Integrate a model into flashdreams

The ordered procedure for binding an external video model to the flashdreams framework. Read the flashdreams-integrations skill first for the architecture (layers, contracts, the cache tree) — this skill is the route, that one is the map.

Reference examples: integrations_v2/wan22/ for the Wan 2.2 TI2V-5B recipe and checkpoint remap, and integrations_v2/lingbot/ for camera conditioning. Read them side-by-side. Match python-docstring-style.

The core bet: reuse, don't re-implement

Most modern video models are DiT-family. Before writing anything, find the closest existing flashdreams recipe (integrations_v2/wan22, wan21, self_forcing, …) and subclass it. Keep model-specific conditioner deltas in small subclasses. If your model maps onto an existing backbone, the job is config + checkpoint remap + deltas + verify, which is days–weeks. If it needs a novel network/attention/inference loop, it is much longer — say so up front.