psychedelicious eb33303e79 fix(mm): handle depth and inpainting models when converting to diffusers ...

"Normal" models have 4 in-channels, while "Depth" models have 5 and "Inpaint" models have 9.

We need to explicitly tell diffusers the channel count when converting models.

Closes  #6058

2024-03-27 07:48:54 -04:00

..

__init__.py

model loading and conversion implemented for vaes

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

controlnet.py

allow checkpoint config files to use root-relative paths

2024-03-22 08:57:45 +11:00

generic_diffusers.py

record model_variant in t2i and clip_vision configs (#5989)

2024-03-19 20:14:12 +00:00

ip_adapter.py

fix(mm): misc typing fixes for model loaders

2024-03-05 23:50:19 +11:00

lora.py

tidy(nodes): use canonical capitalizations

2024-03-07 10:56:59 +11:00

onnx.py

tidy(mm): use canonical capitalization for all model-related enums, classes

2024-03-05 23:50:19 +11:00

stable_diffusion.py

fix(mm): handle depth and inpainting models when converting to diffusers

2024-03-27 07:48:54 -04:00

textual_inversion.py

chore: ruff

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

vae.py

allow checkpoint config files to use root-relative paths

2024-03-22 08:57:45 +11:00