{"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":557,"forks":33,"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","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":"A repository focused on optimizing Stable Diffusion model inference using various tools including 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":"2026-08-02T00:00:47.234864+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"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"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":"2026-08-02T00:00:46.520Z","maintenance":{"label":"Archived","score":8,"methodology":"github_public_v1","releases_90d":0,"days_since_push":971,"last_release_at":null},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T23:12:04.330Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-02T00:00:46.989Z"},"languages":{"value":["jupyter notebook"],"source":"github.language","observed_at":"2026-08-02T00:00:46.989Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-08-02T00:00:46.989Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you require low-latency real-time inference performance at less than 1 second","If your project involves optimizing Stable Diffusion specifically"],"when_not_to_use":["For projects that do not require real-time performance or have higher latency tolerance","If the specific optimizations for Stable Diffusion are not aligned with your model needs"],"source":"enrich:decision_facts","observed_at":"2026-07-12T13:16:30.697Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"x-stable-diffusion offers real-time inference for the Stable Diffusion model with a latency of 0.88s, leveraging AITemplate, nvFuser, TensorRT, and FlashAttention."}]}}