InvokeAI/invokeai/app/invocations/constants.py

from typing import Literal

from invokeai.backend.util.devices import TorchDevice

LATENT_SCALE_FACTOR = 8
"""
HACK: Many nodes are currently hard-coded to use a fixed latent scale factor of 8. This is fragile, and will need to
be addressed if future models use a different latent scale factor. Also, note that there may be places where the scale
factor is hard-coded to a literal '8' rather than using this constant.
The ratio of image:latent dimensions is LATENT_SCALE_FACTOR:1, or 8:1.
"""

IMAGE_MODES = Literal["L", "RGB", "RGBA", "CMYK", "YCbCr", "LAB", "HSV", "I", "F"]
"""A literal type for PIL image modes supported by Invoke"""

DEFAULT_PRECISION = TorchDevice.choose_torch_dtype()
chore(nodes): "SAMPLER_NAME_VALUES" -> "SCHEDULER_NAME_VALUES" This was named inaccurately. 2024-02-10 22:51:25 +00:00			`from typing import Literal`

Fix all comparisons against the DEFAULT_PRECISION constant. DEFAULT_PRECISION is a torch.dtype. Previously, it was compared to a str in a number of places where it would always resolve to False. This is a bugfix that results in a change to the default behavior. In practice, this will not change the behavior for many users, because it only causes a change in behavior if a users has configured float32 as their default precision. 2024-06-06 13:16:45 +00:00			`from invokeai.backend.util.devices import TorchDevice`
chore(nodes): "SAMPLER_NAME_VALUES" -> "SCHEDULER_NAME_VALUES" This was named inaccurately. 2024-02-10 22:51:25 +00:00
feat(nodes): extract LATENT_SCALE_FACTOR to constants.py 2024-02-10 21:52:07 +00:00			`LATENT_SCALE_FACTOR = 8`
			`"""`
			`HACK: Many nodes are currently hard-coded to use a fixed latent scale factor of 8. This is fragile, and will need to`
			`be addressed if future models use a different latent scale factor. Also, note that there may be places where the scale`
			`factor is hard-coded to a literal '8' rather than using this constant.`
			`The ratio of image:latent dimensions is LATENT_SCALE_FACTOR:1, or 8:1.`
			`"""`
chore(nodes): "SAMPLER_NAME_VALUES" -> "SCHEDULER_NAME_VALUES" This was named inaccurately. 2024-02-10 22:51:25 +00:00
chore(invocations): use IMAGE_MODES constant literal 2024-02-18 21:56:46 +00:00			`IMAGE_MODES = Literal["L", "RGB", "RGBA", "CMYK", "YCbCr", "LAB", "HSV", "I", "F"]`
chore: ruff formatting 2024-02-19 04:11:36 +00:00			`"""A literal type for PIL image modes supported by Invoke"""`
Fix all comparisons against the DEFAULT_PRECISION constant. DEFAULT_PRECISION is a torch.dtype. Previously, it was compared to a str in a number of places where it would always resolve to False. This is a bugfix that results in a change to the default behavior. In practice, this will not change the behavior for many users, because it only causes a change in behavior if a users has configured float32 as their default precision. 2024-06-06 13:16:45 +00:00
			`DEFAULT_PRECISION = TorchDevice.choose_torch_dtype()`