Load cached encoder before downloading remaining model

Stage persistent model components before local loading

Split persistent text encoder and runtime model caches

Persist Hugging Face model cache in mounted bucket

Process full uploaded video duration at 24 fps

Lazy-load gated LTX LoRAs with token diagnostics

Use mounted data bucket for render history

Add multi-effect LTX workflow

Switch backend to native LTX-2 (ICLoraPipeline) (#2)

metadata: point models: to the official Lightricks LoRA repo (fix model-card backlink)

Upload README.md with huggingface_hub

initial commit