comfyanonymous
|
2ca8f6e23d
|
Make the stochastic fp8 rounding reproducible.
|
6 months ago |
|
comfyanonymous
|
c6812947e9
|
Fix potential memory leak.
|
6 months ago |
|
comfyanonymous
|
7df42b9a23
|
Fix dora.
|
6 months ago |
|
comfyanonymous
|
c26ca27207
|
Move calculate function to comfy.lora
|
6 months ago |
|
comfyanonymous
|
7c6bb84016
|
Code cleanups.
|
6 months ago |
|
comfyanonymous
|
4d341b78e8
|
Bug fixes.
|
6 months ago |
|
comfyanonymous
|
6138f92084
|
Use better dtype for the lowvram lora system.
|
6 months ago |
|
comfyanonymous
|
be0726c1ed
|
Remove duplication.
|
6 months ago |
|
comfyanonymous
|
20ace7c853
|
Code cleanup.
|
6 months ago |
|
comfyanonymous
|
bb222ceddb
|
Fix loras having a weak effect when applied on fp8.
|
6 months ago |
|
comfyanonymous
|
cd5017c1c9
|
calculate_weight function to use a different dtype.
|
6 months ago |
|
comfyanonymous
|
83f343146a
|
Fix potential lowvram issue.
|
6 months ago |
|
comfyanonymous
|
74e124f4d7
|
Fix some issues with TE being in lowvram mode.
|
6 months ago |
|
comfyanonymous
|
5d43e75e5b
|
Fix some issues with the model sometimes not getting patched.
|
6 months ago |
|
comfyanonymous
|
517f4a94e4
|
Fix some lora loading slowdowns.
|
6 months ago |
|
comfyanonymous
|
52a471c5c7
|
Change name of log.
|
7 months ago |
|
comfyanonymous
|
1de69fe4d5
|
Fix some issues with inference slowing down.
|
7 months ago |
|
comfyanonymous
|
6678d5cf65
|
Fix regression.
|
7 months ago |
|
comfyanonymous
|
a3cc326748
|
Better fix for lowvram issue.
|
7 months ago |
|
comfyanonymous
|
5acdadc9f3
|
Fix issue with some lowvram weights.
|
7 months ago |
|
comfyanonymous
|
1e11d2d1f5
|
Better prints.
|
7 months ago |
|
comfyanonymous
|
08f92d55e9
|
Partial model shift support.
|
7 months ago |
|
comfyanonymous
|
cb7c4b4be3
|
Workaround for lora OOM on lowvram mode.
|
7 months ago |
|
comfyanonymous
|
b334605a66
|
Fix OOMs happening in some cases.
A cloned model patcher sometimes reported a model was loaded on a device
when it wasn't.
|
7 months ago |
Extraltodeus
|
f1a01c2c7e
|
Add sampler_pre_cfg_function (#3979)
* Update samplers.py
* Update model_patcher.py
|
8 months ago |
|
comfyanonymous
|
73ca780019
|
Add SamplerEulerCFG++ node.
This node should match the DDIM implementation of CFG++ when "regular" is
selected.
"alternative" is a slightly different take on CFG++
|
8 months ago |
|
comfyanonymous
|
028a583bef
|
Fix issue with full diffusers SD3 loras.
|
8 months ago |
|
comfyanonymous
|
0e06b370db
|
Print key names for easier debugging.
|
8 months ago |
|
comfyanonymous
|
37a08a41b3
|
Support setting weight offsets in weight patcher.
|
8 months ago |
|
comfyanonymous
|
809cc85a8e
|
Remove useless code.
|
9 months ago |
|
comfyanonymous
|
ffc4b7c30e
|
Fix DORA strength.
This is a different version of #3298 with more correct behavior.
|
9 months ago |
|
comfyanonymous
|
efa5a711b2
|
Reduce memory usage when applying DORA: #3557
|
9 months ago |
Chenlei Hu
|
7718ada4ed
|
Add type annotation UnetWrapperFunction (#3531)
* Add type annotation UnetWrapperFunction
* nit
* Add types.py
|
9 months ago |
|
comfyanonymous
|
2d41642716
|
Fix lowvram dora issue.
|
9 months ago |
|
comfyanonymous
|
fa6dd7e5bb
|
Fix lowvram issue with saving checkpoints.
The previous fix didn't cover the case where the model was loaded in
lowvram mode right before.
|
10 months ago |
|
comfyanonymous
|
e1489ad257
|
Fix issue with lowvram mode breaking model saving.
|
10 months ago |
|
comfyanonymous
|
719fb2c81d
|
Add basic PAG node.
|
10 months ago |
kk-89
|
38ed2da2dd
|
Fix typo in lowvram patcher (#3209)
|
11 months ago |
|
comfyanonymous
|
41ed7e85ea
|
Fix object_patches_backup not being the same object across clones.
|
11 months ago |
|
comfyanonymous
|
1f4fc9ea0c
|
Fix issue with get_model_object on patched model.
|
11 months ago |
|
comfyanonymous
|
1a0486bb96
|
Fix model needing to be loaded on GPU to generate the sigmas.
|
11 months ago |
|
comfyanonymous
|
ae77590b4e
|
dora_scale support for lora file.
|
11 months ago |
|
comfyanonymous
|
c18a203a8a
|
Don't unload model weights for non weight patches.
|
11 months ago |
|
comfyanonymous
|
db8b59ecff
|
Lower memory usage for loras in lowvram mode at the cost of perf.
|
12 months ago |
|
comfyanonymous
|
65397ce601
|
Replace prints with logging and add --verbose argument.
|
12 months ago |
|
comfyanonymous
|
12c1080ebc
|
Simplify differential diffusion code.
|
12 months ago |
|
comfyanonymous
|
1abf8374ec
|
utils.set_attr can now be used to set any attribute.
The old set_attr has been renamed to set_attr_param.
|
12 months ago |
|
comfyanonymous
|
9f71e4b62d
|
Let model patches patch sub objects.
|
12 months ago |
|
comfyanonymous
|
ef4f6037cb
|
Fix model patches not working in custom sampling scheduler nodes.
|
1 year ago |
|
comfyanonymous
|
12e822c6c8
|
Use function to calculate model size in model patcher.
|
1 year ago |