Ryan Dick
|
56731766ca
|
Update FluxControlnetModel to work with both XLabs and InstantX.
|
2024-10-09 14:17:42 +00:00 |
|
Ryan Dick
|
80bc4ebee3
|
Add unit test to test the full flow of loading an InstantX ControlNet from a state dict.
|
2024-10-09 14:17:42 +00:00 |
|
Ryan Dick
|
c7628945c4
|
Add unit test for infer_flux_params_from_state_dict(...).
|
2024-10-09 14:17:42 +00:00 |
|
Ryan Dick
|
2cd14dd066
|
First pass of utility function to infer the FluxParams from a state dict.
|
2024-10-09 14:17:42 +00:00 |
|
Ryan Dick
|
5872f05342
|
Add unit test for convert_diffusers_instantx_state_dict_to_bfl_format(...) and fix a few bugs.
|
2024-10-09 14:17:42 +00:00 |
|
Ryan Dick
|
4ad135c6ae
|
Finish first draft of convert_diffusers_instantx_state_dict_to_bfl_format(...).
|
2024-10-09 14:17:42 +00:00 |
|
Ryan Dick
|
c72c2770fe
|
WIP - implement convert_diffusers_instantx_state_dict_to_bfl_format(...).
|
2024-10-09 14:17:42 +00:00 |
|
Ryan Dick
|
e733a1f30e
|
(minor) rename other_forward() -> forward()
|
2024-10-09 14:17:42 +00:00 |
|
Ryan Dick
|
4be3a33744
|
Add utils for detecting XLabs ControlNet vs. InstantX ControlNet from
state dict.
|
2024-10-09 14:17:42 +00:00 |
|
Ryan Dick
|
1751c380db
|
Migrate DiffusersControlNetFlux from diffusers-style to BFL-style.
|
2024-10-09 14:17:42 +00:00 |
|
Ryan Dick
|
16cda33025
|
Improve typing of zero_module().
|
2024-10-09 14:17:42 +00:00 |
|
Ryan Dick
|
8308e7d186
|
Use top-level torch import for all torch stuff.
|
2024-10-09 14:17:42 +00:00 |
|
Ryan Dick
|
c0aab56d08
|
Remove DiffusersControlNetFlux.from_transformer(...).
|
2024-10-09 14:17:42 +00:00 |
|
Ryan Dick
|
1795f4f8a2
|
Fixup typing around DiffusersControlNetFluxOutput.
|
2024-10-09 14:17:42 +00:00 |
|
Ryan Dick
|
5bfd2ec6b7
|
Remove gradient checkpointing from DiffusersControlNetFlux.
|
2024-10-09 14:17:42 +00:00 |
|
Ryan Dick
|
a35b229a9d
|
Remove FluxMultiControlNetModel
|
2024-10-09 14:17:42 +00:00 |
|
Ryan Dick
|
e93da5d4b2
|
Remove LoRA stuff from DiffusersCotnrolNetFlux.
|
2024-10-09 14:17:42 +00:00 |
|
Ryan Dick
|
a17ea9bfad
|
Remove logic for modifying attn processors from DiffusersControlNetFlux.
|
2024-10-09 14:17:42 +00:00 |
|
Ryan Dick
|
3578010ba4
|
Rename FluxControlNetModel -> DiffusersControlNetFlux
|
2024-10-09 14:17:42 +00:00 |
|
Ryan Dick
|
459cf52043
|
Start updating imports for FluxControlNetModel
|
2024-10-09 14:17:42 +00:00 |
|
Ryan Dick
|
9bcb93f575
|
Copy model from 99f608218c/src/diffusers/models/controlnet_flux.py
|
2024-10-09 14:17:42 +00:00 |
|
Ryan Dick
|
d1a0e99701
|
Rename ControlNetFlux -> XLabsControlNetFlux
|
2024-10-09 14:17:42 +00:00 |
|
Ryan Dick
|
36515e1e2a
|
Add support for FLUX controlnet weight, begin_step_percent and end_step_percent.
|
2024-10-09 14:17:42 +00:00 |
|
Ryan Dick
|
c81bb761ed
|
First pass at integrating FLUX ControlNets into the FLUX Denoise invocation.
|
2024-10-09 14:17:42 +00:00 |
|
Ryan Dick
|
1d4a58e52b
|
Add FLUX XLabs ControlNet model probing.
|
2024-10-09 14:17:42 +00:00 |
|
Ryan Dick
|
62d12e6468
|
Fix type errors and imporve docs for ControlNetFlux.
|
2024-10-09 14:17:41 +00:00 |
|
Ryan Dick
|
9541156ce5
|
Remove gradient checkpointing from ControlNetFlux.
|
2024-10-09 14:17:41 +00:00 |
|
Ryan Dick
|
eb5b6625ea
|
Remove ControlNetFlux logic related to attn processor overrides.
|
2024-10-09 14:17:41 +00:00 |
|
Ryan Dick
|
9758e5a622
|
Remove duplicate FluxParams class.
|
2024-10-09 14:17:41 +00:00 |
|
Ryan Dick
|
58eba8bdbd
|
Fix FLUX module imports for ControlNetFlux.
|
2024-10-09 14:17:41 +00:00 |
|
Ryan Dick
|
2821ba8967
|
Copy ControlNetFlux model from 47495425db/src/flux/controlnet.py.
|
2024-10-09 14:17:41 +00:00 |
|
Kent Keirsey
|
969f8b8e8d
|
ruff update
|
2024-10-08 08:56:26 -04:00 |
|
David Burnett
|
ccb5f90556
|
Get Flux working on MPS when torch 2.5.0 test or nightlies are installed.
|
2024-10-08 08:56:26 -04:00 |
|
Ryan Dick
|
3d4bd71098
|
Update test_probe_handles_state_dict_with_integer_keys() to make sure that it is still testing what it's intended to test. Previously, we were skipping an important part of the test by using a fake file path.
|
2024-10-02 18:33:05 -04:00 |
|
Brandon Rising
|
814be44cd7
|
Ignore paths that don't exist in probe for unit tests
|
2024-10-02 18:33:05 -04:00 |
|
Brandon Rising
|
d328eaf743
|
Remove no longer used dequantize_tensor function
|
2024-10-02 18:33:05 -04:00 |
|
Brandon Rising
|
0f333388bb
|
Add comment describing why we're not using the meta device during probing of gguf files
|
2024-10-02 18:33:05 -04:00 |
|
Ryan Dick
|
bc63e2acc5
|
Add workaround for FLUX GGUF models with incorrect img_in.weight shape.
|
2024-10-02 18:33:05 -04:00 |
|
Ryan Dick
|
ec7e771942
|
Add a compute_dtype field to GGMLTensor.
|
2024-10-02 18:33:05 -04:00 |
|
Ryan Dick
|
fe84013392
|
Add unit tests for GGMLTensor.
|
2024-10-02 18:33:05 -04:00 |
|
Ryan Dick
|
710f81266b
|
Fix type errors in GGMLTensor.
|
2024-10-02 18:33:05 -04:00 |
|
Brandon Rising
|
446e2884bc
|
Remove no longer used code paths, general cleanup of new dequantization code, update probe
|
2024-10-02 18:33:05 -04:00 |
|
Brandon Rising
|
7d9f125232
|
Run ruff and update imports
|
2024-10-02 18:33:05 -04:00 |
|
Brandon Rising
|
66bbd62758
|
Run ruff and fix typing in torch patcher
|
2024-10-02 18:33:05 -04:00 |
|
Brandon Rising
|
0875e861f5
|
Various updates to gguf performance
|
2024-10-02 18:33:05 -04:00 |
|
Brandon
|
0267d73dfc
|
Update invokeai/backend/model_manager/load/model_loaders/flux.py
Co-authored-by: Ryan Dick <ryanjdick3@gmail.com>
|
2024-10-02 18:33:05 -04:00 |
|
Ryan Dick
|
f06765dfba
|
Get alternative GGUF implementation working... barely.
|
2024-10-02 18:33:05 -04:00 |
|
Ryan Dick
|
f347b26999
|
Initial experimentation with Tensor-like extension for GGUF.
|
2024-10-02 18:33:05 -04:00 |
|
Lincoln Stein
|
c665cf3525
|
recognize .gguf files when scanning a folder for import
|
2024-10-02 18:33:05 -04:00 |
|
Brandon Rising
|
2bfb0ddff5
|
Initial GGUF support for flux models
|
2024-10-02 18:33:05 -04:00 |
|