{"data":{"slug":"stochasticai-x-stable-diffusion","name":"x-stable-diffusion","tagline":"Real-time inference for Stable Diffusion - 0.88s latency","github_url":"https://github.com/stochasticai/x-stable-diffusion","owner":"stochasticai","repo":"x-stable-diffusion","owner_avatar_url":"https://avatars.githubusercontent.com/u/66399337?v=4","primary_language":"Jupyter Notebook","stars":556,"forks":34,"topics":["aitemplate","automl","cuda","docker","inference","notebook","nvfuser","onnx","onnxruntime","pytorch","stable-diffusion","tensorrt"],"archived":true,"github_pushed_at":"2023-12-04T17:42:17+00:00","maintenance_label":"Archived","stars_delta_30d":-1,"url":"https://www.graphcanon.com/tools/stochasticai-x-stable-diffusion","markdown_url":"https://www.graphcanon.com/tools/stochasticai-x-stable-diffusion.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/stochasticai-x-stable-diffusion","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=stochasticai-x-stable-diffusion","description":"Real-time inference for Stable Diffusion - 0.88s latency. Covers AITemplate, nvFuser, TensorRT, FlashAttention. Join our Discord communty: https://discord.com/invite/TgHXuSJEk6","homepage_url":"https://stochastic.ai","license":"Apache-2.0","open_issues":22,"watchers":2,"ai_summary":"Provides real-time inference solutions for Stable Diffusion using AITemplate, nvFuser, TensorRT, and FlashAttention.","readme_excerpt":"### Manual deployment\n\nCheck the `README.md` of the following directories:\n- [AITemplate](./AITemplate/README.md)\n- [FlashAttention](./FlashAttention/README.md)\n- [nvFuser](./nvFuser/README.md)\n- [PyTorch](./PyTorch/README.md)\n- [TensorRT](./TensorRT/README.md)","github_created_at":"2022-10-10T10:20:32+00:00","created_at":"2026-07-11T23:11:59.853317+00:00","updated_at":"2026-09-20T04:29:53.396818+00:00","categories":[{"slug":"inference-serving","name":"Inference & Serving","url":"https://www.graphcanon.com/categories/inference-serving","markdown_url":"https://www.graphcanon.com/categories/inference-serving.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/inference-serving"}],"tags":[{"slug":"aitemplate","name":"aitemplate"},{"slug":"automl","name":"automl"},{"slug":"cuda","name":"cuda"},{"slug":"docker","name":"docker"},{"slug":"inference","name":"inference"},{"slug":"notebook","name":"notebook"},{"slug":"nvfuser","name":"nvfuser"},{"slug":"onnx","name":"onnx"}],"trust":{"provenance":{"is_fork":false,"github_id":548876576,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-09-18T08:19:22.342Z","maintenance":{"label":"Archived","score":8,"methodology":"github_public_v1","releases_90d":0,"days_since_push":1018,"last_release_at":null,"stars_delta_30d":-1,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-09-18T08:19:23.975Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-09-18T08:19:21.257Z"},"languages":{"value":["jupyter notebook"],"source":"github.language","observed_at":"2026-09-18T08:19:21.257Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-09-18T08:19:21.257Z"}},"decision_facts":{"hosting":{"model":"unknown","summary":"The repository does not specify the hosting model for the tool."},"pricing":null,"requirements":{"notes":["Requires CUDA for optimal performance.","Supports deployment via Jupyter Notebook."],"min_ram_gb":8,"requires_docker":true},"constraints":{"min_ram_gb":8,"hosting_model":"unknown","requires_docker":true},"when_to_use":["When you need real-time inference with a latency as low as 0.88 seconds for Stable Diffusion models.","If your project requires integration with AITemplate, nvFuser, TensorRT, or FlashAttention for optimized performance."],"when_not_to_use":["If your project does not require real-time inference or can tolerate higher latency.","When you are working in an environment that does not support CUDA, as x-stable-diffusion heavily relies on CUDA for performance."],"source":"enrich:decision_facts","observed_at":"2026-09-18T09:43:55.546Z"},"constraint_facets":{"min_ram_gb":8,"hosting_model":"unknown","requires_docker":true},"decision_summary":[{"label":"Hosting","value":"unknown - The repository does not specify the hosting model for the tool."},{"label":"Requirements","value":"Min 8 GB RAM; Requires Docker; Requires CUDA for optimal performance.; Supports deployment via Jupyter Notebook."},{"label":"Adopt for","value":"x-stable-diffusion offers real-time inference for Stable Diffusion with a latency of 0.88 seconds, leveraging AITemplate, nvFuser, TensorRT, and FlashAttention."},{"label":"License detail","value":"The tool is licensed under Apache-2.0, allowing for free use, modification, and distribution."}]}}