InvokeAI/invokeai/backend
2024-04-09 10:57:02 -04:00
..
image_util feat(nodes): redo tile infill 2024-04-05 08:49:13 +11:00
ip_adapter Create a UNetAttentionPatcher for patching UNet models with CustomAttnProcessor2_0 modules. 2024-04-09 08:12:12 -04:00
model_hash feat(mm): rename "blake3" to "blake3_multi" 2024-03-22 08:26:36 +11:00
model_manager feat(backend): clean up choose_precision 2024-04-07 09:41:05 -04:00
onnx final tidying before marking PR as ready for review 2024-03-01 10:42:33 +11:00
stable_diffusion Remove support for Prompt-to-Prompt cross-attention control (aka .swap()). This feature is not widely used. It does not work with SDXL and is incompatible with IP-Adapter and regional prompting. The implementation is also intertwined with both text embedding and the UNet attention layers, resulting in a high maintenance burden. For all of these reasons, we have decided to drop support. 2024-04-09 10:57:02 -04:00
tiles feat(nodes): extract LATENT_SCALE_FACTOR to constants.py 2024-03-01 10:42:33 +11:00
util Add utility to_standard_float_mask(...) to convert various mask formats to a standardized format. 2024-04-09 08:12:12 -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 chore: ruff 2024-03-01 10:42:33 +11:00
raw_model.py final tidying before marking PR as ready for review 2024-03-01 10:42:33 +11:00
textual_inversion.py final tidying before marking PR as ready for review 2024-03-01 10:42:33 +11:00