[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M795QCFR384V3B6AB8HJPSMH":3,"skill-same:01M795QCFR384V3B6AB8HJPSMH":66},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":17,"publishedAt":18,"linkOnly":19,"markdownContent":20,"markdownBody":21,"frontMatter":22,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":32,"install":33,"resources":45},"01M795QCFR384V3B6AB8HJPSMH","stylegan2-pytorch",null,"Guides StyleGAN2 PyTorch image GAN training, checkpoint generation, interpolation, and programmatic sampling with the stylegan2_pytorch package.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"MIT","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fstylegan2-pytorch\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: stylegan2-pytorch\ndescription: \"Guides StyleGAN2 PyTorch image GAN training, checkpoint\n  generation, interpolation, and programmatic sampling with the\n  stylegan2_pytorch package.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# StyleGAN2 PyTorch Repo Skill\n\nUse this repo skill when a task involves the `stylegan2_pytorch` package, the\n`stylegan2_pytorch` command, or StyleGAN2-style image GAN training\u002Fsampling in\nthis implementation. The package is CUDA-first: importing the main module\nasserts that `torch.cuda.is_available()` is true, so do not plan CPU-only use.\n\n## Fast routing\n\n- Use [training](sub-skills\u002Ftraining\u002FSKILL.md) for command-line training from an\n  image folder, checkpoint resume\u002Frestart decisions, sample generation,\n  interpolation GIFs, low-data augmentation, FID\u002Flogging options, transparent\n  images, attention\u002Fvector-quantization knobs, and multi-GPU settings.\n- Use [programmatic-api](sub-skills\u002Fprogrammatic-api\u002FSKILL.md) when the user\n  wants Python code with `ModelLoader`, `Trainer`, or `StyleGAN2`, especially\n  loading a trained checkpoint and saving generated images from tensors.\n- Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) when an\n  install, import, CUDA, optional dependency, CLI parsing, checkpoint, or\n  package-version failure blocks either workflow.\n- Read [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md) before\n  deciding whether this skill is stale for a checkout or should be refreshed.\n\n## Package facts to keep in mind\n\n- Distribution name and import name: `stylegan2_pytorch`.\n- Console command: `stylegan2_pytorch`.\n- Public exports from the package root: `Trainer`, `StyleGAN2`, `ModelLoader`,\n  and `NanException`.\n- The core CLI is implemented with Python Fire around `train_from_folder`, so\n  Fire help displays underscore flag names even though the README commonly shows\n  hyphenated flag names.\n- Training inputs are recursive image folders containing `.jpg`, `.jpeg`, or\n  `.png` files.\n- Default outputs are `results\u002F\u003Cname>\u002F` for generated images and\n  `models\u002F\u003Cname>\u002Fmodel_\u003Cn>.pt` plus `models\u002F\u003Cname>\u002F.config.json` for checkpoints\n  and model settings.\n\n## Install and environment check\n\nThe documented public install path is:\n\n```bash\npip install stylegan2_pytorch\n```\n\nFor a local clone, an editable install is useful while developing or verifying\nagainst that checkout:\n\n```bash\npip install -e .\n```\n\nUse a CUDA-capable PyTorch\u002Ftorchvision build before relying on the package. The\nmain module imports `aim`, `einops`, `kornia`, `vector_quantize_pytorch`,\n`torch`, `torchvision`, and other setup dependencies at import time.\n\nAfter installing, run the bundled checker from this skill directory if the user\nhas an environment ready:\n\n```bash\npython scripts\u002Fcheck_install.py\n```\n\nIt performs only import, CUDA, signature, and CLI-help checks; it does not train\nor download data.\n\n## Workflow starting points\n\n1. For a new training run, open [training](sub-skills\u002Ftraining\u002FSKILL.md), then\n   use its data-layout and CLI references to choose `--data`, `--name`, image\n   size, batch\u002Faccumulation, output directories, and augmentation settings.\n2. For generation after a run, keep the same `--name`, `--models_dir`, and\n   `--results_dir` layout and use the training generation\u002Finterpolation routes.\n3. For Python sampling, open\n   [programmatic-api](sub-skills\u002Fprogrammatic-api\u002FSKILL.md); `ModelLoader`\n   expects the default `base_dir\u002Fmodels\u002F\u003Cname>\u002F` checkpoint layout.\n4. If the request is about another image-generation stack such as Diffusers,\n   ComfyUI, Stable Diffusion LoRA training, image classification, detection, or\n   segmentation, this skill is probably not the right operating graph.\n\n## Verification status\n\nThis skill was constructed with a CUDA backend inspection environment and a\npost-integration plan for CLI help, one-step training, and `ModelLoader`\nsampling checks. The user requested **not to import** the skill into the managed\nrepo-skill library, so use the generated directory directly unless a later\nrequest authorizes import.\n","# StyleGAN2 PyTorch Repo Skill\n\nUse this repo skill when a task involves the `stylegan2_pytorch` package, the\n`stylegan2_pytorch` command, or StyleGAN2-style image GAN training\u002Fsampling in\nthis implementation. The package is CUDA-first: importing the main module\nasserts that `torch.cuda.is_available()` is true, so do not plan CPU-only use.\n\n## Fast routing\n\n- Use [training](sub-skills\u002Ftraining\u002FSKILL.md) for command-line training from an\n  image folder, checkpoint resume\u002Frestart decisions, sample generation,\n  interpolation GIFs, low-data augmentation, FID\u002Flogging options, transparent\n  images, attention\u002Fvector-quantization knobs, and multi-GPU settings.\n- Use [programmatic-api](sub-skills\u002Fprogrammatic-api\u002FSKILL.md) when the user\n  wants Python code with `ModelLoader`, `Trainer`, or `StyleGAN2`, especially\n  loading a trained checkpoint and saving generated images from tensors.\n- Read [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md) when an\n  install, import, CUDA, optional dependency, CLI parsing, checkpoint, or\n  package-version failure blocks either workflow.\n- Read [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md) before\n  deciding whether this skill is stale for a checkout or should be refreshed.\n\n## Package facts to keep in mind\n\n- Distribution name and import name: `stylegan2_pytorch`.\n- Console command: `stylegan2_pytorch`.\n- Public exports from the package root: `Trainer`, `StyleGAN2`, `ModelLoader`,\n  and `NanException`.\n- The core CLI is implemented with Python Fire around `train_from_folder`, so\n  Fire help displays underscore flag names even though the README commonly shows\n  hyphenated flag names.\n- Training inputs are recursive image folders containing `.jpg`, `.jpeg`, or\n  `.png` files.\n- Default outputs are `results\u002F\u003Cname>\u002F` for generated images and\n  `models\u002F\u003Cname>\u002Fmodel_\u003Cn>.pt` plus `models\u002F\u003Cname>\u002F.config.json` for checkpoints\n  and model settings.\n\n## Install and environment check\n\nThe documented public install path is:\n\n```bash\npip install stylegan2_pytorch\n```\n\nFor a local clone, an editable install is useful while developing or verifying\nagainst that checkout:\n\n```bash\npip install -e .\n```\n\nUse a CUDA-capable PyTorch\u002Ftorchvision build before relying on the package. The\nmain module imports `aim`, `einops`, `kornia`, `vector_quantize_pytorch`,\n`torch`, `torchvision`, and other setup dependencies at import time.\n\nAfter installing, run the bundled checker from this skill directory if the user\nhas an environment ready:\n\n```bash\npython scripts\u002Fcheck_install.py\n```\n\nIt performs only import, CUDA, signature, and CLI-help checks; it does not train\nor download data.\n\n## Workflow starting points\n\n1. For a new training run, open [training](sub-skills\u002Ftraining\u002FSKILL.md), then\n   use its data-layout and CLI references to choose `--data`, `--name`, image\n   size, batch\u002Faccumulation, output directories, and augmentation settings.\n2. For generation after a run, keep the same `--name`, `--models_dir`, and\n   `--results_dir` layout and use the training generation\u002Finterpolation routes.\n3. For Python sampling, open\n   [programmatic-api](sub-skills\u002Fprogrammatic-api\u002FSKILL.md); `ModelLoader`\n   expects the default `base_dir\u002Fmodels\u002F\u003Cname>\u002F` checkpoint layout.\n4. If the request is about another image-generation stack such as Diffusers,\n   ComfyUI, Stable Diffusion LoRA training, image classification, detection, or\n   segmentation, this skill is probably not the right operating graph.\n\n## Verification status\n\nThis skill was constructed with a CUDA backend inspection environment and a\npost-integration plan for CLI help, one-step training, and `ModelLoader`\nsampling checks. The user requested **not to import** the skill into the managed\nrepo-skill library, so use the generated directory directly unless a later\nrequest authorizes import.\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fstylegan2-pytorch",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":25},[35,38,41],{"tool":36,"command":37},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill stylegan2-pytorch",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill stylegan2-pytorch",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill stylegan2-pytorch","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fstylegan2-pytorch\u002FSKILL.md",[46,52,56,60],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Frepo-provenance.md","REFERENCE","参考文档",1851,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fstylegan2-pytorch\u002Freferences\u002Frepo-provenance.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Frepo-routing-metadata.json",337,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fstylegan2-pytorch\u002Freferences\u002Frepo-routing-metadata.json",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",4202,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fstylegan2-pytorch\u002Freferences\u002Ftroubleshooting.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fcheck_install.py","SCRIPT","脚本",5779,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fstylegan2-pytorch\u002Fscripts\u002Fcheck_install.py",[67,75,82,89,96,103],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"publishedAt":18},"01M799NYSH1R3RVAHSM2D88Y84","passnet-triton-opt","Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block\u002Fgrid\u002Fwarp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-triton-opt\u002FSKILL.md",[],[],{"skillNo":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"publishedAt":18},"01M799NS5APEC0N1FZ7XZVW6BN","passnet-solve","END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-solve\u002FSKILL.md",[],[],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":18},"01M799NNY9BKSM21V5R7QVTBJX","passnet-skill","PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under .\u002Fpass_dir\u002F, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-skill\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"publishedAt":18},"01M799NHH6NP7Z1RK77KGXAN6S","passnet-pattern-fusion","Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()\u002Freplacement_args()\u002Freplacement_func() files, when a pass \"failed to match\", or when deciding how to fuse multiple kernels\u002Fops.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-pattern-fusion\u002FSKILL.md",[],[],{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"publishedAt":18},"01M799ND2J4WNC2PGAZ0A06NDF","passnet-orchestrate","Round\u002Fbatch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep\u002Frevert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-orchestrate\u002FSKILL.md",[],[],{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":71,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":18},"01M799N8SBTMY02ZDG2AZF5ZWE","passnet-feedback","Fast, deterministic feedback for PassNet work: pre-flight pattern\u002Fmatch verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Ftask-oriented\u002FPassNet\u002Fskills\u002Fpassnet-feedback\u002FSKILL.md",[],[]]