InvokeAI/backend at 03b9d17d0b312722c11a07e97c0c4362de930e18 - InvokeAI - Z's Git Repo

Mirrored_Repos/InvokeAI

mirror of https://github.com/invoke-ai/InvokeAI synced 2024-08-30 20:32:17 +00:00

History

Lincoln Stein 03b9d17d0b draft sd3 loading; probable VRAM leak when using quantized submodels

2024-06-13 00:51:00 -04:00

..

Merge branch 'main' into lstein/feat/simple-mm2-api

2024-05-17 22:54:03 -04:00

Create a UNetAttentionPatcher for patching UNet models with CustomAttnProcessor2_0 modules.

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

feat(mm): rename "blake3" to "blake3_multi"

2024-03-22 08:26:36 +11:00

draft sd3 loading; probable VRAM leak when using quantized submodels

2024-06-13 00:51:00 -04:00

final tidying before marking PR as ready for review

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

stable_diffusion

cleanup: seamless unused older code cleanup

2024-05-13 08:11:08 +10:00

feat(nodes): extract LATENT_SCALE_FACTOR to constants.py

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

add draft SD3 probing; there is an issue with FromOriginalControlNetMixin in backend.util.hotfixes due to new diffusers

2024-06-12 22:44:34 -04:00

__init__.py

consolidate model manager parts into a single class

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

lora.py

final tidying before marking PR as ready for review

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

model_patcher.py

LoRA patching optimization (#6439 )

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

raw_model.py

final tidying before marking PR as ready for review

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

textual_inversion.py

Add a callout about the hackiness of dropping tokens in the TextualInversionManager.

2024-05-28 05:11:54 -07:00