[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M78Y8YB7FTB1MXM4PYV4RZH2":3,"skill-same:01M78Y8YB7FTB1MXM4PYV4RZH2":70},{"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},"01M78Y8YB7FTB1MXM4PYV4RZH2","data-and-text-conditioning",null,"Prepare Imagen-Pytorch image folders, Hugging Face dataset items, collators, and T5 or precomputed text conditioning inputs.","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\u002Fimagen-pytorch\u002Fsub-skills\u002Fdata-and-text-conditioning\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: data-and-text-conditioning\ndescription: \"Prepare Imagen-Pytorch image folders, Hugging Face dataset items,\n  collators, and T5 or precomputed text conditioning inputs.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: MIT\n---\n\n# Data and Text Conditioning\n\nUse this sub-skill for the preprocessing path that turns local image collections or Hugging Face rows into Imagen-ready batches and text-conditioning inputs.\n\n## Owns\n- Local image-folder validation for unconditional training.\n- `Dataset(folder, image_size, exts, convert_image_to_type)` and `get_images_dataloader(...)`.\n- `Collator(image_size, url_label, text_label, image_label, name, channels)` and its URL\u002Fimage\u002Ftext row handling.\n- Raw texts, `text_embeds`, `text_masks`, and image-channel conversion for Imagen \u002F ImagenTrainer.\n- Shape and mode checks for precomputed text conditioning.\n\n## Route elsewhere\n- Training loop, optimizers, EMA, checkpoints, and `train_step`: [`..\u002Ftraining-and-checkpointing\u002FSKILL.md`](..\u002Ftraining-and-checkpointing\u002FSKILL.md)\n- Config files and CLI flags: [`..\u002Fconfiguration-and-cli\u002FSKILL.md`](..\u002Fconfiguration-and-cli\u002FSKILL.md)\n- Image generation and sampling APIs: [`..\u002Fimage-generation\u002FSKILL.md`](..\u002Fimage-generation\u002FSKILL.md)\n- Video and inpainting sampling APIs: [`..\u002Fvideo-and-inpainting\u002FSKILL.md`](..\u002Fvideo-and-inpainting\u002FSKILL.md)\n\n## Short workflow\n1. Identify the input path: local folder, HF row schema, or precomputed text tensors.\n2. Check the folder or tensor metadata with the bundled scripts:\n   - [`scripts\u002Fcheck_image_folder.py`](scripts\u002Fcheck_image_folder.py)\n   - [`scripts\u002Ftext_embedding_shape_check.py`](scripts\u002Ftext_embedding_shape_check.py)\n3. For local folders, use `Dataset(...)` or `get_images_dataloader(...)` to produce image-only batches.\n4. For HF rows, use `Collator(...)` to produce image tensors and encoded text tensors.\n5. For text conditioning, choose raw texts or precomputed `text_embeds` \u002F `text_masks` and verify the shapes before training.\n6. Hand the validated batches to the training or sampling sub-skill.\n\n## Key contracts\n- The local-folder path is image-only.\n- The collator path can download URLs, skip failing rows, and return `None` if every row in a batch fails.\n- Trainer dataloaders are consumed by keyword order, so tuple layout must match the configured output names.\n- T5 text handling truncates at 256 tokens and uses the configured T5 model name.\n- Channel conversion must match the requested `channels` value and the input image modes.\n\n## References\n- [`references\u002Fdata-formats.md`](references\u002Fdata-formats.md)\n- [`references\u002Ftext-conditioning.md`](references\u002Ftext-conditioning.md)\n- [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md)\n","# Data and Text Conditioning\n\nUse this sub-skill for the preprocessing path that turns local image collections or Hugging Face rows into Imagen-ready batches and text-conditioning inputs.\n\n## Owns\n- Local image-folder validation for unconditional training.\n- `Dataset(folder, image_size, exts, convert_image_to_type)` and `get_images_dataloader(...)`.\n- `Collator(image_size, url_label, text_label, image_label, name, channels)` and its URL\u002Fimage\u002Ftext row handling.\n- Raw texts, `text_embeds`, `text_masks`, and image-channel conversion for Imagen \u002F ImagenTrainer.\n- Shape and mode checks for precomputed text conditioning.\n\n## Route elsewhere\n- Training loop, optimizers, EMA, checkpoints, and `train_step`: [`..\u002Ftraining-and-checkpointing\u002FSKILL.md`](..\u002Ftraining-and-checkpointing\u002FSKILL.md)\n- Config files and CLI flags: [`..\u002Fconfiguration-and-cli\u002FSKILL.md`](..\u002Fconfiguration-and-cli\u002FSKILL.md)\n- Image generation and sampling APIs: [`..\u002Fimage-generation\u002FSKILL.md`](..\u002Fimage-generation\u002FSKILL.md)\n- Video and inpainting sampling APIs: [`..\u002Fvideo-and-inpainting\u002FSKILL.md`](..\u002Fvideo-and-inpainting\u002FSKILL.md)\n\n## Short workflow\n1. Identify the input path: local folder, HF row schema, or precomputed text tensors.\n2. Check the folder or tensor metadata with the bundled scripts:\n   - [`scripts\u002Fcheck_image_folder.py`](scripts\u002Fcheck_image_folder.py)\n   - [`scripts\u002Ftext_embedding_shape_check.py`](scripts\u002Ftext_embedding_shape_check.py)\n3. For local folders, use `Dataset(...)` or `get_images_dataloader(...)` to produce image-only batches.\n4. For HF rows, use `Collator(...)` to produce image tensors and encoded text tensors.\n5. For text conditioning, choose raw texts or precomputed `text_embeds` \u002F `text_masks` and verify the shapes before training.\n6. Hand the validated batches to the training or sampling sub-skill.\n\n## Key contracts\n- The local-folder path is image-only.\n- The collator path can download URLs, skip failing rows, and return `None` if every row in a batch fails.\n- Trainer dataloaders are consumed by keyword order, so tuple layout must match the configured output names.\n- T5 text handling truncates at 256 tokens and uses the configured T5 model name.\n- Channel conversion must match the requested `channels` value and the input image modes.\n\n## References\n- [`references\u002Fdata-formats.md`](references\u002Fdata-formats.md)\n- [`references\u002Ftext-conditioning.md`](references\u002Ftext-conditioning.md)\n- [`references\u002Ftroubleshooting.md`](references\u002Ftroubleshooting.md)\n",{"name":5,"license":14,"metadata":23,"description":7,"disable-model-invocation":25},{"disco-role":24},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fimagen-pytorch\u002Fsub-skills\u002Fdata-and-text-conditioning",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 data-and-text-conditioning",{"tool":39,"command":40},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill data-and-text-conditioning",{"tool":42,"command":43},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill data-and-text-conditioning","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fimagen-pytorch\u002Fsub-skills\u002Fdata-and-text-conditioning\u002FSKILL.md",[46,52,56,60,66],{"path":47,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":50,"sourceHtmlUrl":51},"references\u002Fdata-formats.md","REFERENCE","参考文档",2334,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fimagen-pytorch\u002Fsub-skills\u002Fdata-and-text-conditioning\u002Freferences\u002Fdata-formats.md",{"path":53,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":54,"sourceHtmlUrl":55},"references\u002Ftext-conditioning.md",1841,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fimagen-pytorch\u002Fsub-skills\u002Fdata-and-text-conditioning\u002Freferences\u002Ftext-conditioning.md",{"path":57,"resourceType":48,"resourceTypeDesc":49,"sizeBytes":58,"sourceHtmlUrl":59},"references\u002Ftroubleshooting.md",2121,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fimagen-pytorch\u002Fsub-skills\u002Fdata-and-text-conditioning\u002Freferences\u002Ftroubleshooting.md",{"path":61,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":64,"sourceHtmlUrl":65},"scripts\u002Fcheck_image_folder.py","SCRIPT","脚本",5883,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fimagen-pytorch\u002Fsub-skills\u002Fdata-and-text-conditioning\u002Fscripts\u002Fcheck_image_folder.py",{"path":67,"resourceType":62,"resourceTypeDesc":63,"sizeBytes":68,"sourceHtmlUrl":69},"scripts\u002Ftext_embedding_shape_check.py",5830,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fimagen-pytorch\u002Fsub-skills\u002Fdata-and-text-conditioning\u002Fscripts\u002Ftext_embedding_shape_check.py",[71,79,86,93,100,107],{"skillNo":72,"name":73,"nameZh":6,"description":74,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"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":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"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":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"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":94,"name":95,"nameZh":6,"description":96,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":97,"categories":98,"keywords":99,"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":101,"name":102,"nameZh":6,"description":103,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":104,"categories":105,"keywords":106,"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":108,"name":109,"nameZh":6,"description":110,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":75,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"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",[],[]]