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
12 months ago
f2fe635c9f
SamplerDPMAdaptative node to test the different options.
12 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.
1 year ago
c62e836167
Move noise scaling to object with sampling math.
1 year 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
comfyanonymous
kk-89
Shiimizu
logtd
Jedrzej Kosinski
blepping
Dr.Lt.Data
pythongosssss
Hari
Rafie Walker