InvokeAI

custom_nodes

fix(nodes): gracefully handle custom nodes init error

2024-04-02 13:25:14 +11:00

__init__.py

fix(config): remove unnecessary resolve on config path

2024-03-19 09:24:28 +11:00

baseinvocation.py

feat(app): dynamic type adapters for invocations & outputs

2024-05-30 12:03:38 +10:00

blend_latents.py

Move BlendLatentsInvocation to its own file. No functional changes.

2024-06-07 09:28:42 -04:00

collections.py

fix(nodes): restore type annotations for InvocationContext

2024-03-01 10:42:33 +11:00

compel.py

LoRA patching optimization (#6439 )

2024-06-06 13:53:35 +00:00

constants.py

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.

2024-06-14 11:26:10 -07:00

controlnet_image_processors.py

replace load_and_cache_model() with load_remote_model() and load_local_odel()

2024-06-07 14:12:16 +10:00

create_denoise_mask.py

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.

2024-06-14 11:26:10 -07:00

create_gradient_mask.py

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.

2024-06-14 11:26:10 -07:00

crop_latents.py

Move CropLatentsCoreInvocation to its own file. No functional changes.

2024-06-07 09:28:42 -04:00

cv.py

chore: bump nodes versions

2024-03-20 10:28:07 +11:00

denoise_latents.py

Revert "Remove the redundant init_timestep parameter that was being passed around. It is simply the first element of the timesteps array."

2024-06-26 12:51:51 -04:00

facetools.py

chore: bump nodes versions

2024-03-20 10:28:07 +11:00

fields.py

Rename MaskField to be a generice TensorField.

2024-04-09 08:12:12 -04:00

ideal_size.py

Move IdealSizeInvocation to its own file. No functional changes.

2024-06-07 09:28:42 -04:00

image_to_latents.py

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.

2024-06-14 11:26:10 -07:00

image.py

feat(nodes): use new blur_if_nsfw method

2024-05-14 07:23:38 +10:00

infill.py

replace load_and_cache_model() with load_remote_model() and load_local_odel()

2024-06-07 14:12:16 +10:00

ip_adapter.py

feat(nodes): make all ModelIdentifierField inputs accept connections

2024-05-19 20:14:01 +10:00

latents_to_image.py

Revert "Expose vae_decode(...) as a staticmethod on LatentsToImageInvocation."

2024-06-25 11:31:52 -07:00

mask.py

fix ruff

2024-06-03 11:41:47 -07:00

math.py

chore: bump nodes versions

2024-03-20 10:28:07 +11:00

metadata.py

tidy(nodes): move cnet mode literals to utils

2024-04-25 13:20:09 +10:00

model.py

feat(nodes): make ModelIdentifierInvocation a prototype

2024-05-19 20:14:01 +10:00

noise.py

[util] Add generic torch device class (#6174 )

2024-04-15 13:12:49 +00:00

param_easing.py

chore: bump nodes versions

2024-03-20 10:28:07 +11:00

primitives.py

Rename MaskField to be a generice TensorField.

2024-04-09 08:12:12 -04:00

prompt.py

chore: bump nodes versions

2024-03-20 10:28:07 +11:00

resize_latents.py

Move ScaleLatentsInvocation and ResizeLatentsInvocation to their own file. No functional changes.

2024-06-07 09:28:42 -04:00

scheduler.py

Move SchedulerInvocation to a new file. No functional changes.

2024-06-07 09:28:42 -04:00

sdxl.py

feat(nodes): make all ModelIdentifierField inputs accept connections

2024-05-19 20:14:01 +10:00

strings.py

chore: bump nodes versions

2024-03-20 10:28:07 +11:00

t2i_adapter.py

feat(nodes): make all ModelIdentifierField inputs accept connections

2024-05-19 20:14:01 +10:00

tiled_multi_diffusion_denoise_latents.py

Revert "Remove the redundant init_timestep parameter that was being passed around. It is simply the first element of the timesteps array."

2024-06-26 12:51:51 -04:00

tiles.py

chore: bump nodes versions

2024-03-20 10:28:07 +11:00

upscale.py

replace load_and_cache_model() with load_remote_model() and load_local_odel()

2024-06-07 14:12:16 +10:00

util.py

fix(nodes): fix constraints/validation for controlnet

2024-01-02 07:28:53 -05:00