44947e7ad4
Add DEIS order 3 sampler.
...
Order 4 seems to give bad results.
8 months ago
69d710e40f
Implement my alternative take on CFG++ as the euler_pp sampler.
...
Add euler_ancestral_pp which is the ancestral version of euler with the
same modification.
8 months ago
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
2f360ae898
Support OneTrainer SD3 lora format.
8 months ago
4ef1479dcd
Multi dimension tiled scale function and tiled VAE audio encoding fallback.
8 months ago
1e2839f4d9
More proper tiled audio decoding.
8 months ago
d5efde89b7
Add ipndm_v sampler, works best with the exponential scheduler.
8 months ago
028a583bef
Fix issue with full diffusers SD3 loras.
8 months ago
0d6a57938e
Support loading diffusers SD3 model format with UNETLoader node.
8 months ago
b08a9dd04b
Remove empty line.
8 months ago
eee815ec99
Update sd1_clip.py ( #3684 )
...
Made token instance check more flexible so it also works with integers from numpy arrays or long tensors
8 months ago
e11052afcf
Add ipndm sampler.
8 months ago
3914d5a2ae
Support full SD3 loras.
8 months ago
a45df69570
Basic tiled decoding for audio VAE.
8 months ago
b7c473d1ab
Fix lora keys for SimpleTuner ( #3759 )
8 months ago
6425252c4f
Use fp16 as the default vae dtype for the audio VAE.
8 months ago
8ddc151a4c
Squash depreciation warning on new pytorch.
8 months ago
ca9d300a80
Better estimation for memory usage during audio VAE encoding/decoding.
8 months ago
746a0410d4
Fix VAEEncode with taesd3.
8 months ago
04e8798c37
Improvements to the TAESD3 implementation.
8 months ago
df7db0e027
support TAESD3 ( #3738 )
8 months ago
bb1969cab7
Initial support for the stable audio open model.
8 months ago
1281f933c1
Small optimization.
8 months ago
f2e844e054
Optimize some unneeded if conditions in the sampling code.
8 months ago
0ec513d877
Add a --force-channels-last to inference models in channel last mode.
8 months ago
0e06b370db
Print key names for easier debugging.
8 months ago
5eb98f0092
Exempt IPEX from non_blocking previews fixing segmentation faults. ( #3708 )
9 months ago
ac151ac169
Support SD3 diffusers lora.
9 months ago
37a08a41b3
Support setting weight offsets in weight patcher.
9 months ago
605e64f6d3
Fix lowvram issue.
9 months ago
1ddf512fdc
Don't auto convert clip and vae weights to fp16 when saving checkpoint.
9 months ago
694e0b48e0
SD3 better memory usage estimation.
9 months ago
69c8d6d8a6
Single and dual clip loader nodes support SD3.
...
You can use the CLIPLoader to use the t5xxl only or the DualCLIPLoader to
use CLIP-L and CLIP-G only for sd3.
9 months ago
0e49211a11
Load the SD3 T5xxl model in the same dtype stored in the checkpoint.
9 months ago
5889b7ca0a
Support multiple text encoder configurations on SD3.
9 months ago
9424522ead
Reuse code.
9 months ago
73ce178021
Remove redundancy in mmdit.py ( #3685 )
9 months ago
a82fae2375
Fix bug with cosxl edit model.
9 months ago
8c4a9befa7
SD3 Support.
9 months ago
a5e6a632f9
Support sampling non 2D latents.
9 months ago
742d5720d1
Support zeroing out text embeddings with the attention mask.
9 months ago
6cd8ffc465
Reshape the empty latent image to the right amount of channels if needed.
9 months ago
56333d4850
Use the end token for the text encoder attention mask.
9 months ago
104fcea0c8
Add function to get the list of currently loaded models.
9 months ago
b1fd26fe9e
pytorch xpu should be flash or mem efficient attention?
9 months ago
809cc85a8e
Remove useless code.
9 months ago
b249862080
Add an annoying print to a function I want to remove.
9 months ago
bf3e334d46
Disable non_blocking when --deterministic or directml.
9 months ago
b26da2245f
Fix UnetParams annotation typo ( #3589 )
9 months ago
0920e0e5fe
Remove some unused imports.
9 months ago
ffc4b7c30e
Fix DORA strength.
...
This is a different version of #3298 with more correct behavior.
9 months ago
efa5a711b2
Reduce memory usage when applying DORA: #3557
9 months ago
6c23854f54
Fix OSX latent2rgb previews.
9 months ago
7718ada4ed
Add type annotation UnetWrapperFunction ( #3531 )
...
* Add type annotation UnetWrapperFunction
* nit
* Add types.py
9 months ago
8508df2569
Work around black image bug on Mac 14.5 by forcing attention upcasting.
9 months ago
83d969e397
Disable xformers when tracing model.
9 months ago
1900e5119f
Fix potential issue.
9 months ago
09e069ae6c
Log the pytorch version.
9 months ago
11a2ad5110
Fix controlnet not upcasting on models that have it enabled.
9 months ago
0bdc2b15c7
Cleanup.
9 months ago
98f828fad9
Remove unnecessary code.
9 months ago
19300655dd
Don't automatically switch to lowvram mode on GPUs with low memory.
9 months ago
46daf0a9a7
Add debug options to force on and off attention upcasting.
9 months ago
2d41642716
Fix lowvram dora issue.
10 months ago
ec6f16adb6
Fix SAG.
10 months ago
bb4940d837
Only enable attention upcasting on models that actually need it.
10 months ago
b0ab31d06c
Refactor attention upcasting code part 1.
10 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.
10 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.
10 months ago
49c20cdc70
No longer necessary.
10 months ago
e1489ad257
Fix issue with lowvram mode breaking model saving.
10 months ago
93e876a3be
Remove warnings that confuse people.
10 months ago
cd07340d96
Typo fix.
10 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.
10 months ago
a56d02efc7
Change torch.xpu to ipex.optimize, xpu device initialization and remove workaround for text node issue from older IPEX. ( #3388 )
10 months ago
f81a6fade8
Fix some edge cases with samplers and arrays with a single sigma.
10 months ago
2aed53c4ac
Workaround xformers bug.
10 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
10 months ago
7990ae18c1
Fix error when more cond masks passed in than batch size ( #3353 )
10 months ago
8dc19e40d1
Don't init a VAE model when there are no VAE weights.
10 months ago
c59fe9f254
Support VAE without quant_conv.
10 months ago
719fb2c81d
Add basic PAG node.
11 months ago
258dbc06c3
Fix some memory related issues.
11 months ago
58812ab8ca
Support SDXS 512 model.
11 months ago
831511a1ee
Fix issue with sampling_settings persisting across models.
11 months ago
30abc324c2
Support properly saving CosXL checkpoints.
11 months ago
0a03009808
Fix issue with controlnet models getting loaded multiple times.
11 months ago
38ed2da2dd
Fix typo in lowvram patcher ( #3209 )
11 months ago
1088d1850f
Support for CosXL models.
11 months ago
41ed7e85ea
Fix object_patches_backup not being the same object across clones.
11 months ago
0f5768e038
Fix missing arguments in cfg_function.
11 months ago
1f4fc9ea0c
Fix issue with get_model_object on patched model.
11 months ago
1a0486bb96
Fix model needing to be loaded on GPU to generate the sigmas.
11 months ago
c6bd456c45
Make zero denoise a NOP.
11 months ago
fcfd2bdf8a
Small cleanup.
11 months ago
0542088ef8
Refactor sampler code for more advanced sampler nodes part 2.
11 months ago
57753c964a
Refactor sampling code for more advanced sampler nodes.
11 months ago
6c6a39251f
Fix saving text encoder in fp8.
11 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.
11 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.
11 months ago
comfyanonymous
Mario Klingemann
Janek Mann
Dr.Lt.Data
Simon Lui
Dango233
JettHu
Chenlei Hu
Garrett Sutula
Jedrzej Kosinski
kk-89