1900e5119f
Fix potential issue.
6 months ago
09e069ae6c
Log the pytorch version.
6 months ago
11a2ad5110
Fix controlnet not upcasting on models that have it enabled.
6 months ago
0bdc2b15c7
Cleanup.
6 months ago
98f828fad9
Remove unnecessary code.
6 months ago
19300655dd
Don't automatically switch to lowvram mode on GPUs with low memory.
6 months ago
46daf0a9a7
Add debug options to force on and off attention upcasting.
6 months ago
2d41642716
Fix lowvram dora issue.
6 months ago
ec6f16adb6
Fix SAG.
6 months ago
bb4940d837
Only enable attention upcasting on models that actually need it.
6 months ago
b0ab31d06c
Refactor attention upcasting code part 1.
6 months ago
f509c6fe21
Fix Intel GPU memory allocation accuracy and documentation update. ( #3459 )
...
* Change calculation of memory total to be more accurate, allocated is actually smaller than reserved.
* Update README.md install documentation for Intel GPUs.
6 months ago
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.
6 months ago
49c20cdc70
No longer necessary.
6 months ago
e1489ad257
Fix issue with lowvram mode breaking model saving.
6 months ago
93e876a3be
Remove warnings that confuse people.
6 months ago
cd07340d96
Typo fix.
6 months ago
c61eadf69a
Make the load checkpoint with config function call the regular one.
...
I was going to completely remove this function because it is unmaintainable
but I think this is the best compromise.
The clip skip and v_prediction parts of the configs should still work but
not the fp16 vs fp32.
6 months ago
a56d02efc7
Change torch.xpu to ipex.optimize, xpu device initialization and remove workaround for text node issue from older IPEX. ( #3388 )
7 months ago
f81a6fade8
Fix some edge cases with samplers and arrays with a single sigma.
7 months ago
2aed53c4ac
Workaround xformers bug.
7 months ago
bacce529fb
Add TLS Support ( #3312 )
...
* Add TLS Support
* Add to readme
* Add guidance for windows users on generating certificates
* Add guidance for windows users on generating certificates
* Fix typo
7 months ago
7990ae18c1
Fix error when more cond masks passed in than batch size ( #3353 )
7 months ago
8dc19e40d1
Don't init a VAE model when there are no VAE weights.
7 months ago
c59fe9f254
Support VAE without quant_conv.
7 months ago
719fb2c81d
Add basic PAG node.
7 months ago
258dbc06c3
Fix some memory related issues.
7 months ago
58812ab8ca
Support SDXS 512 model.
7 months ago
831511a1ee
Fix issue with sampling_settings persisting across models.
7 months ago
30abc324c2
Support properly saving CosXL checkpoints.
7 months ago
0a03009808
Fix issue with controlnet models getting loaded multiple times.
7 months ago
38ed2da2dd
Fix typo in lowvram patcher ( #3209 )
8 months ago
1088d1850f
Support for CosXL models.
8 months ago
41ed7e85ea
Fix object_patches_backup not being the same object across clones.
8 months ago
0f5768e038
Fix missing arguments in cfg_function.
8 months ago
1f4fc9ea0c
Fix issue with get_model_object on patched model.
8 months ago
1a0486bb96
Fix model needing to be loaded on GPU to generate the sigmas.
8 months ago
c6bd456c45
Make zero denoise a NOP.
8 months ago
fcfd2bdf8a
Small cleanup.
8 months ago
0542088ef8
Refactor sampler code for more advanced sampler nodes part 2.
8 months ago
57753c964a
Refactor sampling code for more advanced sampler nodes.
8 months ago
6c6a39251f
Fix saving text encoder in fp8.
8 months ago
e6482fbbfc
Refactor calc_cond_uncond_batch into calc_cond_batch.
...
calc_cond_batch can take an arbitrary amount of cond inputs.
Added a calc_cond_uncond_batch wrapper with a warning so custom nodes
won't break.
8 months ago
575acb69e4
IP2P model loading support.
...
This is the code to load the model and inference it with only a text
prompt. This commit does not contain the nodes to properly use it with an
image input.
This supports both the original SD1 instructpix2pix model and the
diffusers SDXL one.
8 months ago
94a5a67c32
Cleanup to support different types of inpaint models.
8 months ago
5d8898c056
Fix some performance issues with weight loading and unloading.
...
Lower peak memory usage when changing model.
Fix case where model weights would be unloaded and reloaded.
8 months ago
327ca1313d
Support SDXS 0.9
8 months ago
ae77590b4e
dora_scale support for lora file.
8 months ago
c6de09b02e
Optimize memory unload strategy for more optimized performance.
8 months ago
0624838237
Add inverse noise scaling function.
8 months ago
comfyanonymous
Simon Lui
Garrett Sutula
Jedrzej Kosinski
kk-89