3696d1699a
Add support for GLIGEN textbox model.
2 years ago
884ea653c8
Add a way for nodes to set a custom CFG function.
2 years ago
73c3e11e83
Fix model_management import so it doesn't get executed twice.
2 years ago
81d1f00df3
Some refactoring: from_tokens -> encode_from_tokens
2 years ago
719c26c3c9
Merge branch 'master' of https://github.com/BlenderNeko/ComfyUI
2 years ago
d0b1b6c6bf
fixed improper padding
2 years ago
deb2b93e79
Move code to empty gpu cache to model_management.py
2 years ago
04d9bc13af
Safely load pickled embeds that don't load with weights_only=True.
2 years ago
da115bd78d
ensure backwards compat with optional args
2 years ago
752f7a162b
align behavior with old tokenize function
2 years ago
334aab05e5
Don't stop workflow if loading embedding fails.
2 years ago
73175cf58c
split tokenizer from encoder
2 years ago
8489cba140
add unique ID per word/embedding for tokenizer
2 years ago
92eca60ec9
Fix for new transformers version.
2 years ago
1e1875f674
Print xformers version and warning about 0.0.18
2 years ago
7e254d2f69
Clarify what --windows-standalone-build does.
2 years ago
44fea05064
Cleanup.
2 years ago
58ed0f2da4
Fix loading SD1.5 diffusers checkpoint.
2 years ago
8b9ac8fedb
Merge branch 'master' of https://github.com/sALTaccount/ComfyUI
2 years ago
64557d6781
Add a --force-fp32 argument to force fp32 for debugging.
2 years ago
bceccca0e5
Small refactor.
2 years ago
28a7205739
Merge branch 'ipex' of https://github.com/kwaa/ComfyUI-IPEX
2 years ago
05eeaa2de5
Merge branch 'master' into ipex
2 years ago
28fff5d1db
fixes lack of support for multi configs
...
also adds some metavars to argarse
2 years ago
f84f2508cc
Rename the cors parameter to something more verbose.
2 years ago
48efae1608
makes cors a cli parameter
2 years ago
01c1fc669f
set listen flag to listen on all if specifed
2 years ago
3e2608e12b
Fix auto lowvram detection on CUDA
2 years ago
60127a8304
diffusers loader
2 years ago
7cb924f684
Use separate variables instead of `vram_state`
2 years ago
84b9c0ac2f
Import intel_extension_for_pytorch as ipex
2 years ago
e5e587b1c0
seperates out arg parser and imports args
2 years ago
37713e3b0a
Add basic XPU device support
...
closed #387
2 years ago
e46b1c3034
Disable xformers in VAE when xformers == 0.0.18
2 years ago
1718730e80
Ignore embeddings when sizes don't match and print a WARNING.
2 years ago
23524ad8c5
Remove print.
2 years ago
539ff487a8
Pull latest tomesd code from upstream.
2 years ago
f50b1fec69
Add noise augmentation setting to unCLIPConditioning.
2 years ago
809bcc8ceb
Add support for unCLIP SD2.x models.
...
See _for_testing/unclip in the UI for the new nodes.
unCLIPCheckpointLoader is used to load them.
unCLIPConditioning is used to add the image cond and takes as input a
CLIPVisionEncode output which has been moved to the conditioning section.
2 years ago
0d972b85e6
This seems to give better quality in tome.
2 years ago
18a6c1db33
Add a TomePatchModel node to the _for_testing section.
...
Tome increases sampling speed at the expense of quality.
2 years ago
61ec3c9d5d
Add a way to pass options to the transformers blocks.
2 years ago
afd65d3819
Fix noise mask not working with > 1 batch size on ksamplers.
2 years ago
b2554bc4dd
Split VAE decode batches depending on free memory.
2 years ago
0d65cb17b7
Fix ddim_uniform crashing with 37 steps.
2 years ago
f55755f0d2
code cleanup
2 years ago
cf0098d539
no lowvram state if cpu only
2 years ago
f5365c9c81
Fix ddim for Mac: #264
2 years ago
4adcea7228
I don't think controlnets were being handled correctly by MPS.
2 years ago
3c6ff8821c
Merge branch 'master' of https://github.com/GaidamakUA/ComfyUI
2 years ago
fc71e7ea08
Fixed typo
2 years ago
7f0fd99b5d
Make ddim work with --cpu
2 years ago
4b943d2b60
Removed unnecessary comment
2 years ago
89fd5ed574
Added MPS device support
2 years ago
dd095efc2c
Support loha that use cp decomposition.
2 years ago
94a7c895f4
Add loha support.
2 years ago
3ed4a4e4e6
Try again with vae tiled decoding if regular fails because of OOM.
2 years ago
4039616ca6
Less seams in tiled outputs at the cost of more processing.
2 years ago
c692509c2b
Try to improve VAEEncode memory usage a bit.
2 years ago
9d0665c8d0
Add laptop quadro cards to fp32 list.
2 years ago
cc309568e1
Add support for locon mid weights.
2 years ago
edfc4ca663
Try to fix a vram issue with controlnets.
2 years ago
b4b21be707
Fix area composition feathering not working properly.
2 years ago
50099bcd96
Support multiple paths for embeddings.
2 years ago
2e73367f45
Merge T2IAdapterLoader and ControlNetLoader.
...
Workflows will be auto updated.
2 years ago
ee46bef03a
Make --cpu have priority over everything else.
2 years ago
0e836d525e
use half() on fp16 models loaded with config.
2 years ago
986dd820dc
Use half() function on model when loading in fp16.
2 years ago
54dbfaf2ec
Remove omegaconf dependency and some ci changes.
2 years ago
83f23f82b8
Add pytorch attention support to VAE.
2 years ago
a256a2abde
--disable-xformers should not even try to import xformers.
2 years ago
0f3ba7482f
Xformers is now properly disabled when --cpu used.
...
Added --windows-standalone-build option, currently it only opens
makes the code open up comfyui in the browser.
2 years ago
e33dc2b33b
Add a VAEEncodeTiled node.
2 years ago
1de86851b1
Try to fix memory issue.
2 years ago
2b1fce2943
Make tiled_scale work for downscaling.
2 years ago
9db2e97b47
Tiled upscaling with the upscale models.
2 years ago
cd64111c83
Add locon support.
2 years ago
c70f0ac64b
SD2.x controlnets now work.
2 years ago
19415c3ace
Relative imports to test something.
2 years ago
165be5828a
Fixed import ( #44 )
...
* fixed import error
I had an
ImportError: cannot import name 'Protocol' from 'typing'
while trying to update so I fixed it to start an app
* Update main.py
* deleted example files
2 years ago
501f19eec6
Fix clip_skip no longer being loaded from yaml file.
2 years ago
afff30fc0a
Add --cpu to use the cpu for inference.
2 years ago
47acb3d73e
Implement support for t2i style model.
...
It needs the CLIPVision model so I added CLIPVisionLoader and CLIPVisionEncode.
Put the clip vision model in models/clip_vision
Put the t2i style model in models/style_models
StyleModelLoader to load it, StyleModelApply to apply it
ConditioningAppend to append the conditioning it outputs to a positive one.
2 years ago
cc8baf1080
Make VAE use common function to get free memory.
2 years ago
798c90e1c0
Fix pytorch 2.0 cross attention not working.
2 years ago
16130c7546
Add support for new colour T2I adapter model.
2 years ago
9d00235b41
Update T2I adapter code to latest.
2 years ago
ebfcf0a9c9
Fix issue.
2 years ago
4215206281
Add a node to set CLIP skip.
...
Use a more simple way to detect if the model is -v prediction.
2 years ago
fed315a76a
To be really simple CheckpointLoaderSimple should pick the right type.
2 years ago
94bb0375b0
New CheckpointLoaderSimple to load checkpoints without a config.
2 years ago
c1f5855ac1
Make some cross attention functions work on the CPU.
2 years ago
1a612e1c74
Add some pytorch scaled_dot_product_attention code for testing.
...
--use-pytorch-cross-attention to use it.
2 years ago
69cc75fbf8
Add a way to interrupt current processing in the backend.
2 years ago
9502ee45c3
Hopefully fix a strange issue with xformers + lowvram.
2 years ago
b31daadc03
Try to improve memory issues with del.
2 years ago
2c5f0ec681
Small adjustment.
2 years ago
86721d5158
Enable highvram automatically when vram >> ram
2 years ago
75fa162531
Remove sample_ from some sampler names.
...
Old workflows will still work.
2 years ago
9f4214e534
Preparing to add another function to load checkpoints.
2 years ago
3cd7d84b53
Fix uni_pc sampler not working with 1 or 2 steps.
2 years ago
dfb397e034
Fix multiple controlnets not working.
2 years ago
af3cc1b5fb
Fixed issue when batched image was used as a controlnet input.
2 years ago
d2da346b0b
Fix missing variable.
2 years ago
4e6b83a80a
Add a T2IAdapterLoader node to load T2I-Adapter models.
...
They are loaded as CONTROL_NET objects because they are similar.
2 years ago
fcb25d37db
Prepare for t2i adapter.
2 years ago
cf5a211efc
Remove some useless imports
2 years ago
87b00b37f6
Added an experimental VAEDecodeTiled.
...
This decodes the image with the VAE in tiles which should be faster and
use less vram.
It's in the _for_testing section so I might change/remove it or even
add the functionality to the regular VAEDecode node depending on how
well it performs which means don't depend too much on it.
2 years ago
62df8dd62a
Add a node to load diff controlnets.
2 years ago
f04dc2c2f4
Implement DDIM sampler.
2 years ago
2976c1ad28
Uni_PC: make max denoise behave more like other samplers.
...
On the KSamplers denoise of 1.0 is the same as txt2img but there was a
small difference on UniPC.
2 years ago
c9daec4c89
Remove prints that are useless when xformers is enabled.
2 years ago
a7328e4945
Add uni_pc bh2 variant.
2 years ago
d80af7ca30
ControlNetApply now stacks.
...
It can be used to apply multiple control nets at the same time.
2 years ago
00a9189e30
Support old pytorch.
2 years ago
137ae2606c
Support people putting commas after the embedding name in the prompt.
2 years ago
2326ff1263
Add: --highvram for when you want models to stay on the vram.
2 years ago
09f1d76ed8
Fix an OOM issue.
2 years ago
d66415c021
Low vram mode for controlnets.
2 years ago
220a72d36b
Use fp16 for fp16 control nets.
2 years ago
6135a21ee8
Add a way to control controlnet strength.
2 years ago
4efa67fa12
Add ControlNet support.
2 years ago
bc69fb5245
Use inpaint models the proper way by using VAEEncodeForInpaint.
2 years ago
cef2cc3cb0
Support for inpaint models.
2 years ago
07db00355f
Add masks to samplers code for inpainting.
2 years ago
e3451cea4f
uni_pc now works with KSamplerAdvanced return_with_leftover_noise.
2 years ago
f542f248f1
Show the right amount of steps in the progress bar for uni_pc.
...
The extra step doesn't actually call the unet so it doesn't belong in
the progress bar.
2 years ago
f10b8948c3
768-v support for uni_pc sampler.
2 years ago
ce0aeb109e
Remove print.
2 years ago
5489d5af04
Add uni_pc sampler to KSampler* nodes.
2 years ago
1a4edd19cd
Fix overflow issue with inplace softmax.
2 years ago
509c7dfc6d
Use real softmax in split op to fix issue with some images.
2 years ago
7e1e193f39
Automatically enable lowvram mode if vram is less than 4GB.
...
Use: --normalvram to disable it.
2 years ago
324273fff2
Fix embedding not working when on new line.
2 years ago
1f6a467e92
Update ldm dir with latest upstream stable diffusion changes.
2 years ago
773cdabfce
Same thing but for the other places where it's used.
2 years ago
df40d4f3bf
torch.cuda.OutOfMemoryError is not present on older pytorch versions.
2 years ago
e8c499ddd4
Split optimization for VAE attention block.
2 years ago
5b4e312749
Use inplace operations for less OOM issues.
2 years ago
3fd87cbd21
Slightly smarter batching behaviour.
...
Try to keep batch sizes more consistent which seems to improve things on
AMD GPUs.
2 years ago
bbdcf0b737
Use relative imports for k_diffusion.
2 years ago
708138c77d
Remove print.
2 years ago
047775615b
Lower the chances of an OOM.
2 years ago
853e96ada3
Increase it/s by batching together some stuff sent to unet.
2 years ago
c92633eaa2
Auto calculate amount of memory to use for --lowvram
2 years ago
534736b924
Add some low vram modes: --lowvram and --novram
2 years ago
a84cd0d1ad
Don't unload/reload model from CPU uselessly.
2 years ago
b1a7c9ebf6
Embeddings/textual inversion support for SD2.x
2 years ago
1de5aa6a59
Add a CLIPLoader node to load standalone clip weights.
...
Put them in models/clip
2 years ago
56d802e1f3
Use transformers CLIP instead of open_clip for SD2.x
...
This should make things a bit cleaner.
2 years ago
comfyanonymous
BlenderNeko
藍+85CD
EllangoK
sALTaccount
Francesco Yoshi Gobbo
Yurii Mazurevich
edikius