InvokeAI/invokeai/backend
psychedelicious 04d8f2dfea fix(backend): fix controlnet zip len
Do not use `strict=True` when scaling controlnet conditioning.

When using `guess_mode` (e.g. `more_control` or `more_prompt`), `down_block_res_samples` and `scales` are zipped.

These two objects are of different lengths, so using zip's strict mode raises an error.

In testing, `len(scales) === len(down_block_res_samples) + 1`.

It appears this behaviour is intentional, as the final "extra" item in `scales` is used immediately afterwards.
2023-11-13 15:45:03 +11:00
..
image_util chore: ruff check - fix pycodestyle 2023-11-11 10:55:33 +11:00
install chore: ruff format 2023-11-11 10:55:40 +11:00
ip_adapter chore: ruff format 2023-11-11 10:55:40 +11:00
model_management chore: ruff format 2023-11-11 10:55:40 +11:00
stable_diffusion chore: ruff format 2023-11-11 10:55:40 +11:00
training chore: ruff check - fix flake8-comprensions 2023-11-11 10:55:23 +11:00
util fix(backend): fix controlnet zip len 2023-11-13 15:45:03 +11:00
__init__.py isort wip 2 2023-09-12 13:01:58 -04:00