[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M794S1AF8WRRV433RZXG05QR":3,"skill-same:01M794S1AF8WRRV433RZXG05QR":67},{"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":27,"commitSha":28,"skillDirectory":29,"forksCount":30,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":33,"install":34,"resources":46},"01M794S1AF8WRRV433RZXG05QR","generation",null,"Run and troubleshoot sd-scripts image generation and minimal inference CLIs, including txt2img, img2img, inpainting, prompt files, SDXL conditioning, LoRA\u002Fnetwork application, ControlNet\u002FLLLite, and model-family inference scripts.","VectorSpaceLab\u002FAREX-Skill","VectorSpaceLab","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F180637102?v=4","01M7538C5WPSJGWF7KHR4EFZ9F","01M7538C6R2GFP53NPXTCZNBRT",351,"Apache-2.0","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsd-scripts\u002Fsub-skills\u002Fgeneration\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: generation\ndescription: \"Run and troubleshoot sd-scripts image generation and minimal\n  inference CLIs, including txt2img, img2img, inpainting, prompt files, SDXL\n  conditioning, LoRA\u002Fnetwork application, ControlNet\u002FLLLite, and model-family\n  inference scripts.\"\ndisable-model-invocation: true\nmetadata:\n  disco-role: operating\nlicense: Apache 2.0\n---\n\n# sd-scripts Generation\n\nUse this sub-skill when the user wants to generate images, validate prompt files, apply trained LoRA weights during inference, or diagnose generation failures. For LoRA training route to `..\u002Ftraining`; for model merging\u002Fconversion route to `..\u002Fmodel-utilities`; for dataset TOML route to `..\u002Fdata-preparation`.\n\n## Choose the Entry Point\n\n- Use `gen_img.py` for SD 1.x, SD 2.x, SDXL, txt2img, img2img, inpainting-by-mask, prompt files, highres fix, LoRA networks, ControlNet, and ControlNet-LLLite.\n- Use `sdxl_gen_img.py` when you want the SDXL-focused script surface and the same prompt-file conventions.\n- Use `gen_img_diffusers.py` when the model is a Diffusers pipeline\u002Ffolder and the user wants Diffusers-style loading.\n- Use `inpainting_minimal_inference.py` for a small inpainting script with `--ckpt_path`, `--image`, `--mask`, and `--sdxl` rather than the broader `gen_img.py` interface.\n- Use family minimal inference scripts for newer architectures: `sdxl_minimal_inference.py`, `sd3_minimal_inference.py`, `flux_minimal_inference.py`, `lumina_minimal_inference.py`, `hunyuan_image_minimal_inference.py`, `anima_minimal_inference.py`, and `anima_minimal_inference_control_net_lllite.py`.\n\n## Fast Start Commands\n\nKeep commands model-path agnostic and replace placeholders with the user’s files:\n\n```bash\npython gen_img.py --ckpt \u003Cmodel.ckpt-or-safetensors-or-diffusers-id> --outdir outputs \\\n  --fp16 --xformers --W 512 --H 768 --steps 30 --sampler k_euler_a \\\n  --prompt \"masterpiece, detailed illustration --n low quality, blurry\"\n```\n\n```bash\npython gen_img.py --ckpt \u003Cmodel> --outdir outputs --bf16 --sdpa --no_preview \\\n  --from_file prompts.txt --images_per_prompt 4 --batch_size 2 --seed 1234\n```\n\n```bash\npython gen_img.py --ckpt \u003Csdxl-model> --sdxl --outdir outputs --bf16 --sdpa \\\n  --original_width 1024 --original_height 1024 --target_width 1024 --target_height 1024 \\\n  --prompt \"cinematic studio portrait --n distorted face\"\n```\n\nBefore running a batch, validate prompt-file syntax without loading models:\n\n```bash\npython skills\u002Fsd-scripts\u002Fsub-skills\u002Fgeneration\u002Fscripts\u002Fvalidate_prompt_file.py prompts.txt --family gen-img\n```\n\n## Required References\n\n- `references\u002Fcommands.md`: command templates for txt2img, img2img, inpainting, SDXL, LoRA, ControlNet, LLLite, and minimal inference scripts.\n- `references\u002Fprompt-formats.md`: prompt-file syntax, negative prompts, prompt weights, dynamic prompts, per-line options, and model-family differences.\n- `references\u002Ftroubleshooting.md`: diagnosis for model-family flags, path errors, headless preview, precision artifacts, xformers\u002FSDPA, OOM, LoRA count mismatch, ControlNet mismatches, and offline tokenizer cache.\n\n## Practical Workflow\n\n1. Identify the model family first: SD1\u002FSD2\u002FSDXL uses `gen_img.py`; SD3\u002FFlux\u002FLumina\u002FHunyuan\u002FAnima use family minimal inference scripts.\n2. Confirm required model components exist: checkpoint or DiT plus text encoders plus VAE\u002FAE as required by the selected script.\n3. Select precision and memory flags conservatively: start with `--fp16` or `--bf16`, reduce `--batch_size`, reduce resolution, then add VAE slicing\u002Foffload flags if needed.\n4. Validate prompt files with the bundled script; it catches malformed per-line options, missing values, invalid numeric fields, and likely LoRA multiplier count mistakes.\n5. If applying LoRA at inference, match each `--network_module` with a `--network_weights` entry for `gen_img.py`, or use the family script’s `--lora_weights`\u002F`--lora_weight` convention.\n6. For ControlNet\u002FLLLite, verify image, mask, and control dimensions and ensure ControlNet and LLLite are not mixed in one `gen_img.py` command.\n\n## Common Decisions\n\n- Prefer `--no_preview` on servers, containers, CI, SSH sessions, and any headless environment.\n- Prefer `--sdpa` on modern PyTorch when xformers is unavailable; use `--xformers` only when the package is installed and compatible.\n- For SD2 v-parameterized checkpoints, include both `--v2` and `--v_parameterization`; missing `--v_parameterization` can produce brown images.\n- For black images or NaNs, retry with `--bf16`, `--no_half_vae`, lower resolution, or fp32 depending on hardware support.\n- For prompt weighting, use WebUI-like `(term:1.2)`, `(term)`, and `[term]`; keep generation options separated with spaces, such as `prompt text --n bad anatomy --w 768`.\n","# sd-scripts Generation\n\nUse this sub-skill when the user wants to generate images, validate prompt files, apply trained LoRA weights during inference, or diagnose generation failures. For LoRA training route to `..\u002Ftraining`; for model merging\u002Fconversion route to `..\u002Fmodel-utilities`; for dataset TOML route to `..\u002Fdata-preparation`.\n\n## Choose the Entry Point\n\n- Use `gen_img.py` for SD 1.x, SD 2.x, SDXL, txt2img, img2img, inpainting-by-mask, prompt files, highres fix, LoRA networks, ControlNet, and ControlNet-LLLite.\n- Use `sdxl_gen_img.py` when you want the SDXL-focused script surface and the same prompt-file conventions.\n- Use `gen_img_diffusers.py` when the model is a Diffusers pipeline\u002Ffolder and the user wants Diffusers-style loading.\n- Use `inpainting_minimal_inference.py` for a small inpainting script with `--ckpt_path`, `--image`, `--mask`, and `--sdxl` rather than the broader `gen_img.py` interface.\n- Use family minimal inference scripts for newer architectures: `sdxl_minimal_inference.py`, `sd3_minimal_inference.py`, `flux_minimal_inference.py`, `lumina_minimal_inference.py`, `hunyuan_image_minimal_inference.py`, `anima_minimal_inference.py`, and `anima_minimal_inference_control_net_lllite.py`.\n\n## Fast Start Commands\n\nKeep commands model-path agnostic and replace placeholders with the user’s files:\n\n```bash\npython gen_img.py --ckpt \u003Cmodel.ckpt-or-safetensors-or-diffusers-id> --outdir outputs \\\n  --fp16 --xformers --W 512 --H 768 --steps 30 --sampler k_euler_a \\\n  --prompt \"masterpiece, detailed illustration --n low quality, blurry\"\n```\n\n```bash\npython gen_img.py --ckpt \u003Cmodel> --outdir outputs --bf16 --sdpa --no_preview \\\n  --from_file prompts.txt --images_per_prompt 4 --batch_size 2 --seed 1234\n```\n\n```bash\npython gen_img.py --ckpt \u003Csdxl-model> --sdxl --outdir outputs --bf16 --sdpa \\\n  --original_width 1024 --original_height 1024 --target_width 1024 --target_height 1024 \\\n  --prompt \"cinematic studio portrait --n distorted face\"\n```\n\nBefore running a batch, validate prompt-file syntax without loading models:\n\n```bash\npython skills\u002Fsd-scripts\u002Fsub-skills\u002Fgeneration\u002Fscripts\u002Fvalidate_prompt_file.py prompts.txt --family gen-img\n```\n\n## Required References\n\n- `references\u002Fcommands.md`: command templates for txt2img, img2img, inpainting, SDXL, LoRA, ControlNet, LLLite, and minimal inference scripts.\n- `references\u002Fprompt-formats.md`: prompt-file syntax, negative prompts, prompt weights, dynamic prompts, per-line options, and model-family differences.\n- `references\u002Ftroubleshooting.md`: diagnosis for model-family flags, path errors, headless preview, precision artifacts, xformers\u002FSDPA, OOM, LoRA count mismatch, ControlNet mismatches, and offline tokenizer cache.\n\n## Practical Workflow\n\n1. Identify the model family first: SD1\u002FSD2\u002FSDXL uses `gen_img.py`; SD3\u002FFlux\u002FLumina\u002FHunyuan\u002FAnima use family minimal inference scripts.\n2. Confirm required model components exist: checkpoint or DiT plus text encoders plus VAE\u002FAE as required by the selected script.\n3. Select precision and memory flags conservatively: start with `--fp16` or `--bf16`, reduce `--batch_size`, reduce resolution, then add VAE slicing\u002Foffload flags if needed.\n4. Validate prompt files with the bundled script; it catches malformed per-line options, missing values, invalid numeric fields, and likely LoRA multiplier count mistakes.\n5. If applying LoRA at inference, match each `--network_module` with a `--network_weights` entry for `gen_img.py`, or use the family script’s `--lora_weights`\u002F`--lora_weight` convention.\n6. For ControlNet\u002FLLLite, verify image, mask, and control dimensions and ensure ControlNet and LLLite are not mixed in one `gen_img.py` command.\n\n## Common Decisions\n\n- Prefer `--no_preview` on servers, containers, CI, SSH sessions, and any headless environment.\n- Prefer `--sdpa` on modern PyTorch when xformers is unavailable; use `--xformers` only when the package is installed and compatible.\n- For SD2 v-parameterized checkpoints, include both `--v2` and `--v_parameterization`; missing `--v_parameterization` can produce brown images.\n- For black images or NaNs, retry with `--bf16`, `--no_half_vae`, lower resolution, or fp32 depending on hardware support.\n- For prompt weighting, use WebUI-like `(term:1.2)`, `(term)`, and `[term]`; keep generation options separated with spaces, such as `prompt text --n bad anatomy --w 768`.\n",{"name":5,"license":23,"metadata":24,"description":7,"disable-model-invocation":26},"Apache 2.0",{"disco-role":25},"operating",true,"main","ac3fe1afa80fb9a09775ecfb2b6cc3ba850a2db6","skills\u002Frepositories\u002Frepo-skills\u002Fsd-scripts\u002Fsub-skills\u002Fgeneration",27,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill","https:\u002F\u002Fgithub.com\u002FVectorSpaceLab","2026-09-03 10:25:21",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":26},[36,39,42],{"tool":37,"command":38},"npx","npx skills add VectorSpaceLab\u002FAREX-Skill --skill generation",{"tool":40,"command":41},"bunx","bunx skills add VectorSpaceLab\u002FAREX-Skill --skill generation",{"tool":43,"command":44},"pnpm","pnpm dlx skills add VectorSpaceLab\u002FAREX-Skill --skill generation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsd-scripts\u002Fsub-skills\u002Fgeneration\u002FSKILL.md",[47,53,57,61],{"path":48,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":51,"sourceHtmlUrl":52},"references\u002Fcommands.md","REFERENCE","参考文档",9238,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsd-scripts\u002Fsub-skills\u002Fgeneration\u002Freferences\u002Fcommands.md",{"path":54,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":55,"sourceHtmlUrl":56},"references\u002Fprompt-formats.md",5252,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsd-scripts\u002Fsub-skills\u002Fgeneration\u002Freferences\u002Fprompt-formats.md",{"path":58,"resourceType":49,"resourceTypeDesc":50,"sizeBytes":59,"sourceHtmlUrl":60},"references\u002Ftroubleshooting.md",5826,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsd-scripts\u002Fsub-skills\u002Fgeneration\u002Freferences\u002Ftroubleshooting.md",{"path":62,"resourceType":63,"resourceTypeDesc":64,"sizeBytes":65,"sourceHtmlUrl":66},"scripts\u002Fvalidate_prompt_file.py","SCRIPT","脚本",7494,"https:\u002F\u002Fgithub.com\u002FVectorSpaceLab\u002FAREX-Skill\u002Fblob\u002Fmain\u002Fskills\u002Frepositories\u002Frepo-skills\u002Fsd-scripts\u002Fsub-skills\u002Fgeneration\u002Fscripts\u002Fvalidate_prompt_file.py",[68,75,82,89,96,103],{"skillNo":69,"name":70,"nameZh":6,"description":71,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"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.","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":14,"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":14,"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":14,"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":14,"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":14,"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",[],[]]