复制安装命令
用 Codex 或 Claude 安装复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它先审查 Skill 页面再帮你安装。
复制前请先查看来源、License 和安全提示。
SkillAtlasSkill 详情
paidf-augmentation
Official, NVIDIA-verified Agent Skills for Claude Code, Codex, and other coding agents.
审核状态：已审核Quality 72Security 70
项目 README
来源文件：README.md
NVIDIA Agent Skills
Official, NVIDIA-verified Agent Skills for Claude Code, Codex, and other coding agents.
📖 Docs: docs.nvidia.com/skills · 📺 Livestream: From Vulnerable to Verified · 📝 Blog: NVIDIA Verified Agent Skills: Capability Governance for AI Agents
Skills are portable instruction sets that teach AI agents how to use NVIDIA software optimally: Physical AI and robotics workflows, simulation, CUDA-X libraries, RAG and AI Blueprints, and platform tools. This repository is a catalog: skills are maintained in their respective product repos, and mirrored here daily via an automated sync pipeline. Skills are being added continuously, so check back for updates. We are building this infrastructure in the open, and contributions are welcome. See the Roadmap for what is planned next.
Quickstart
Install NVIDIA skills with the default skills CLI flow:
npx skills add nvidia/skills
The CLI runs through npx and prompts you to choose a skill and install destination. You do not need to clone this repo or copy skill folders by hand.
Requires a current
skillsCLI (v1.5.16 or newer). Installing vianpx skills@latest add nvidia/skillsalways uses the latest. On older CLIs (v1.5.15 and earlier), skills may install but not appear in Claude Code — see Troubleshooting.
The skill is available the next time your agent loads skills and encounters a relevant task. For example, ask your agent to "solve a linear programming problem with cuOpt" and the skill guides it through the cuOpt Python API. In Claude Code, run /reload-skills to load newly installed skills in your current session.
Install One Skill Without Prompts
Use this when you already know the skill name and want to skip prompts.
npx skills add nvidia/skills --skill cuopt-numerical-optimization-api --yes
Replace cuopt-numerical-optimization-api with any skill name from the Skill Catalog.
Install for a Specific Agent
Use --agent to target a specific AI coding agent. Initially, we'll support common client targets, expanding the list over time. For the full list of clients supported by the spec, see the skills CLI Supported Agents table.
Claude Code
npx skills add nvidia/skills --skill cuopt-numerical-optimization-api --agent claude-code
Codex
npx skills add nvidia/skills --skill cuopt-numerical-optimization-api --agent codex
Snowflake CoCo
npx skills add nvidia/skills --skill cuopt-numerical-optimization-api --agent cortex
Cursor
npx skills add nvidia/skills --skill cuopt-numerical-optimization-api --agent cursor
Kiro
npx skills add nvidia/skills --skill cuopt-numerical-optimization-api --agent kiro-cli
Use --agent more than once to install the same skill into multiple agents.
npx skills add nvidia/skills \
--skill cuopt-numerical-optimization-api \
--agent claude-code \
--agent codex \
--agent cursor \
--agent kiro-cli
Keep Skills Up to Date
New skills land continuously, and existing ones are revised, renamed, or consolidated as the catalog evolves. Refresh what you have installed with:
npx skills update
Run it interactively and the CLI also flags skills that were removed or merged upstream (for example, when several skills are consolidated into one) and offers to remove the stale local copies. Use npx skills list to see what is installed and npx skills check to preview what is out of date first.
Browse the Catalog
Use this when you want to see available NVIDIA skills before installing anything.
npx skills add nvidia/skills --list
For non-interactive installs, global installs, agent-specific installs, updates, removals, and fallback manual copying, see Advanced installation.
Skill Catalog
Getting Help & Contributing
Where to file an issue depends on what's broken:
- Skill content issues (a specific skill has a bug, missing functionality, or incorrect content) — file in the source repo for that product, using the per-product table below.
- Catalog issues (catalog README errors, sync workflow problems, distribution channels, signing/verification flow, docs in this repo) — file here using the catalog issue templates: Bug Report, Feature Request, or Documentation Request or Correction.
- Questions or general discussion — use Discussions. The issue tracker is reserved for bug reports, feature proposals with a design, and documentation issues.
- Security vulnerabilities — follow the disclosure process in SECURITY.md; do not open a public issue.
Per-product source repo links:
For issues with this catalog repo itself (README, structure, listing a new product): open an issue here.
Verifying Skills
Every published skill ships with a detached OMS signature (skill.oms.sig). The sync pipeline drops any skill missing the required artifacts before publishing, so every skill in the catalog carries:
SKILL.md— the skill instructions consumed by the agentskill-card.md— skill identity and governance cardskill.oms.sig— detached OMS signature (verifiable againstnv-agent-root-cert.pem)- A Tier-3 evaluation dataset — accepted at
evals/evals.json,evals/*.json,eval/*.json, orbenchmark/evals.json BENCHMARK.md— generated benchmark report capturing verifiable uplift data
Verify a skill against the NVIDIA trust anchor nv-agent-root-cert.pem:
pip install model-signing
model_signing verify certificate SKILL_DIR \
--signature SKILL_DIR/skill.oms.sig \
--certificate_chain nv-agent-root-cert.pem \
--ignore_unsigned_files
A successful verification confirms that the skill contents have not been modified since signing by NVIDIA.
See Verify Signed Agent Skills for signature layout, the trust pipeline, and policy options.
Roadmap
- ✅ Public skills catalog with NVIDIA-verified skills across multiple products
- ✅ Automated sync pipeline with skills mirrored from product repos daily
- ✅ Security scanning for all published skills covering instruction safety and supply-chain integrity
- ✅ Skills signing so every published skill carries a verifiable NVIDIA signature
- ✅ Skills universal evaluation criteria and task-specific criteria
- ✅ Skill Card with machine-readable metadata for identity, provenance, quality, and behavioral boundaries
- ✅ Sync-time compliance gates — signature drift detection and missing-artifact enforcement
- ✅ Syndication to external marketplaces — Skills.sh, Codex plugin, Claude Code plugin, ClawHub, Hermes Hub
- 🔲 Syndication to additional MCP hubs and partner channels
Repository Structure
NVIDIA/skills/
├── skills/ # NVIDIA-verified skills (count grows continuously),
│ │ synced from upstream product repos
│ ├── README.md # Browser-facing install guidance
│ ├── <product-prefix>-*/ # Flat layout — one dir per skill, product-prefixed
│ │ # e.g. aiq-*, cuopt-*, cupynumeric-*,
│ │ # dali-*, deepstream-*, dicom-*, digital-health-*,
│ │ # dynamo-*, earth2studio-*, holoscan-*, hsb-*,
│ │ # jetson-*, launch-nemo-rl, mcore-*,
│ │ # nemo-automodel-*, nemo-data-designer-plugin,
│ │ # nemo-evaluator-plugin, nemo-mbridge-* (20 skills),
│ │ # nemo-retriever, nemo-rl-* (4 skills),
│ │ # nemoclaw-user-guide, nemotron-*, nemotron-speech,
│ │ # nv-* (medical AI), physicsnemo-*, rag-*,
│ │ # skill-card-generator, tao-*, tilegym-*,
│ │ # vss-* (15 skills), accelerated-computing-cudf,
│ │ # cudaq-guide, portfolio-optimization
│ ├── omniverse-*/ # Physical AI — manually staged (see manual-components.yml)
│ └── physical-ai-*/ # Physical AI — manually staged
├── components.d/ # Product registry — one file per component, teams onboard here
│ ├── README.md # Schema and onboarding instructions
│ └── <product>.yml # one file per registered product
├── plugins/ # Packaged plugin distributions
│ └── nvidia-skills/ # Curated NVIDIA skills bundle (Claude Code, Codex)
├── plugins.d/ # Plugin build registry — config for `build-plugins.py`
│ ├── README.md
│ ├── _defaults.yml
│ └── nvidia-skills.yml
├── .claude-plugin/ # Claude Code marketplace metadata
│ └── marketplace.json
├── .agents/plugins/ # Agent marketplace metadata (other clients)
│ └── marketplace.json
├── docs/ # Long-form documentation (published via Fern)
│ ├── README.md # How to build the docs locally
│ ├── index.mdx
│ ├── advanced-install.mdx
│ ├── agent-skill-trust-pipeline.mdx
│ ├── release-checklist.mdx
│ ├── scanning-agent-skills.mdx
│ ├── signing-agent-skills.mdx
│ └── skill-cards.mdx
├── fern/ # Fern docs site configuration
├── .github/
│ ├── workflows/ # Sync pipeline, plugin validation, DCO check, author verify
│ └── scripts/ # regenerate-readme.sh, build-plugins.py,
│ # manual-components.yml (temp Physical AI catalog
│ # exception, removed after Computex 2026),
│ # marketplace/metadata.json (skill metadata sidecar)
├── nv-agent-root-cert.pem # Trust anchor for OMS signature verification
├── skills.sh.json # Skills.sh marketplace grouping config
├── CHANGELOG.md
├── CONTRIBUTING.md # Contribution guidelines
├── SECURITY.md # Security reporting policy
├── CODE_OF_CONDUCT.md # Community code of conduct
├── LICENSE-APACHE # Apache 2.0 (source code)
└── LICENSE-CC-BY-4.0 # CC BY 4.0 (documentation/skills)
Skills are maintained in their respective product repos (see the Source column in the Skill Catalog) and synced to this repo daily. Products only appear under skills/ after the sync pipeline confirms each skill carries:
skill.oms.sig— detached OMS-format signature (verifiable againstnv-agent-root-cert.pem)skill-card.md— skill identity and governance card- A Tier-3 evaluation dataset — accepted at
evals/evals.json,evals/*.json,eval/*.json, orbenchmark/evals.json
When evaluation runs produce a BENCHMARK.md, it ships alongside the skill so consumers can see verifiable benchmark uplift data.
Standards & Compatibility
This repository adheres to the Agent Skills specification:
- Skills are portable directories with a
SKILL.mdfile at their root. - Metadata uses YAML frontmatter with required
nameanddescriptionfields. - Skills follow a progressive disclosure model — lightweight metadata loads at startup, full instructions load on activation.
- Validate your skill using the
skills-refreference library.
License
Copyright (c) 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
This code is dual-licensed with documentation/skills under the CC-BY-4.0 AND source code under Apache-2.0 license terms. The full license texts can be found in LICENSE-APACHE and LICENSE-CC-BY-4.0 respectively.
其他
中风险
- 来源需自行核对维护者身份。
- 包含脚本或命令调用，安装前请复核。
- 可能需要外部 token、网络权限或第三方服务。
- 未检测到高风险命令。
- 扫描发现：2 条。
Codex — Git Clone 安装
- 安装前请先查看来源仓库和风险报告。
- 克隆仓库：git clone https://github.com/NVIDIA/skills.git
- 将 "skills/paidf-augmentation" 文件夹复制到 Codex 的 skills 目录中。
- 重启 Codex 让新的 skill 生效。
Codex — 手动复制安装
- 安装前请先查看来源仓库和风险报告。
- 从源仓库下载 SKILL.md 及相关文件。
- 在 Codex 的 skills 目录中创建新文件夹。
- 将所有 skill 文件复制到新文件夹中。
- 重启 Codex 让新的 skill 生效。
Claude Code — Git Clone 安装
- 安装前请先查看来源仓库和风险报告。
- 克隆仓库：git clone https://github.com/NVIDIA/skills.git
- 将 "skills/paidf-augmentation" 文件夹复制到 Claude Code 的 skills 目录中。
- 重启 Claude Code 让新的 skill 生效。
Claude Code — 手动复制安装
- 安装前请先查看来源仓库和风险报告。
- 从源仓库下载 SKILL.md 及相关文件。
- 在 Claude Code 的 skills 目录中创建新文件夹。
- 将所有 skill 文件复制到新文件夹中。
- 重启 Claude Code 让新的 skill 生效。
Cursor — Git Clone 安装
- 安装前请先查看来源仓库和风险报告。
- 克隆仓库：git clone https://github.com/NVIDIA/skills.git
- 将 "skills/paidf-augmentation" 文件夹复制到 Cursor 的 skills 目录中。
- 重启 Cursor 让新的 skill 生效。
Cursor — 手动复制安装
- 安装前请先查看来源仓库和风险报告。
- 从源仓库下载 SKILL.md 及相关文件。
- 在 Cursor 的 skills 目录中创建新文件夹。
- 将所有 skill 文件复制到新文件夹中。
- 重启 Cursor 让新的 skill 生效。
GitHub Copilot — Git Clone 安装
- 安装前请先查看来源仓库和风险报告。
- 克隆仓库：git clone https://github.com/NVIDIA/skills.git
- 将 "skills/paidf-augmentation" 文件夹复制到 GitHub Copilot 的 skills 目录中。
- 重启 GitHub Copilot 让新的 skill 生效。
GitHub Copilot — 手动复制安装
- 安装前请先查看来源仓库和风险报告。
- 从源仓库下载 SKILL.md 及相关文件。
- 在 GitHub Copilot 的 skills 目录中创建新文件夹。
- 将所有 skill 文件复制到新文件夹中。
- 重启 GitHub Copilot 让新的 skill 生效。
Windsurf — Git Clone 安装
- 安装前请先查看来源仓库和风险报告。
- 克隆仓库：git clone https://github.com/NVIDIA/skills.git
- 将 "skills/paidf-augmentation" 文件夹复制到 Windsurf 的 skills 目录中。
- 重启 Windsurf 让新的 skill 生效。
Windsurf — 手动复制安装
- 安装前请先查看来源仓库和风险报告。
- 从源仓库下载 SKILL.md 及相关文件。
- 在 Windsurf 的 skills 目录中创建新文件夹。
- 将所有 skill 文件复制到新文件夹中。
- 重启 Windsurf 让新的 skill 生效。
查看 SKILL.md 原文
name: paidf-augmentation
description: >-
Use when authoring or validating PAIDF augmentation YAML configs, or running
remote Cosmos Transfer/Predict, image-edit, or image-to-video inference.
license: Apache-2.0
metadata:
owner: NVIDIA
service: physical-ai-data-factory
version: 1.1.0
reviewed: '2026-08-31'
author: NVIDIA
tags:
- physical-ai
- augmentation
- cosmos
- image-editPAIDF Augmentation Pipeline Skill
Unified pipeline for augmenting camera data through NVIDIA generative AI models with automated captioning, generation, and quality evaluation. BYOM (bring-your-own-model): every model is reached over a remote HTTP endpoint described by one entry in the config's endpoints: list; adding a model is usually a config change, not code.
Purpose
Use this skill to drive the PAIDF augmentation pipeline end to end:
- Select the right model — Cosmos Transfer 2.5 (transform a video), Cosmos Predict 2.5 (generate/extend video), image-edit (edit an image), or image-to-video (animate a first frame: Cosmos3 or Veo 3.1).
- Author and validate YAML configs against the
PipelineConfigPydantic schema. - Configure captioning (VLM, LLM, deterministic VLM-template, text, or file) and evaluators (hallucination check, attribute verification, VLM verification).
- Launch and run inference inside the
paidf-augmentation:1.1.0Docker container (remote-API only — no local model weights).
Use this skill when running inference, authoring or editing configs, debugging validation or runtime errors, adding data samples, configuring captioning, tuning generation parameters, registering BYOM endpoints/adapters, or setting up evaluators. Trigger keywords: augmentation, cosmos transfer, cosmos predict, image edit, image-to-video, veo, image attribute augmentation, defect image generation, captioning, attribute verification, config validation.
Do not use this skill for training or fine-tuning models, deploying clusters or NIM endpoints, or unrelated application/database development.
Prerequisites
| Requirement | Detail |
|---|---|
| Docker | docker --version. The image is remote-API only — it bundles no Cosmos/torch weights, so plain remote inference needs no GPU and no HF_TOKEN. |
| NVIDIA GPU (conditional) | Only for the data_processing.alignment post-processor (cupy) and H.264 decode (evaluators, data_processing.transcode). See Limitations. |
| Endpoint URLs | One reachable URL per role the config uses: the model role (video_transfer/video_predict/image_edit/image2video) plus vlm/llm for captioning and evaluation. Defaults are local Qwen vLLM servers (Qwen/Qwen3.6-27B-FP8 on vlm, Qwen/Qwen2.5-14B-Instruct on llm). If the user has none running, ask for URLs. |
| API keys (conditional) | Only for endpoints requiring auth. Passed by env var named in each endpoint's api_key_env — never hardcoded in YAML. Common: VLM_API_KEY, LLM_API_KEY, VEO_API_KEY, BUILD_NVIDIA_API_KEY. Local endpoints need none. |
| Input media | A video (transfer/predict) or image (edit/image2video) reachable by multistorageclient — local path, s3://, gs://, az://, or HTTP. |
Inputs
Resolve each value in this precedence order: state file → explicit prompt arguments → agent context → user prompt. Ask the user only for what remains unresolved.
| Input | Required | Description |
|---|---|---|
config_path | Yes | Path to the pipeline YAML, e.g. configs/cookbook/video-data-augmentation/config_video_transfer_CT25_nim.yaml. If absent, pick a starting config from Supported Models and confirm with the user. |
input_media | Yes | Source video/image → data[].inputs.rgb. Overridable at run time via data.0.inputs.rgb=.... |
output_paths | Yes | data[].output.{video,caption,metadata}; evaluation optional. |
model_name | Yes | augmentation.model.name — an endpoint id, a role, or a known model name. Free-form string, not an enum. |
endpoint_urls | Yes | One endpoints[] entry per role in use. |
api_key_env | If auth | Env-var name per endpoint; the value comes from the environment. |
target_attributes | No | captioning.llm.variables (e.g. weather_condition, lighting_condition). |
generation_params | No | augmentation.parameters — pass-through; only set knobs are sent. |
seed | No | Under augmentation.parameters; null = random, re-rolled on retry. |
BYOM model: endpoints, adapters, roles
The pipeline never embeds an SDK per model. Instead:
endpoints:is a list. Each entry hasrole,url,model(the wire model string), an optionalid(only to disambiguate 2+ endpoints sharing a role), an optionaladapter(API contract; defaults from the role),api_key_env, andtimeout.- Roles:
vlm,llm(captioning + evaluators),image_edit,video_transfer(Cosmos Transfer),video_predict(Cosmos Predict),image2video(Cosmos3 / Veo). - Adapters (API contracts):
openai.chat.completions,openai.images.edits,openai.video.sync,openai.video.async,nim,passthrough. The same model can be served over different contracts by changing only the endpoint'sadapterfield. - Model selection:
augmentation.model.nameresolves to an endpoint byid, else byrole, else by the model-name→role map (image-edit→image_edit,cosmos-transfer2.5→video_transfer,cosmos-predict→video_predict,cosmos3-image2video→image2video).
Supported Models
When the user hasn't specified a model, choose from their input type and goal:
| Input Type → Goal | model.name | Role / default adapter | Input → Output |
|---|---|---|---|
| Video — change scene attributes (weather, lighting, style) | cosmos-transfer2.5 | video_transfer / nim | Video (+ controls) → Video |
| Video + text — extend or predict continuation | cosmos-predict | video_predict / nim | Video+Text → Video |
| Text only — generate video from scratch | cosmos-predict (inference_type: text2world) | video_predict / nim | Text → Video |
| Image — edit specific attributes | image-edit | image_edit / nim (or openai.chat.completions, openai.images.edits) | Image → Image |
| Image — animate a first frame | cosmos3-image2video (or your Veo endpoint id) | image2video / openai.video.sync (Veo: openai.video.async) | Image + prompt → Video |
Key rule: video in + scene-attribute change → Cosmos Transfer. Generate new video from text/image/video conditioning → Cosmos Predict. Single image edit → image edit. Still image → moving clip → image-to-video.
All models run via remote HTTP through one BaseExecutor; there is no local torchrun and no executor_type field.
Usage
Step 1: Launch the Docker Container
Set PAIDF_IMAGE_ID to the immutable sha256: image ID recorded from the
trusted local build (or supplied in trusted release metadata). The image ID is
build- and architecture-specific, so this repository cannot provide one
universal value. Verify that the mutable convenience tag still resolves to the
expected ID, then run the ID directly:
set -e
PAIDF_IMAGE_ID="sha256:<expected-image-id>"
test "$(docker image inspect --format '{{.Id}}' paidf-augmentation:1.1.0)" = "$PAIDF_IMAGE_ID"
docker network inspect paidf >/dev/null 2>&1 || \
docker network create paidf
docker run -it --rm \
--network paidf \
-v "$(pwd)/modules:/workspace/modules" \
-v "$(pwd)/configs:/workspace/configs" \
-v "$(pwd)/data:/workspace/data" \
--entrypoint /bin/bash \
"$PAIDF_IMAGE_ID"
Do not derive PAIDF_IMAGE_ID from the tag and immediately trust it; compare
the tag against the digest recorded when the image was built or published. If
a registry release provides a signed manifest, verify that signature before
pulling and use its name:tag@sha256:<manifest-digest> reference instead.
- Networking: augmentation only makes outbound requests, so it needs no
-p/--publishports. Keep the sharedpaidfbridge shown above for remote endpoints. For another model container, attach it to the same bridge and use its container name in the endpoint URL. Run host-local models in a container on that bridge, or use a remote endpoint; do not grant the augmentation container access to the host network. - API keys: prefer a platform secrets manager that injects the required
environment variables. Otherwise, export only the required keys and forward
their names with
-e VAR_NAME; never mount or load a broad credential file. - No GPU needed for remote inference — add
--gpusfordata_processing.alignmentand any H.264 decode; pick a GPU not shared with a busy model server. Container runs as uid 10000; ensuredata/is writable (or--user "$(id -u):$(id -g)").
Security: Host networking is prohibited for this workflow, especially when API keys are present. Review pipeline-operations.md.
Step 2: Run the Pipeline (Inside the Container)
uv run --no-sync modules/cli.py --config configs/<config_file>.yaml
# With OmegaConf CLI overrides (dot-list syntax)
uv run --no-sync modules/cli.py --config configs/cookbook/video-data-augmentation/config_video_transfer_CT25_nim.yaml \
data.0.inputs.rgb=/workspace/data/input.mp4 \
augmentation.parameters.seed=42
Environment variables: keys resolve as the api_key_env var → the role's default env var. If api_key_env names an unset var, resolution falls back to the role default; leave it off for unauthenticated endpoints. LOG_LEVEL sets logging.
Configuration Schema
Configs are validated against PipelineConfig (modules/aug_utils/schema/) and have seven top-level sections: data, endpoints (a list), pipeline, captioning, augmentation, data_processing, and evaluators. Full per-section YAML is in configuration-schema.md; runtime flow and common editing tasks are in pipeline-operations.md.
Examples
Configs live under
configs/cookbook/<use-case>/. See the cookbook index for the folder layout.
| Use case | Config(s) |
|---|---|
Video scene-attribute transfer (CT2.5, nim) | config_video_transfer_CT25_nim.yaml |
| Image → video | config_image2video_cosmos3.yaml (VLM→LLM) · config_image2video_cosmos3_vlm_template.yaml (VLM→template) · config_image2video_veo31.yaml (Veo 3.1, async) |
| Image Attribute Augmentation | config_image_edit_attribute_{chat_api,images_api,nim}.yaml · …_gemma_llm.yaml (hosted-Gemma LLM swap) |
| Defect Image Generation + MI alignment | config_image_edit_defect_{chat_api,images_api}.yaml |
| Batch config generation | workflow_example.yaml · attribute_distribution_1000_v1.yaml |
| Smart-space seed image / event video | config_seed_image_gen_cosmos3_super_t2i_smart_spaces.yaml · config_event_video_gen_cosmos3_smart_spaces.yaml |
Per-config captioning / evaluator / adapter details are in config-decision-tree.md.
Troubleshooting
Run all inference and schema validation inside the Docker container for a consistent environment. For config-validation errors, runtime/endpoint errors, and typical per-stage timings, see troubleshooting.md.
Limitations
- Remote inference only. All models run behind remote HTTP endpoints; no local weights, no
torchrun, noexecutor_type, no Gradio executor. - GPU for alignment and H.264 decode. Remote inference needs no GPU. A CUDA GPU is required by
data_processing.alignment(cupy) and by anything decoding H.264 — the evaluators anddata_processing.transcode— because the image ships only the hardwareh264_cuviddecoder (software AVC decode is off for licensing). VP9 decodes in software. Video output is VP9-only. - Inference only. This pipeline augments and generates media — it does not train or fine-tune models.
- Auth varies by endpoint. Hosted endpoints (e.g. Veo) need a key via
api_key_env; local endpoints (e.g. vLLM) need none.
Reference files
- configuration-schema.md — full per-section YAML for every config section.
- config-decision-tree.md — which config to start from, model/captioning selection, alignment override rules.
- pipeline-operations.md — pipeline flow, worked example, common tasks, storage, security notes.
- captioning-strategy-guide.md — all 6 captioning modes with complete YAML.
- evaluator-setup-guide.md — hallucination tuning, attribute verification, MCQ wiring.
- troubleshooting.md — validation/runtime errors and per-stage timings.
- image-attribute-augmentation.md — Image Attribute Augmentation image-edit workflow and dataset packaging.
- event-video-gen.md — smart-space image-to-video event generation.
评论 (0)
暂无评论，成为第一个评论者吧！