GitLab

Lower peak memory usage when changing model.

Fix case where model weights would be unloaded and reloaded.

* FIX recursive_will_execute performance

* Minimize code changes

* memo must be created outside lambda

I think message describes them better.

A POST request to /free with: {"unload_models":true}
will unload models from vram.

A POST request to /free with: {"free_memory":true}
will unload models and free all cached data from the last run workflow.

Allow VALIDATE_INPUTS to only validate specific inputs.

Try to keep models on the vram when possible.

Better lowvram mode for controlnets.

If the same node id with the same class exists between two executions the
same instance will be used.

This means you can now cache things in nodes for more efficiency.

"node_errors" contains a dict keyed by node ids. The contents are a message
and a list of dependent outputs.