psychedelicious 615eddea6f feat(nodes): add PiDiNetEdgeDetectionInvocation ...

Similar to the existing node, but without any resizing and with a revised model loading API that uses the model manager.

All code related to the invocation now lives in the Invoke repo.

2024-09-11 08:12:48 -04:00

..

flux

Update latents used for preview images in flux

2024-09-03 14:04:16 -04:00

image_util

feat(nodes): add PiDiNetEdgeDetectionInvocation

2024-09-11 08:12:48 -04:00

ip_adapter

fix(backend): revert non-blocking device transfer

2024-07-16 08:59:42 +10:00

model_hash

Run ruff

2024-06-26 21:46:59 +10:00

model_manager

Simplify flux model dtype conversion in model loader

2024-09-05 15:47:14 -04:00

onnx

fix(backend): revert non-blocking device transfer

2024-07-16 08:59:42 +10:00

quantization

Fix bug in InvokeLinear8bitLt that was causing old state information to persist after loading from a state dict. This manifested as state tensors being left on the GPU even when a model had been offloaded to the CPU cache.

2024-08-29 19:08:18 +00:00

stable_diffusion

Tidy variable management and dtype handling in FluxTextToImageInvocation.

2024-08-29 19:08:18 +00:00

tiles

feat(nodes): extract LATENT_SCALE_FACTOR to constants.py

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

util

Tidy up GIG -> GB and remove unused GIG constant.

2024-08-29 19:08:18 +00:00

__init__.py

consolidate model manager parts into a single class

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

lora.py

Remove tmp code

2024-08-07 22:06:05 -04:00

model_patcher.py

Optimize weights handling

2024-07-30 03:39:01 +03:00

raw_model.py

Merge branch 'main' into ryan/spandrel-upscale

2024-07-16 15:14:08 -04:00

spandrel_image_to_image_model.py

Add tiling support to the SpoandrelImageToImage node.

2024-07-10 14:25:19 -04:00

textual_inversion.py

fix(backend): revert non-blocking device transfer

2024-07-16 08:59:42 +10:00