{"id":22884206,"url":"https://github.com/lightdiffusion/lightdiffusion","last_synced_at":"2026-04-17T03:02:46.386Z","repository":{"id":267924351,"uuid":"902756882","full_name":"LightDiffusion/LightDiffusion","owner":"LightDiffusion","description":"Fastest Stable Diffusion GUI, Pipeline, with only one python script, with the least number of lines and in the least complex way.","archived":false,"fork":false,"pushed_at":"2024-12-13T07:55:10.000Z","size":35482,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-31T17:34:24.348Z","etag":null,"topics":["ai","artificial-intelligence","deep-learning","diffusion","generative-ai","gui","image-generation","pytorch","stable-diffusion","text2image","torch","txt2img"],"latest_commit_sha":null,"homepage":"https://aatrick.github.io/LightDiffusion/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/LightDiffusion.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":"2024-12-13T07:53:47.000Z","updated_at":"2024-12-13T08:00:41.000Z","dependencies_parsed_at":"2024-12-13T09:31:04.942Z","dependency_job_id":"a46ddd02-7442-4a08-a428-12fcacef9c00","html_url":"https://github.com/LightDiffusion/LightDiffusion","commit_stats":null,"previous_names":["lightdiffusion/lightdiffusion"],"tags_count":9,"template":false,"template_full_name":null,"purl":"pkg:github/LightDiffusion/LightDiffusion","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LightDiffusion%2FLightDiffusion","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LightDiffusion%2FLightDiffusion/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LightDiffusion%2FLightDiffusion/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LightDiffusion%2FLightDiffusion/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/LightDiffusion","download_url":"https://codeload.github.com/LightDiffusion/LightDiffusion/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/LightDiffusion%2FLightDiffusion/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31913078,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-16T18:22:33.417Z","status":"online","status_checked_at":"2026-04-17T02:00:06.879Z","response_time":62,"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":["ai","artificial-intelligence","deep-learning","diffusion","generative-ai","gui","image-generation","pytorch","stable-diffusion","text2image","torch","txt2img"],"created_at":"2024-12-13T19:16:34.238Z","updated_at":"2026-04-17T03:02:46.362Z","avatar_url":"https://github.com/LightDiffusion.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# LightDiffusion\n\nThe purpose of this repository and project is to remake the famous **stable-diffusion** in only **one python script**, with the\n**least number of lines** and in the **least complex way**, while being the **fastest diffusion algorithm**. It's made by retro-engineering Stable-Diffusion, ComfyUI and\nSDWebUI.\n\nThere's also a LightDiffusion version using Flux Dev available in releases and Flux branch.\n\nFor more information, check the [documentation](https://aatrick.github.io/LightDiffusion/)\n\nThe project grew up with time, leaving the purpose of only being the fastest and simplest SD1.5 image generator, if you seek the **original version of about 3000 lines of python**, you can still find it at [LightDiffusion-og](https://github.com/Aatrick/LightDiffusion-og) or in the releases [here](https://github.com/Aatrick/LightDiffusion/releases/tag/V1.0).\n\nAlso check out the **Refactored version for improved simplicity and assembling SD and Flux** at [LightDiffusion-Next](https://github.com/Aatrick/LightDiffusion-Next)\n\n## Features\n\n- Original **Txt2Img**, **Img2Img** (R-ERSGAN4x+ UltimateSDUpscaling DPM++ 2M)\n- **Attention** syntax\n- **Hires-Fix** (euler ancestral normal)\n- Nvidia, amd and Intel gpus and cpu\n- **Xformers and Pytorch** optimization\n- **Stable-Fast** implementation offering a 70% speedup at the cost of pre inference model optimization windup time\n- **FP16 and FP32** precision support\n- **Saved state** in between starts\n- **GUI**\n- DPM Adaptive Karras\n- **Clip Skip**\n- **LoRa and textual inversion** (embeddings) support\n- **Automatic Prompt-Enhancing** with llama3.1 (ollama)\n- **Discord bot** integration with the installation of [Boubou](https://github.com/Aatrick/Boubou) and the usage of LightDiffusion's pipeline\n- **Automatic Face and body Detailer** (based on [Impact pack](https://github.com/ltdrdata/ComfyUI-Impact-Pack))\n- **TAESD** image previewing at the cost of a 10% performance hit\n\n![Screenshot 2024-06-10 140130](https://github.com/Aatrick/LightDiffusion/assets/113598245/711100ee-3af6-49aa-9de6-81361a64f3f9)\n\n## Installation\n\nTo install, please download a release or clone this repo and execute the run.bat file in a cmd and you should be good to go.\n\n#### From Source\n\nElse install the python dependencies by writing `pip install -r requirements.txt`\n\nAfter doing that, add your SD1/1.5 safetensors model to the checkpoints directory and you should be good to go.\n\n### Stable-Fast\n\nTo use the stable-fast optimization refer to this [guide](https://github.com/chengzeyi/stable-fast?tab=readme-ov-file#installation) to install from the wheel file.\n\n### Ollama\n\nTo use the Prompt enhancer refer to this [guide](https://github.com/ollama/ollama?tab=readme-ov-file) to install and run those commands\n`ollama run llama3.1`\n`pip install ollama`\n\n### Discord\n\nTo use LightDiffusion in discord, refer to the installation guide in this [repo](https://github.com/Aatrick/Boubou)\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flightdiffusion%2Flightdiffusion","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flightdiffusion%2Flightdiffusion","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flightdiffusion%2Flightdiffusion/lists"}