[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7F8DFVXT5KFN5ASTMWP2F9T":3,"skill-same:01M7F8DFVXT5KFN5ASTMWP2F9T":62},{"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},"01M7F8DFVXT5KFN5ASTMWP2F9T","dalle2-pytorch",null,"Use the DALLE2-pytorch package for DALL-E 2 style text-to-image model APIs, diffusion prior\u002Fdecoder training, WebDataset data layouts, and tracker\u002Fcheckpoint workflows.","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\u002Fdalle2-pytorch\u002FSKILL.md",[],[],"2026-11-16 10:05:34",false,"---\nname: dalle2-pytorch\ndescription: \"Use the DALLE2-pytorch package for DALL-E 2 style text-to-image\n  model APIs, diffusion prior\u002Fdecoder training, WebDataset data layouts, and\n  tracker\u002Fcheckpoint workflows.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# DALLE2-pytorch\n\nUse this repo skill when a task involves the `dalle2-pytorch` package, DALL-E 2 style CLIP-latent text-to-image generation, diffusion prior training, cascaded decoder training, DALLE2 checkpoints, WebDataset embedding data, or the package's training\u002Fexperiment tracking utilities.\n\n## What This Skill Covers\n\n- Public Python APIs for `DALLE2`, `DiffusionPriorNetwork`, `DiffusionPrior`, `Unet`, `Decoder`, CLIP adapters, VQGAN\u002FVAE latent diffusion, inpainting, tokenization, and the `dream` CLI.\n- JSON config classes and bundled training launchers for decoder and diffusion-prior training.\n- WebDataset and EmbeddingReader data layouts, sidecar embedding folders, shard\u002Findex validation, trackers, checkpoint loading, and checkpoint saving.\n- Troubleshooting for install\u002Fimport, CLIP downloads, CPU vs GPU expectations, config validation, data layout, tracker credentials, and checkpoint format mismatches.\n\n## Install And Minimal Check\n\nInstall the public package:\n\n```bash\npython -m pip install dalle2-pytorch\n```\n\nRun the bundled package check from this skill directory:\n\n```bash\npython scripts\u002Fcheck_install.py --mode imports\npython scripts\u002Fcheck_install.py --mode cli-help\n```\n\nFor a CPU-only synthetic API smoke test that avoids CLIP downloads and model weights:\n\n```bash\npython sub-skills\u002Fgeneration-and-api\u002Fscripts\u002Fcheck_dalle2_runtime.py --mode tiny-forward\n```\n\n## Choose A Sub-Skill\n\n### `generation-and-api`\n\nRead [sub-skills\u002Fgeneration-and-api\u002FSKILL.md](sub-skills\u002Fgeneration-and-api\u002FSKILL.md) for Python model construction and generation tasks:\n\n- Build or call `DALLE2`, `DiffusionPrior`, `Decoder`, `Unet`, CLIP adapters, or `VQGanVAE`.\n- Use `dream`, load generation checkpoints, tokenize prompts, sample images, or perform decoder inpainting.\n- Debug checkpoint architecture mismatches, CLIP weight downloads, CPU\u002FGPU limitations, inpaint mask shape, or classifier-free guidance.\n\n### `training-and-configs`\n\nRead [sub-skills\u002Ftraining-and-configs\u002FSKILL.md](sub-skills\u002Ftraining-and-configs\u002FSKILL.md) for training and configuration tasks:\n\n- Author\u002Fvalidate `TrainDecoderConfig` or `TrainDiffusionPriorConfig` JSON.\n- Use `DecoderTrainer` or `DiffusionPriorTrainer` directly.\n- Build `python` or `accelerate launch` commands, run bundled training wrappers, resume\u002Fsave trainer checkpoints, or debug `unet_training_mask`, resampling, DeepSpeed fp16, and config errors.\n\n### `data-and-tracking`\n\nRead [sub-skills\u002Fdata-and-tracking\u002FSKILL.md](sub-skills\u002Fdata-and-tracking\u002FSKILL.md) for data and experiment-management tasks:\n\n- Validate decoder WebDataset shard names, sample keys, sidecar image\u002Ftext embedding folders, `shard_width`, or `index_width`.\n- Use `ImageEmbeddingDataset`, `create_image_embedding_dataloader`, `get_reader`, `make_splits`, or `PriorEmbeddingDataset`.\n- Configure console\u002FW&B logging, local\u002FURL\u002FW&B checkpoint loading, or local\u002FW&B\u002FHuggingFace saving.\n\n## Important Constraints\n\n- Real training and useful image sampling normally need GPU memory and trained checkpoints. CPU is suitable for imports, config parsing, CLI help, and tiny synthetic forward-loss tests.\n- CLIP adapters (`OpenAIClipAdapter`, `OpenClipAdapter`) may download weights and require network\u002Fcache. Do not instantiate them in offline smoke checks unless weights are already cached.\n- Training examples may need datasets, W&B\u002FHuggingFace\u002FS3 credentials, metric assets, and long runtime. Validate configs and data layout before launch.\n- The `dream` CLI expects a combined DALLE2 checkpoint with package-expected init\u002Fmodel keys; trainer checkpoints are a different format.\n- If `clip-anytorch` fails because `pkg_resources` is missing, install `setuptools\u003C81` and rerun `python -m pip check`.\n\n## Root References\n\n- Repository snapshot and refresh baseline: [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md).\n- Cross-cutting install\u002Fimport\u002Fbackend troubleshooting: [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md).\n- Router metadata used by managed import: [references\u002Frepo-routing-metadata.json](references\u002Frepo-routing-metadata.json).\n\n## Self-Containment Rule\n\nUse the bundled references and scripts in this skill tree. Do not require future agents to open, run, or copy scripts, docs, configs, tests, or examples from an original DALLE2-pytorch checkout. When a user wants to train in a checkout intentionally, treat that checkout as their working project, not as this skill's required evidence source.\n","# DALLE2-pytorch\n\nUse this repo skill when a task involves the `dalle2-pytorch` package, DALL-E 2 style CLIP-latent text-to-image generation, diffusion prior training, cascaded decoder training, DALLE2 checkpoints, WebDataset embedding data, or the package's training\u002Fexperiment tracking utilities.\n\n## What This Skill Covers\n\n- Public Python APIs for `DALLE2`, `DiffusionPriorNetwork`, `DiffusionPrior`, `Unet`, `Decoder`, CLIP adapters, VQGAN\u002FVAE latent diffusion, inpainting, tokenization, and the `dream` CLI.\n- JSON config classes and bundled training launchers for decoder and diffusion-prior training.\n- WebDataset and EmbeddingReader data layouts, sidecar embedding folders, shard\u002Findex validation, trackers, checkpoint loading, and checkpoint saving.\n- Troubleshooting for install\u002Fimport, CLIP downloads, CPU vs GPU expectations, config validation, data layout, tracker credentials, and checkpoint format mismatches.\n\n## Install And Minimal Check\n\nInstall the public package:\n\n```bash\npython -m pip install dalle2-pytorch\n```\n\nRun the bundled package check from this skill directory:\n\n```bash\npython scripts\u002Fcheck_install.py --mode imports\npython scripts\u002Fcheck_install.py --mode cli-help\n```\n\nFor a CPU-only synthetic API smoke test that avoids CLIP downloads and model weights:\n\n```bash\npython sub-skills\u002Fgeneration-and-api\u002Fscripts\u002Fcheck_dalle2_runtime.py --mode tiny-forward\n```\n\n## Choose A Sub-Skill\n\n### `generation-and-api`\n\nRead [sub-skills\u002Fgeneration-and-api\u002FSKILL.md](sub-skills\u002Fgeneration-and-api\u002FSKILL.md) for Python model construction and generation tasks:\n\n- Build or call `DALLE2`, `DiffusionPrior`, `Decoder`, `Unet`, CLIP adapters, or `VQGanVAE`.\n- Use `dream`, load generation checkpoints, tokenize prompts, sample images, or perform decoder inpainting.\n- Debug checkpoint architecture mismatches, CLIP weight downloads, CPU\u002FGPU limitations, inpaint mask shape, or classifier-free guidance.\n\n### `training-and-configs`\n\nRead [sub-skills\u002Ftraining-and-configs\u002FSKILL.md](sub-skills\u002Ftraining-and-configs\u002FSKILL.md) for training and configuration tasks:\n\n- Author\u002Fvalidate `TrainDecoderConfig` or `TrainDiffusionPriorConfig` JSON.\n- Use `DecoderTrainer` or `DiffusionPriorTrainer` directly.\n- Build `python` or `accelerate launch` commands, run bundled training wrappers, resume\u002Fsave trainer checkpoints, or debug `unet_training_mask`, resampling, DeepSpeed fp16, and config errors.\n\n### `data-and-tracking`\n\nRead [sub-skills\u002Fdata-and-tracking\u002FSKILL.md](sub-skills\u002Fdata-and-tracking\u002FSKILL.md) for data and experiment-management tasks:\n\n- Validate decoder WebDataset shard names, sample keys, sidecar image\u002Ftext embedding folders, `shard_width`, or `index_width`.\n- Use `ImageEmbeddingDataset`, `create_image_embedding_dataloader`, `get_reader`, `make_splits`, or `PriorEmbeddingDataset`.\n- Configure console\u002FW&B logging, local\u002FURL\u002FW&B checkpoint loading, or local\u002FW&B\u002FHuggingFace saving.\n\n## Important Constraints\n\n- Real training and useful image sampling normally need GPU memory and trained checkpoints. CPU is suitable for imports, config parsing, CLI help, and tiny synthetic forward-loss tests.\n- CLIP adapters (`OpenAIClipAdapter`, `OpenClipAdapter`) may download weights and require network\u002Fcache. Do not instantiate them in offline smoke checks unless weights are already cached.\n- Training examples may need datasets, W&B\u002FHuggingFace\u002FS3 credentials, metric assets, and long runtime. Validate configs and data layout before launch.\n- The `dream` CLI expects a combined DALLE2 checkpoint with package-expected init\u002Fmodel keys; trainer checkpoints are a different format.\n- If `clip-anytorch` fails because `pkg_resources` is missing, install `setuptools\u003C81` and rerun `python -m pip check`.\n\n## Root References\n\n- Repository snapshot and refresh baseline: [references\u002Frepo-provenance.md](references\u002Frepo-provenance.md).\n- Cross-cutting install\u002Fimport\u002Fbackend troubleshooting: [references\u002Ftroubleshooting.md](references\u002Ftroubleshooting.md).\n- Router metadata used by managed import: [references\u002Frepo-routing-metadata.json](references\u002Frepo-routing-metadata.json).\n\n## Self-Containment Rule\n\nUse the bundled references and scripts in this skill tree. Do not require future agents to open, run, or copy scripts, docs, configs, tests, or examples from an original DALLE2-pytorch checkout. When a user wants to train in a checkout intentionally, treat that checkout as their working project, not as this skill's required evidence source.\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\u002Fdalle2-pytorch",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 dalle2-pytorch",{"tool":41,"command":42},"bunx","bunx skills add lza6\u002FArmor-piercing-system-prompts --skill dalle2-pytorch",{"tool":44,"command":45},"pnpm","pnpm dlx skills add lza6\u002FArmor-piercing-system-prompts --skill dalle2-pytorch","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\u002Fdalle2-pytorch\u002FSKILL.md",[48,54,58],{"path":49,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":52,"sourceHtmlUrl":53},"references\u002Frepo-provenance.md","REFERENCE","参考文档",2202,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fdalle2-pytorch\u002Freferences\u002Frepo-provenance.md",{"path":55,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":56,"sourceHtmlUrl":57},"references\u002Frepo-routing-metadata.json",421,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fdalle2-pytorch\u002Freferences\u002Frepo-routing-metadata.json",{"path":59,"resourceType":50,"resourceTypeDesc":51,"sizeBytes":60,"sourceHtmlUrl":61},"references\u002Ftroubleshooting.md",3215,"https:\u002F\u002Fgithub.com\u002Flza6\u002FArmor-piercing-system-prompts\u002Fblob\u002Fmain\u002F06-前端与设计\u002Fdalle2-pytorch\u002Freferences\u002Ftroubleshooting.md",[63,70,75,82,89,96],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"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":71,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":72,"categories":73,"keywords":74,"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":76,"name":77,"nameZh":6,"description":78,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":79,"categories":80,"keywords":81,"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":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":88,"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":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":93,"categories":94,"keywords":95,"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":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":102,"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",[],[]]