com/overshard/ai-art","last_synced_at":"2025-07-13T07:09:59.746Z","repository":{"id":41244260,"uuid":"508815072","full_name":"overshard/ai-art","owner":"overshard","description":"Art generation using VQGAN + CLIP using docker containers. A simplified, updated, and expanded upon version of Kevin Costa's work. This project tries to make generating art as easy as possible for anyone with a GPU by providing a simple web UI.","archived":false,"fork":false,"pushed_at":"2022-07-04T00:11:01.000Z","size":2340,"stargazers_count":15,"open_issues_count":0,"forks_count":2,"subscribers_count":2,"default_branch":"master","last_synced_at":"2023-06-16T20:17:50.957Z","etag":null,"topics":["ai","ai-art","clip","docker","docker-compose","imagenet","python","pytorch","torch","torchvision","vqgan","vqgan-clip"],"latest_commit_sha":null,"homepage":"https://hub.docker.com/r/overshard/ai-art","language":"Python","has_issues":false,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"bsd-2-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/overshard.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.md","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2022-06-29T19:06:45.000Z","updated_at":"2023-06-16T18:55:56.000Z","dependencies_parsed_at":"2022-09-09T09:51:37.779Z","dependency_job_id":null,"html_url":"https://github.com/overshard/ai-art","commit_stats":null,"previous_names":[],"tags_count":null,"template":null,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/overshard%2Fai-art","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/overshard%2Fai-art/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/overshard%2Fai-art/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/overshard%2Fai-art/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/overshard","download_url":"https://codeload.github.com/overshard/ai-art/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":223624336,"owners_count":17175195,"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":["ai","ai-art","clip","docker","docker-compose","imagenet","python","pytorch","torch","torchvision","vqgan","vqgan-clip"],"created_at":"2024-11-08T02:53:31.633Z","updated_at":"2024-11-08T02:53:32.442Z","avatar_url":"https://github.com/overshard.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# AI-Art\n\n![AI-Art Screenshot](./Screenshot.webp)\n\nArt generation using VQGAN + CLIP using docker containers. A simplified,\nupdated, and expanded upon version of\n[Kevin Costa's work](https://github.com/kcosta42/VQGAN-CLIP-Docker). This\nproject tries to make generating art as easy as possible for anyone with a GPU\nby providing a simple web UI.\n\n\n## Samples\n\nFor samples check out the [AI Generated](https://isaacbythewood.com/art) section\non the art page on my website.\n\n\n## Using ai-art\n\nThis works best if you have an NVIDIA GPU however there is a fallback CPU mode\nincluded. I've found the CPU mode to take significantly longer than even the\nmost basic of GPUs though.\n\nInstall [Docker Desktop](https://www.docker.com/products/docker-desktop/) for\nyour OS.\n\n\n### Quick start usage\n\nNote that this creates a new directory in your current directory called ai-art\nfor all output and model storage. Make sure it's where you want it to be.\n\n    docker run -it --rm --gpus all -p 3000:3000 -v ${pwd}/ai-art:/data overshard/ai-art\n\nOnce it's running you can access AI-Art in your browser at:\n\n    http://localhost:3000/\n\n\n### Development usage\n\nGet the latest version of this project from GitHub:\n\n    git clone https://github.com/overshard/ai-art.git\n\nThen run it with:\n\n    docker build --tag overshard/ai-art .\n    docker run -it --rm --gpus all -p 3000:3000 -v ${pwd}/data:/data overshard/ai-art\n\nIf you are using a docker container on Windows to develop this project like I am\nthen you can use something like this to mount a directory on the host system\nfrom your development container:\n\n    docker run -it --rm --gpus all -p 3000:3000 -v \"/C/Users/Isaac Bythewood/Documents/AI-Art:/data\" overshard/ai-art\n\n\n## Image sizes\n\nThe larger the image the more VRAM your graphics card needs:\n\n- 6 GB of VRAM is required to generate 256x256 images.\n- 12 GB of VRAM is required to generate 512x512 images.\n- 24 GB of VRAM is required to generate 1024x1024 images.\n\nIf you don't know how much VRAM your graphics card has you probably have 6 GB\nor less so stick with smaller images.\n\nThat being said you can do non-square images if you want as long as you don't\ngo above the number of pixels your GPU's VRAM supports, for example you could\ndo ultrawide images with 6 GB of ram at \"384x128\" or do tall images at \"128x384\"\nand so on. You do not have to use numbers with a power of 2, \"300x100\" is also\nperfectly valid.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fovershard%2Fai-art","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fovershard%2Fai-art","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fovershard%2Fai-art/lists"}