{"id":21220826,"url":"https://github.com/rupeshs/sdimagegenerator","last_synced_at":"2025-07-10T12:31:17.528Z","repository":{"id":60574962,"uuid":"535018364","full_name":"rupeshs/SDImageGenerator","owner":"rupeshs","description":"Stable Diffusion desktop UI for Windows","archived":false,"fork":false,"pushed_at":"2022-11-27T15:28:08.000Z","size":713,"stargazers_count":24,"open_issues_count":1,"forks_count":5,"subscribers_count":2,"default_branch":"main","last_synced_at":"2024-05-02T01:39:28.910Z","etag":null,"topics":["artificial-intelligence","cpp","deep-learning","python","qt5","stable-diffusion","texttoimage","windows"],"latest_commit_sha":null,"homepage":"","language":"C++","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/rupeshs.png","metadata":{"files":{"readme":"ReadMe.md","changelog":"changelog.md","contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null}},"created_at":"2022-09-10T14:13:40.000Z","updated_at":"2024-02-23T19:58:50.000Z","dependencies_parsed_at":"2023-01-22T14:45:23.983Z","dependency_job_id":null,"html_url":"https://github.com/rupeshs/SDImageGenerator","commit_stats":null,"previous_names":[],"tags_count":2,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rupeshs%2FSDImageGenerator","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rupeshs%2FSDImageGenerator/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rupeshs%2FSDImageGenerator/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/rupeshs%2FSDImageGenerator/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/rupeshs","download_url":"https://codeload.github.com/rupeshs/SDImageGenerator/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":225637111,"owners_count":17500365,"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":["artificial-intelligence","cpp","deep-learning","python","qt5","stable-diffusion","texttoimage","windows"],"created_at":"2024-11-20T22:14:14.870Z","updated_at":"2024-11-20T22:14:15.364Z","avatar_url":"https://github.com/rupeshs.png","language":"C++","readme":"## SDImageGenerator\nSDImageGenerator(SDIG) is a text-to-image generation AI desktop app  for Windows/Linux. It is still actively under development. The Linux version of the app is coming soon.\n\nSDImageGenerator v2            |  SDIG output sample\n:-------------------------:|:-------------------------:\n![SDImageGenerator ](/images/SDImageGenerator_v2.PNG \"SDImageGenerator 2.0\") | ![SDImageGenerator output](/images/SDImageGenerator_v2_output.PNG \"SDImageGenerator 2.0 output\").\n\n\n\n## Version 2.0.0, What's New? \n - Works on CPU/GPU but CPU image generation is slow(Recommended to use GPU for faster image generation)\n- The stable diffusion 1.5 model is used as default\n- Added model switching (For advanced use)\n- Supports dreambooth models (checkpoint files (.ckpt) supported)\n- Added textual inversion support(Hugging Face's concepts library models supported)\n- Added VAE(Variational autoencoder) support for fine details\n- Added CodeFormer support\n- Updated full precision mode with float32\n- Added high-resolution duplication fix setting\n- Image-to-image now supports k-diffusion samplers\n- Added Image-to-image mask image support \n- Added cancel functionality\n- Negative prompt support, use [ ] to use negative prompt\n           E.g: `a cute [white] dog`\n- Added Attention control support in prompt :\n            Use \"+\" to increase attention - `a house, apple++ tree`\n            Use \"-\" to decrease attention - `a house, apple- tree`\n- Supports prompt-to-Prompt editing (Cross attention control)\n            E.g:  In the below prompt cat will be replaced with a dog\n                    `A cat.swap(dog) riding bicycle`\n - Supports prompt blending \n                    E.g: `car:0.30 boat:0.70 hybrid`\n\nFor older changelogs, please visit [changelog](changelog.md).\n## Features \n- Simple interface\n- Portable package, simply extract and run the app\n- Image viewer for generated images\n- Application logs\n- Configurable image generation settings\n\n## System Requirements:\n- Windows 10/11 64-bit\n- Recent Nvidia GPU, preferably RTX ( 4 GB or more VRAM memory)\n- 12 GB RAM (16+ recommended)\n- ~11 GB disk space after installation (on SSD for best performance)\n\n## Development Dependencies \n- Qt 5.15.2\n\n## Coding Style\nIf you want to contribute please follow the coding style\n- [Qt Coding Style](https://wiki.qt.io/Qt_Coding_Style)\n\n## Python Part\n\n[Stable Diffusion fork](https://github.com/rupeshs/InvokeAI/tree/sdig)\n\n## Download SDImageGenerator\n[Download latest release ](https://rupeshsreeraman.itch.io/sdimagegenerator)","funding_links":[],"categories":[],"sub_categories":[],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frupeshs%2Fsdimagegenerator","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Frupeshs%2Fsdimagegenerator","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Frupeshs%2Fsdimagegenerator/lists"}