{"id":19815949,"url":"https://github.com/replicate/cog-sdxl","last_synced_at":"2025-05-16T08:06:37.194Z","repository":{"id":185434059,"uuid":"673493846","full_name":"replicate/cog-sdxl","owner":"replicate","description":"Stable Diffusion XL training and inference as a cog model","archived":false,"fork":false,"pushed_at":"2024-11-08T22:25:25.000Z","size":29295,"stargazers_count":224,"open_issues_count":34,"forks_count":107,"subscribers_count":24,"default_branch":"main","last_synced_at":"2025-05-16T01:34:24.517Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://replicate.com/stability-ai/sdxl","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/replicate.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,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-08-01T18:50:46.000Z","updated_at":"2025-04-27T09:13:13.000Z","dependencies_parsed_at":null,"dependency_job_id":"57125161-1fb8-494b-87b5-ebf3ba5942f7","html_url":"https://github.com/replicate/cog-sdxl","commit_stats":{"total_commits":51,"total_committers":16,"mean_commits":3.1875,"dds":0.607843137254902,"last_synced_commit":"c79cb3c9c3c2968ee53ada00c7fb02aa3b9fc58c"},"previous_names":["replicate/cog-sdxl"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/replicate%2Fcog-sdxl","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/replicate%2Fcog-sdxl/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/replicate%2Fcog-sdxl/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/replicate%2Fcog-sdxl/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/replicate","download_url":"https://codeload.github.com/replicate/cog-sdxl/tar.gz/refs/heads/main","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":"2024-11-12T10:07:49.812Z","updated_at":"2025-05-16T08:06:32.186Z","avatar_url":"https://github.com/replicate.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Cog-SDXL\n\n[![Replicate demo and cloud API](https://replicate.com/stability-ai/sdxl/badge)](https://replicate.com/stability-ai/sdxl)\n\nThis is an implementation of Stability AI's [SDXL](https://github.com/Stability-AI/generative-models) as a [Cog](https://github.com/replicate/cog) model.\n\n## Development\n\nFollow the [model pushing guide](https://replicate.com/docs/guides/push-a-model) to push your own fork of SDXL to [Replicate](https://replicate.com).\n\n## Basic Usage\n\nfor prediction,\n\n```bash\ncog predict -i prompt=\"a photo of TOK\"\n```\n\n```bash\ncog train -i input_images=@example_datasets/__data.zip -i use_face_detection_instead=True\n```\n\n```bash\ncog run -p 5000 python -m cog.server.http\n```\n\n## Update notes\n\n**2023-08-17**\n* ROI problem is fixed.\n* Now BLIP caption_prefix does not interfere with BLIP captioner.\n\n\n**2023-08-12**\n* Input types are inferred from input name extensions, or from the `input_images_filetype` argument\n* Preprocssing are now done with fp16, and if no mask is found, the model will use the whole image\n\n**2023-08-11**\n* Default to 768x768 resolution training\n* Rank as argument now, default to 32\n* Now uses Swin2SR `caidas/swin2SR-realworld-sr-x4-64-bsrgan-psnr` as default, and will upscale + downscale to 768x768\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Freplicate%2Fcog-sdxl","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Freplicate%2Fcog-sdxl","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Freplicate%2Fcog-sdxl/lists"}