[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F8J3M5PTACM5CMM44G2G52":3,"skill-same:01M7F8J3M5PTACM5CMM44G2G52":66},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":33,"updatedAt":34,"install":35,"resources":47},"01M7F8J3M5PTACM5CMM44G2G52","advanced-variants",null,"Advanced denoising-diffusion-pytorch variants: Karras UNets, continuous-time, EDM, simple diffusion, learned\u002Fweighted objectives, and attention backend compatibility.","lza6\u002FArmor-piercing-system-prompts","lza6","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F128880206?v=4","01M7EB3K7WPX5T28EJ2NVHE6EG","Chinese-tingfeng","01M7EB3K97E1KQ16QWKJMFNGX8",11,"MIT","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fdenoising-diffusion-pytorch\u002Fsub-skills\u002Fadvanced-variants\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: advanced-variants\ndescription: \"Advanced denoising-diffusion-pytorch variants: Karras UNets,\n  continuous-time, EDM, simple diffusion, learned\u002Fweighted objectives, and\n  attention backend compatibility.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Advanced Variants\n\nUse this sub-skill when a task goes beyond common DDPM\u002FDDIM image or 1D sequence paths and asks for Karras magnitude-preserving UNets, continuous-time or v-parameterized diffusion, EDM \u002F elucidated diffusion, simple diffusion UViT, learned variance, weighted objectives, video-shaped Karras 3D models, or flash \u002F SDPA attention behavior in `denoising-diffusion-pytorch` 2.3.1.\n\n## Route elsewhere\n\n- Common 2D image `Unet`, `GaussianDiffusion`, folder `Trainer`, FID, DDIM, or RePaint work: [..\u002Fimage-diffusion\u002FSKILL.md](..\u002Fimage-diffusion\u002FSKILL.md).\n- Common 1D sequence `Unet1D`, `GaussianDiffusion1D`, `Dataset1D`, or `Trainer1D` work: [..\u002Fsequence-diffusion\u002FSKILL.md](..\u002Fsequence-diffusion\u002FSKILL.md).\n- Classifier-free guidance, external classifier `cond_fn`, or `XMWrapper`: [..\u002Fconditioning-guidance\u002FSKILL.md](..\u002Fconditioning-guidance\u002FSKILL.md).\n\n## What this sub-skill covers\n\n- Karras architectures: `KarrasUnet`, `KarrasUnet1D`, `KarrasUnet3D`, and `InvSqrtDecayLRSched`.\n- Advanced diffusion wrappers: `ContinuousTimeGaussianDiffusion`, `VParamContinuousTimeGaussianDiffusion`, `ElucidatedDiffusion`, `LearnedGaussianDiffusion`, and `WeightedObjectiveGaussianDiffusion`.\n- Simple diffusion APIs: `denoising_diffusion_pytorch.simple_diffusion.UViT` and its `GaussianDiffusion`.\n- Attention compatibility: `Attend`, `flash_attn` constructor flags, PyTorch SDPA behavior, and CPU\u002FCUDA expectations.\n- A bundled tiny smoke helper: [scripts\u002Fsmoke_advanced_variants.py](scripts\u002Fsmoke_advanced_variants.py).\n\n## Required reference order\n\n1. Read [references\u002Fapi-reference.md](references\u002Fapi-reference.md) for import paths, signatures, tensor shapes, and constructor constraints.\n2. Read [references\u002Fworkflows.md](references\u002Fworkflows.md) for safe setup recipes and cross-skill routing.\n3. Read [references\u002Fcompatibility.md](references\u002Fcompatibility.md) before changing devices, enabling `flash_attn`, using Karras 3D downsampling, or selecting a CPU\u002FCUDA verification plan.\n4. Use [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) when an assertion mentions sinusoidal conditioning, self-conditioning, `out_dim`, DDIM, simple diffusion noise dimensions, Karras video divisibility, or SDPA.\n\n## Fast verification\n\nFrom the generated skill root:\n\n```bash\npython sub-skills\u002Fadvanced-variants\u002Fscripts\u002Fsmoke_advanced_variants.py --quick --device cpu\n```\n\nAdd `--include-3d` only when a tiny video-shaped Karras 3D check is desired.\n","# Advanced Variants\n\nUse this sub-skill when a task goes beyond common DDPM\u002FDDIM image or 1D sequence paths and asks for Karras magnitude-preserving UNets, continuous-time or v-parameterized diffusion, EDM \u002F elucidated diffusion, simple diffusion UViT, learned variance, weighted objectives, video-shaped Karras 3D models, or flash \u002F SDPA attention behavior in `denoising-diffusion-pytorch` 2.3.1.\n\n## Route elsewhere\n\n- Common 2D image `Unet`, `GaussianDiffusion`, folder `Trainer`, FID, DDIM, or RePaint work: [..\u002Fimage-diffusion\u002FSKILL.md](..\u002Fimage-diffusion\u002FSKILL.md).\n- Common 1D sequence `Unet1D`, `GaussianDiffusion1D`, `Dataset1D`, or `Trainer1D` work: [..\u002Fsequence-diffusion\u002FSKILL.md](..\u002Fsequence-diffusion\u002FSKILL.md).\n- Classifier-free guidance, external classifier `cond_fn`, or `XMWrapper`: [..\u002Fconditioning-guidance\u002FSKILL.md](..\u002Fconditioning-guidance\u002FSKILL.md).\n\n## What this sub-skill covers\n\n- Karras architectures: `KarrasUnet`, `KarrasUnet1D`, `KarrasUnet3D`, and `InvSqrtDecayLRSched`.\n- Advanced diffusion wrappers: `ContinuousTimeGaussianDiffusion`, `VParamContinuousTimeGaussianDiffusion`, `ElucidatedDiffusion`, `LearnedGaussianDiffusion`, and `WeightedObjectiveGaussianDiffusion`.\n- Simple diffusion APIs: `denoising_diffusion_pytorch.simple_diffusion.UViT` and its `GaussianDiffusion`.\n- Attention compatibility: `Attend`, `flash_attn` constructor flags, PyTorch SDPA behavior, and CPU\u002FCUDA expectations.\n- A bundled tiny smoke helper: [scripts\u002Fsmoke_advanced_variants.py](scripts\u002Fsmoke_advanced_variants.py).\n\n## Required reference order\n\n1. Read [references\u002Fapi-reference.md](references\u002Fapi-reference.md) for import paths, signatures, tensor shapes, and constructor constraints.\n2. Read [references\u002Fworkflows.md](references\u002Fworkflows.md) for safe setup recipes and cross-skill routing.\n3. Read [references\u002Fcompatibility.md](references\u002Fcompatibility.md) before changing devices, enabling `flash_attn`, using Karras 3D downsampling, or selecting a CPU\u002FCUDA verification plan.\n4. Use [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) when an assertion mentions sinusoidal conditioning, self-conditioning, `out_dim`, DDIM, simple diffusion noise dimensions, Karras video divisibility, or SDPA.\n\n## Fast verification\n\nFrom the generated skill root:\n\n```bash\npython sub-skills\u002Fadvanced-variants\u002Fscripts\u002Fsmoke_advanced_variants.py --quick --device cpu\n```\n\nAdd `--include-3d` only when a tiny video-shaped Karras 3D check is desired.\n",{"name":5,"license":15,"metadata":24,"description":7,"disable-model-invocation":26},{"disco-role":25},"operating",true,"main","d69096e239f2a89aabc2cd078c47664a9d3b1e11","06-前端与设计\u002Fdenoising-diffusion-pytorch\u002Fsub-skills\u002Fadvanced-variants",3,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts","https:\u002F\u002Fgithub.com\u002Flza6","个人vx：Tf00798\r\n个人✈：@TFGY999","2026-10-08 14:29:22",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":26},[37,40,43],{"tool":38,"command":39},"npx","npx skills add lza6\u002FArmor-piercing-system-prompts --skill advanced-variants",{"tool":41,"command":42},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill advanced-variants",{"tool":44,"command":45},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill advanced-variants","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fdenoising-diffusion-pytorch\u002Fsub-skills\u002Fadvanced-variants\u002FSKILL.md",[48,54,58,62],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Fapi-reference.md","REFERENCE","参考文档",3799,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fdenoising-diffusion-pytorch\u002Fsub-skills\u002Fadvanced-variants\u002Freferences\u002Fapi-reference.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Fcompatibility.md",3552,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fdenoising-diffusion-pytorch\u002Fsub-skills\u002Fadvanced-variants\u002Freferences\u002Fcompatibility.md",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Ftroubleshooting.md",2953,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fdenoising-diffusion-pytorch\u002Fsub-skills\u002Fadvanced-variants\u002Freferences\u002Ftroubleshooting.md",{"path":63,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":64,"sourceHtmlUrl":65},"references\u002Fworkflows.md",5030,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fdenoising-diffusion-pytorch\u002Fsub-skills\u002Fadvanced-variants\u002Freferences\u002Fworkflows.md",[67,74,79,86,93,100],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M7FFG485KY83TD6HSC4YPCMC","obsidian-clipper-template-creator","Guide for creating templates for the Obsidian Web Clipper. Use when you want to create a new clipping template, understand available variables, or format clipped content.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator\u002FSKILL.md",[],[],{"skillNo":75,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":19},"01M7FFG0T6AZ0STEJPSB3CX84K","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobsidian-clipper-template-creator-antigravity-awesome-skills-main\u002FSKILL.md",[],[],{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":19},"01M7FFFY0QEM14SKWPDYGMXM2P","python-api","Programmatic Object-Detection-Metrics API guidance for BoundingBox, BoundingBoxes, Evaluator, enums, coordinate conversion, AP\u002FmAP semantics, and source-style import diagnostics.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Fpython-api\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7FFFVZQZ2GJ0C0TGP7JHD20","file-evaluation","Folder-based PASCAL VOC AP\u002FmAP evaluation from ground-truth and detection text files.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002Fsub-skills\u002Ffile-evaluation\u002FSKILL.md",[],[],{"skillNo":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"publishedAt":19},"01M7FFFSFNYSE77SJ6PE1CK2DA","object-detection-metrics","Guides legacy Object-Detection-Metrics PASCAL VOC AP\u002FmAP evaluation from detection text folders and direct Python API classes.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fobject-detection-metrics\u002FSKILL.md",[],[],{"skillNo":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"publishedAt":19},"01M7FFFP0GCK1RVXBCPQ8APBMT","nx-workspace-patterns","Configure and optimize Nx monorepo workspaces. Use when setting up Nx, configuring project boundaries, optimizing build caching, or implementing affected commands.","https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F07-后端与架构\u002Fnx-workspace-patterns\u002FSKILL.md",[],[]]