domains / families / data / paidf-augmentation

paidf-augmentation

separate

Use when authoring or validating PAIDF augmentation YAML configs, or running remote Cosmos Transfer (including Cosmos3 WSM controls), Cosmos Predict, image-edit, or image-to-video inference.

When to use

• Use it to select a supported generation mode, author and validate `PipelineConfig` YAML, configure captioning/evaluators, and run the `paidf-augmentation:1.2.0` container. It covers Cosmos Transfer/Predict, Cosmos3 WSM controls, image edit…

When not to use

• **Remote inference only.** All models run behind remote HTTP endpoints; no local weights, no `torchrun`, no `executor_type`, no Gradio executor.
• **GPU for configured local stages.** Remote inference needs no augmentation-container GPU. A CUDA GPU is required by `data_processing.alignment` (cupy) and by any local stage decoding H.264 because the image ships only the hardware `h264_c…
• **External-evaluator media must be remote.** When an external evaluator is enabled, schema validation rejects local `data[].inputs.rgb`, control media, generated `data[].output.video`, and configured companion media. Use checker-readable `…
• **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.

Skill page

Source