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.
9 months ago
ec6f16adb6
Fix SAG.
9 months ago
bb4940d837
Only enable attention upcasting on models that actually need it.
9 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.
10 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
94a5a67c32
Cleanup to support different types of inpaint models.
11 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.
11 months ago
327ca1313d
Support SDXS 0.9
11 months ago
ae77590b4e
dora_scale support for lora file.
11 months ago
c6de09b02e
Optimize memory unload strategy for more optimized performance.
11 months ago
0624838237
Add inverse noise scaling function.
11 months ago
5d875d77fe
Fix regression with lcm not working with batches.
11 months ago
4b9005e949
Fix regression with model merging.
11 months ago
c18a203a8a
Don't unload model weights for non weight patches.
11 months ago
150a3e946f
Make LCM sampler use the model noise scaling function.
11 months ago
40e124c6be
SV3D support.
11 months ago
cacb022c4a
Make saved SD1 checkpoints match more closely the official one.
11 months ago
d7897fff2c
Move cascade scale factor from stage_a to latent_formats.py
11 months ago
f2fe635c9f
SamplerDPMAdaptative node to test the different options.
11 months ago
448d9263a2
Fix control loras breaking.
12 months ago
db8b59ecff
Lower memory usage for loras in lowvram mode at the cost of perf.
12 months ago
2a813c3b09
Switch some more prints to logging.
12 months ago
0ed72befe1
Change log levels.
...
Logging level now defaults to info. --verbose sets it to debug.
12 months ago
65397ce601
Replace prints with logging and add --verbose argument.
12 months ago
5f60ee246e
Support loading the sr cascade controlnet.
12 months ago
03e6e81629
Set upscale algorithm to bilinear for stable cascade controlnet.
12 months ago
03e83bb5d0
Support stable cascade canny controlnet.
12 months ago
10860bcd28
Add compression_ratio to controlnet code.
12 months ago
478f71a249
Remove useless check.
12 months ago
12c1080ebc
Simplify differential diffusion code.
12 months ago
727021bdea
Implement Differential Diffusion ( #2876 )
...
* Implement Differential Diffusion
* Cleanup.
* Fix.
* Masks should be applied at full strength.
* Fix colors.
* Register the node.
* Cleaner code.
* Fix issue with getting unipc sampler.
* Adjust thresholds.
* Switch to linear thresholds.
* Only calculate nearest_idx on valid thresholds.
12 months ago
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
dce3555339
Add some tesla pascal GPUs to the fp16 working but slower list.
12 months ago
51df846598
Let conditioning specify custom concat conds.
12 months ago
9f71e4b62d
Let model patches patch sub objects.
12 months ago
00425563c0
Cleanup: Use sampling noise scaling function for inpainting.
12 months ago
c62e836167
Move noise scaling to object with sampling math.
12 months ago
cb7c3a2921
Allow image_only_indicator to be None.
1 year ago
b3e97fc714
Koala 700M and 1B support.
...
Use the UNET Loader node to load the unet file to use them.
1 year ago
37a86e4618
Remove duplicate text_projection key from some saved models.
1 year ago
8daedc5bf2
Auto detect playground v2.5 model.
1 year ago
d46583ecec
Playground V2.5 support with ModelSamplingContinuousEDM node.
...
Use ModelSamplingContinuousEDM with edm_playground_v2.5 selected.
1 year ago
1e0fcc9a65
Make XL checkpoints save in a more standard format.
1 year ago
b416be7d78
Make the text projection saved in the checkpoint the right format.
1 year ago
03c47fc0f2
Add a min_length property to tokenizer class.
1 year ago
8ac69f62e5
Make return_projected_pooled setable from the __init__
1 year ago
ca7c310a0e
Support loading old CLIP models saved with CLIPSave.
1 year ago
c2cb8e889b
Always return unprojected pooled output for gligen.
1 year ago
1cb3f6a83b
Move text projection into the CLIP model code.
...
Fix issue with not loading the SSD1B clip correctly.
1 year ago
6533b172c1
Support text encoder text_projection in lora.
1 year ago
1e5f0f66be
Support lora keys with lora_prior_unet_ and lora_prior_te_
1 year ago
e1cb93c383
Fix model and cond transformer options merge
1 year ago
10847dfafe
Cleanup uni_pc inpainting.
...
This causes some small changes to the uni pc inpainting behavior but it
seems to improve results slightly.
1 year ago
18c151b3e3
Add some latent2rgb matrices for previews.
1 year ago
0d0fbabd1d
Pass pooled CLIP to stage b.
1 year ago
c6b7a157ed
Align simple scheduling closer to official stable cascade scheduler.
1 year ago
88f300401c
Enable fp16 by default on mps.
1 year ago
e93cdd0ad0
Remove print.
1 year ago
3711b31dff
Support Stable Cascade in checkpoint format.
1 year ago
d91f45ef28
Some cleanups to how the text encoders are loaded.
1 year ago
a7b5eaa7e3
Forgot to commit this.
1 year ago
3b2e579926
Support loading the Stable Cascade effnet and previewer as a VAE.
...
The effnet can be used to encode images for img2img with Stage C.
1 year ago
dccca1daa5
Fix gligen lowvram mode.
1 year ago
8b60d33bb7
Add ModelSamplingStableCascade to control the shift sampling parameter.
...
shift is 2.0 by default on Stage C and 1.0 by default on Stage B.
1 year ago
6bcf57ff10
Fix attention masks properly for multiple batches.
1 year ago
11e3221f1f
fp8 weight support for Stable Cascade.
1 year ago
f8706546f3
Fix attention mask batch size in some attention functions.
1 year ago
3b9969c1c5
Properly fix attention masks in CLIP with batches.
1 year ago
5b40e7a5ed
Implement shift schedule for cascade stage C.
1 year ago
929e266f3e
Manual cast for bf16 on older GPUs.
1 year ago
6c875d846b
Fix clip attention mask issues on some hardware.
1 year ago
805c36ac9c
Make Stable Cascade work on old pytorch 2.0
1 year ago
f2d1d16f4f
Support Stable Cascade Stage B lite.
1 year ago
0b3c50480c
Make --force-fp32 disable loading models in bf16.
1 year ago
97d03ae04a
StableCascade CLIP model support.
1 year ago
667c92814e
Stable Cascade Stage B.
1 year ago
f83109f09b
Stable Cascade Stage C.
1 year ago
5e06baf112
Stable Cascade Stage A.
1 year ago
aeaeca10bd
Small refactor of is_device_* functions.
1 year ago
38b7ac6e26
Don't init the CLIP model when the checkpoint has no CLIP weights.
1 year ago
7dd352cbd7
Merge branch 'feature_expose_discard_penultimate_sigma' of https://github.com/blepping/ComfyUI
1 year ago
f44225fd5f
Fix infinite while loop being possible in ddim_scheduler
1 year ago
25a4805e51
Add a way to set different conditioning for the controlnet.
1 year ago
a352c021ec
Allow custom samplers to request discard penultimate sigma
1 year ago
c661a8b118
Don't use numpy for calculating sigmas.
1 year ago
236bda2683
Make minimum tile size the size of the overlap.
1 year ago
66e28ef45c
Don't use is_bf16_supported to check for fp16 support.
1 year ago
24129d78e6
Speed up SDXL on 16xx series with fp16 weights and manual cast.
1 year ago
4b0239066d
Always use fp16 for the text encoders.
1 year ago
da7a8df0d2
Put VAE key name in model config.
1 year ago
89507f8adf
Remove some unused imports.
1 year ago
05cd00695a
typo fix - calculate_sigmas_scheduler ( #2619 )
...
self.scheduler -> scheduler_name
Co-authored-by: Lt.Dr.Data <lt.dr.data@gmail.com>
1 year ago
4871a36458
Cleanup some unused imports.
1 year ago
78a70fda87
Remove useless import.
1 year ago
d76a04b6ea
Add unfinished ImageOnlyCheckpointSave node to save a SVD checkpoint.
...
This node is unfinished, SVD checkpoints saved with this node will
work with ComfyUI but not with anything else.
1 year ago
f9e55d8463
Only auto enable bf16 VAE on nvidia GPUs that actually support it.
1 year ago
2395ae740a
Make unclip more deterministic.
...
Pass a seed argument note that this might make old unclip images different.
1 year ago
53c8a99e6c
Make server storage the default.
...
Remove --server-storage argument.
1 year ago
977eda19a6
Don't round noise mask.
1 year ago
10f2609fdd
Add InpaintModelConditioning node.
...
This is an alternative to VAE Encode for inpaint that should work with
lower denoise.
This is a different take on #2501
1 year ago
1a57423d30
Fix issue when using multiple t2i adapters with batched images.
1 year ago
6a7bc35db8
Use basic attention implementation for small inputs on old pytorch.
1 year ago
235727fed7
Store user settings/data on the server and multi user support ( #2160 )
...
* wip per user data
* Rename, hide menu
* better error
rework default user
* store pretty
* Add userdata endpoints
Change nodetemplates to userdata
* add multi user message
* make normal arg
* Fix tests
* Ignore user dir
* user tests
* Changed to default to browser storage and add server-storage arg
* fix crash on empty templates
* fix settings added before load
* ignore parse errors
1 year ago
c6951548cf
Update optimized_attention_for_device function for new functions that
...
support masked attention.
1 year ago
aaa9017302
Add attention mask support to sub quad attention.
1 year ago
0c2c9fbdfa
Support attention mask in split attention.
1 year ago
3ad0191bfb
Implement attention mask on xformers.
1 year ago
8c6493578b
Implement noise augmentation for SD 4X upscale model.
1 year ago
ef4f6037cb
Fix model patches not working in custom sampling scheduler nodes.
1 year ago
a7874d1a8b
Add support for the stable diffusion x4 upscaling model.
...
This is an old model.
Load the checkpoint like a regular one and use the new
SD_4XUpscale_Conditioning node.
1 year ago
2c4e92a98b
Fix regression.
1 year ago
5eddfdd80c
Refactor VAE code.
...
Replace constants with downscale_ratio and latent_channels.
1 year ago
a47f609f90
Auto detect out_channels from model.
1 year ago
79f73a4b33
Remove useless code.
1 year ago
1b103e0cb2
Add argument to run the VAE on the CPU.
1 year ago
12e822c6c8
Use function to calculate model size in model patcher.
1 year ago
e1e322cf69
Load weights that can't be lowvramed to target device.
1 year ago
c782144433
Fix clip vision lowvram mode not working.
1 year ago
f21bb41787
Fix taesd VAE in lowvram mode.
1 year ago
61b3f15f8f
Fix lowvram mode not working with unCLIP and Revision code.
1 year ago
d0165d819a
Fix SVD lowvram mode.
1 year ago
a252963f95
--disable-smart-memory now unloads everything like it did originally.
1 year ago
36a7953142
Greatly improve lowvram sampling speed by getting rid of accelerate.
...
Let me know if this breaks anything.
1 year ago
261bcbb0d9
A few missing comfy ops in the VAE.
1 year ago
9a7619b72d
Fix regression with inpaint model.
1 year ago
571ea8cdcc
Fix SAG not working with cfg 1.0
1 year ago
8cf1daa108
Fix SDXL area composition sometimes not using the right pooled output.
1 year ago
2258f85159
Support stable zero 123 model.
...
To use it use the ImageOnlyCheckpointLoader to load the checkpoint and
the new Stable_Zero123 node.
1 year ago
2f9d6a97ec
Add --deterministic option to make pytorch use deterministic algorithms.
1 year ago
e45d920ae3
Don't resize clip vision image when the size is already good.
1 year ago
13e6d5366e
Switch clip vision to manual cast.
...
Make it use the same dtype as the text encoder.
1 year ago
719fa0866f
Set clip vision model in eval mode so it works without inference mode.
1 year ago
574363a8a6
Implement Perp-Neg
1 year ago
a5056cfb1f
Remove useless code.
1 year ago
329c571993
Improve code legibility.
1 year ago
6c5990f7db
Fix cfg being calculated more than once if sampler_cfg_function.
1 year ago
ba04a87d10
Refactor and improve the sag node.
...
Moved all the sag related code to comfy_extras/nodes_sag.py
1 year ago
6761233e9d
Implement Self-Attention Guidance ( #2201 )
...
* First SAG test
* need to put extra options on the model instead of patcher
* no errors and results seem not-broken
* Use @ashen-uncensored formula, which works better!!!
* Fix a crash when using weird resolutions. Remove an unnecessary UNet call
* Improve comments, optimize memory in blur routine
* SAG works with sampler_cfg_function
1 year ago
b454a67bb9
Support segmind vega model.
1 year ago
824e4935f5
Add dtype parameter to VAE object.
1 year ago
32b7e7e769
Add manual cast to controlnet.
1 year ago
3152023fbc
Use inference dtype for unet memory usage estimation.
1 year ago
77755ab8db
Refactor comfy.ops
...
comfy.ops -> comfy.ops.disable_weight_init
This should make it more clear what they actually do.
Some unused code has also been removed.
1 year ago
b0aab1e4ea
Add an option --fp16-unet to force using fp16 for the unet.
1 year ago
ba07cb748e
Use faster manual cast for fp8 in unet.
1 year ago
57926635e8
Switch text encoder to manual cast.
...
Use fp16 text encoder weights for CPU inference to lower memory usage.
1 year ago
340177e6e8
Disable non blocking on mps.
1 year ago
614b7e731f
Implement GLora.
1 year ago
cb63e230b4
Make lora code a bit cleaner.
1 year ago
174eba8e95
Use own clip vision model implementation.
1 year ago
97015b6b38
Cleanup.
1 year ago
a4ec54a40d
Add linear_start and linear_end to model_config.sampling_settings
1 year ago
9ac0b487ac
Make --gpu-only put intermediate values in GPU memory instead of cpu.
1 year ago
efb704c758
Support attention masking in CLIP implementation.
1 year ago
fbdb14d4c4
Cleaner CLIP text encoder implementation.
...
Use a simple CLIP model implementation instead of the one from
transformers.
This will allow some interesting things that would too hackish to implement
using the transformers implementation.
1 year ago
2db86b4676
Slightly faster lora applying.
1 year ago
1bbd65ab30
Missed this one.
1 year ago
9b655d4fd7
Fix memory issue with control loras.
1 year ago
26b1c0a771
Fix control lora on fp8.
1 year ago
be3468ddd5
Less useless downcasting.
1 year ago
ca82ade765
Use .itemsize to get dtype size for fp8.
1 year ago
31b0f6f3d8
UNET weights can now be stored in fp8.
...
--fp8_e4m3fn-unet and --fp8_e5m2-unet are the two different formats
supported by pytorch.
1 year ago
af365e4dd1
All the unet ops with weights are now handled by comfy.ops
1 year ago
61a123a1e0
A different way of handling multiple images passed to SVD.
...
Previously when a list of 3 images [0, 1, 2] was used for a 6 frame video
they were concated like this:
[0, 1, 2, 0, 1, 2]
now they are concated like this:
[0, 0, 1, 1, 2, 2]
1 year ago
c97be4db91
Support SD2.1 turbo checkpoint.
1 year ago
983ebc5792
Use smart model management for VAE to decrease latency.
1 year ago
c45d1b9b67
Add a function to load a unet from a state dict.
1 year ago
f30b992b18
.sigma and .timestep now return tensors on the same device as the input.
1 year ago
13fdee6abf
Try to free memory for both cond+uncond before inference.
1 year ago
be71bb5e13
Tweak memory inference calculations a bit.
1 year ago
39e75862b2
Fix regression from last commit.
1 year ago
50dc39d6ec
Clean up the extra_options dict for the transformer patches.
...
Now everything in transformer_options gets put in extra_options.
1 year ago
5d6dfce548
Fix importing diffusers unets.
1 year ago
3e5ea74ad3
Make buggy xformers fall back on pytorch attention.
1 year ago
871cc20e13
Support SVD img2vid model.
1 year ago
410bf07771
Make VAE memory estimation take dtype into account.
1 year ago
32447f0c39
Add sampling_settings so models can specify specific sampling settings.
1 year ago
c3ae99a749
Allow controlling downscale and upscale methods in PatchModelAddDownscale.
1 year ago
72741105a6
Remove useless code.
1 year ago
6a491ebe27
Allow model config to preprocess the vae state dict on load.
1 year ago
cd4fc77d5f
Add taesd and taesdxl to VAELoader node.
...
They will show up if both the taesd_encoder and taesd_decoder or taesdxl
model files are present in the models/vae_approx directory.
1 year ago
ce67dcbcda
Make it easy for models to process the unet state dict on load.
1 year ago
d9d8702d8d
percent_to_sigma now returns a float instead of a tensor.
1 year ago
0cf4e86939
Add some command line arguments to store text encoder weights in fp8.
...
Pytorch supports two variants of fp8:
--fp8_e4m3fn-text-enc (the one that seems to give better results)
--fp8_e5m2-text-enc
1 year ago
107e78b1cb
Add support for loading SSD1B diffusers unet version.
...
Improve diffusers model detection.
1 year ago
7e3fe3ad28
Make deep shrink behave like it should.
1 year ago
9f00a18095
Fix potential issues.
1 year ago
7ea6bb038c
Print warning when controlnet can't be applied instead of crashing.
1 year ago
dcec1047e6
Invert the start and end percentages in the code.
...
This doesn't affect how percentages behave in the frontend but breaks
things if you relied on them in the backend.
percent_to_sigma goes from 0 to 1.0 instead of 1.0 to 0 for less confusion.
Make percent 0 return an extremely large sigma and percent 1.0 return a
zero one to fix imprecision.
1 year ago
57eea0efbb
heunpp2 sampler.
1 year ago
728613bb3e
Fix last pr.
1 year ago
ec3d0ab432
Merge branch 'master' of https://github.com/Jannchie/ComfyUI
1 year ago
c962884a5c
Make bislerp work on GPU.
1 year ago
420beeeb05
Clean up and refactor sampler code.
...
This should make it much easier to write custom nodes with kdiffusion type
samplers.
1 year ago
f2e49b1d57
fix: adaptation to older versions of pytroch
1 year ago
94cc718e9c
Add a way to add patches to the input block.
1 year ago
7339479b10
Disable xformers when it can't load properly.
1 year ago
4781819a85
Make memory estimation aware of model dtype.
1 year ago
comfyanonymous
JettHu
Chenlei Hu
Simon Lui
Garrett Sutula
Jedrzej Kosinski
kk-89
Shiimizu
logtd
blepping
Dr.Lt.Data
pythongosssss
Hari
Rafie Walker
Jianqi Pan