{"id":18973889,"url":"https://github.com/josefalbers/aggressor","last_synced_at":"2026-03-11T11:03:23.081Z","repository":{"id":256856422,"uuid":"856628713","full_name":"JosefAlbers/Aggressor","owner":"JosefAlbers","description":"Ultra-minimal autoregressive diffusion model for image generation","archived":false,"fork":false,"pushed_at":"2024-10-06T04:03:56.000Z","size":2478,"stargazers_count":21,"open_issues_count":0,"forks_count":1,"subscribers_count":2,"default_branch":"main","last_synced_at":"2025-12-22T00:38:05.707Z","etag":null,"topics":["artificial-intelligence","audio-generation","autoregressive","autoregressive-diffusion","autoregressive-models","deep-learning","diffusion","diffusion-models","image-generation","mlx","tts"],"latest_commit_sha":null,"homepage":"","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/JosefAlbers.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,"zenodo":null}},"created_at":"2024-09-12T23:07:52.000Z","updated_at":"2025-11-27T16:24:49.000Z","dependencies_parsed_at":"2025-04-20T14:16:16.840Z","dependency_job_id":null,"html_url":"https://github.com/JosefAlbers/Aggressor","commit_stats":null,"previous_names":["josefalbers/aggressor"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/JosefAlbers/Aggressor","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JosefAlbers%2FAggressor","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JosefAlbers%2FAggressor/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JosefAlbers%2FAggressor/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JosefAlbers%2FAggressor/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/JosefAlbers","download_url":"https://codeload.github.com/JosefAlbers/Aggressor/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/JosefAlbers%2FAggressor/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30379264,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-11T06:09:32.197Z","status":"ssl_error","status_checked_at":"2026-03-11T06:09:17.086Z","response_time":84,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["artificial-intelligence","audio-generation","autoregressive","autoregressive-diffusion","autoregressive-models","deep-learning","diffusion","diffusion-models","image-generation","mlx","tts"],"created_at":"2024-11-08T15:13:30.181Z","updated_at":"2026-03-11T11:03:23.059Z","avatar_url":"https://github.com/JosefAlbers.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Aggressor: Ultra-minimal autoregressive diffusion model for image and speech generation\n\n\u003ctable\u003e\n\u003ctr\u003e\n\u003ctd align=\"center\"\u003e\n\n**CIFAR**\n\n\u003c/td\u003e\n\u003ctd align=\"center\"\u003e\n\n**MNIST**\n\n\u003c/td\u003e\n\u003ctd align=\"center\"\u003e\n\n**AUDIO**\n\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003ctr\u003e\n\u003ctd align=\"center\"\u003e\n\n![cifar](https://raw.githubusercontent.com/JosefAlbers/Aggressor/main/assets/aggressor_cifar.png)\n\n\u003c/td\u003e\n\u003ctd align=\"center\"\u003e\n\n![mnist](https://raw.githubusercontent.com/JosefAlbers/Aggressor/main/assets/aggressor_mnist.png)\n\n\u003c/td\u003e\n\u003ctd align=\"center\"\u003e\n\n[audio](https://github.com/user-attachments/assets/89574625-2ec0-4aeb-884f-bf03e5a4aab0)\n\n\u003c/td\u003e\n\u003c/tr\u003e\n\u003c/table\u003e\n\nA simplest possible implementation of [Autoregressive Image Generation without Vector Quantization](https://arxiv.org/abs/2406.11838).\n\n## Key Features\n\n- **Simple Architecture**: A tiny transformer for autoregression and an MLP for diffusion.\n- **Minimal Dependencies**: Built from scratch using only basic MLX operations.\n- **Single-File Implementation**: Entire model in one Python file `aggressor.py`.\n\n## Components\n\n- `Aggressor`: Main model class combining transformer and diffusion.\n- `Transformer`: Multi-layer transformer with attention and MLP blocks.\n- `Denoiser`: MLP-based diffusion process with time embedding.\n- `Scheduler`: Handles forward and backward processes for diffusion.\n\n## Usage\n\n```zsh\npython aggressor.py\n```\n\n*(Training on 60000 images x 20 epochs takes approximately 7~8 minutes on 8GB M2 MacBook.)*\n\n## Acknowledgements\n\nThanks to [lucidrains](https://github.com/lucidrains/autoregressive-diffusion-pytorch)' fantastic code that inspired this project. The official implementation is available [here](https://github.com/LTH14/mar).\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjosefalbers%2Faggressor","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjosefalbers%2Faggressor","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjosefalbers%2Faggressor/lists"}