comfyanonymous
bc6be6c11e
Some fixes to the lowvram system.
2024-11-22 16:40:04 -05:00
comfyanonymous
5818f6cf51
Remove print.
2024-11-22 10:49:15 -05:00
comfyanonymous
5e16f1d24b
Support Lightricks LTX-Video model.
2024-11-22 08:46:39 -05:00
comfyanonymous
2fd9c1308a
Fix mask issue in some attention functions.
2024-11-22 02:10:09 -05:00
comfyanonymous
8f0009aad0
Support new flux model variants.
2024-11-21 08:38:23 -05:00
comfyanonymous
41444b5236
Add some new weight patching functionality.
...
Add a way to reshape lora weights.
Allow weight patches to all weight not just .weight and .bias
Add a way for a lora to set a weight to a specific value.
2024-11-21 07:19:17 -05:00
comfyanonymous
07f6eeaa13
Fix mask issue with attention_xformers.
2024-11-20 17:07:46 -05:00
comfyanonymous
22535d0589
Skip layer guidance now works on stable audio model.
2024-11-20 07:33:06 -05:00
comfyanonymous
b699a15062
Refactor inpaint/ip2p code.
2024-11-19 03:25:25 -05:00
comfyanonymous
d9f90965c8
Support block replace patches in auraflow.
2024-11-17 08:19:59 -05:00
comfyanonymous
41886af138
Add transformer options blocks replace patch to mochi.
2024-11-16 20:48:14 -05:00
comfyanonymous
3b9a6cf2b1
Fix issue with 3d masks.
2024-11-13 07:18:30 -05:00
comfyanonymous
8ebf2d8831
Add block replace transformer_options to flux.
2024-11-12 08:00:39 -05:00
comfyanonymous
eb476e6ea9
Allow 1D masks for 1D latents.
2024-11-11 14:44:52 -05:00
comfyanonymous
8b275ce5be
Support auto detecting some zsnr anime checkpoints.
2024-11-11 05:34:11 -05:00
comfyanonymous
2a18e98ccf
Refactor so that zsnr can be set in the sampling_settings.
2024-11-11 04:55:56 -05:00
comfyanonymous
bdeb1c171c
Fast previews for mochi.
2024-11-10 03:39:35 -05:00
comfyanonymous
8b90e50979
Properly handle and reshape masks when used on 3d latents.
2024-11-09 15:30:19 -05:00
comfyanonymous
2865f913f7
Free memory before doing tiled decode.
2024-11-07 04:01:24 -05:00
comfyanonymous
b49616f951
Make VAEDecodeTiled node work with video VAEs.
2024-11-07 03:47:12 -05:00
comfyanonymous
5e29e7a488
Remove scaled_fp8 key after reading it to silence warning.
2024-11-06 04:56:42 -05:00
comfyanonymous
8afb97cd3f
Fix unknown VAE being detected as the mochi VAE.
2024-11-05 03:43:27 -05:00
contentis
69694f40b3
fix dynamic shape export ( #5490 )
2024-11-04 14:59:28 -05:00
comfyanonymous
6c9dbde7de
Fix mochi all in one checkpoint t5xxl key names.
2024-11-03 01:40:42 -05:00
comfyanonymous
fabf449feb
Mochi VAE encoder.
2024-11-01 17:33:09 -04:00
Aarni Koskela
1c8286a44b
Avoid SyntaxWarning in UniPC docstring ( #5442 )
2024-10-31 15:17:26 -04:00
comfyanonymous
1af4a47fd1
Bump up mac version for attention upcast bug workaround.
2024-10-31 15:15:31 -04:00
comfyanonymous
daa1565b93
Fix diffusers flux controlnet regression.
2024-10-30 13:11:34 -04:00
comfyanonymous
09fdb2b269
Support SD3.5 medium diffusers format weights and loras.
2024-10-30 04:24:00 -04:00
comfyanonymous
30c0c81351
Add a way to patch blocks in SD3.
2024-10-29 00:48:32 -04:00
comfyanonymous
13b0ff8a6f
Update SD3 code.
2024-10-28 21:58:52 -04:00
comfyanonymous
c320801187
Remove useless line.
2024-10-28 17:41:12 -04:00
comfyanonymous
669d9e4c67
Set default shift on mochi to 6.0
2024-10-27 22:21:04 -04:00
comfyanonymous
9ee0a6553a
float16 inference is a bit broken on mochi.
2024-10-27 04:56:40 -04:00
comfyanonymous
5cbb01bc2f
Basic Genmo Mochi video model support.
...
To use:
"Load CLIP" node with t5xxl + type mochi
"Load Diffusion Model" node with the mochi dit file.
"Load VAE" with the mochi vae file.
EmptyMochiLatentVideo node for the latent.
euler + linear_quadratic in the KSampler node.
2024-10-26 06:54:00 -04:00
comfyanonymous
c3ffbae067
Make LatentUpscale nodes work on 3d latents.
2024-10-26 01:50:51 -04:00
comfyanonymous
d605677b33
Make euler_ancestral work on flow models (credit: Ashen).
2024-10-25 19:53:44 -04:00
PsychoLogicAu
af8cf79a2d
support SimpleTuner lycoris lora for SD3 ( #5340 )
2024-10-24 01:18:32 -04:00
comfyanonymous
66b0961a46
Fix ControlLora issue with last commit.
2024-10-23 17:02:40 -04:00
comfyanonymous
754597c8a9
Clean up some controlnet code.
...
Remove self.device which was useless.
2024-10-23 14:19:05 -04:00
comfyanonymous
915fdb5745
Fix lowvram edge case.
2024-10-22 16:34:50 -04:00
contentis
5a8a48931a
remove attention abstraction ( #5324 )
2024-10-22 14:02:38 -04:00
comfyanonymous
8ce2a1052c
Optimizations to --fast and scaled fp8.
2024-10-22 02:12:28 -04:00
comfyanonymous
f82314fcfc
Fix duplicate sigmas on beta scheduler.
2024-10-21 20:19:45 -04:00
comfyanonymous
0075c6d096
Mixed precision diffusion models with scaled fp8.
...
This change allows supports for diffusion models where all the linears are
scaled fp8 while the other weights are the original precision.
2024-10-21 18:12:51 -04:00
comfyanonymous
83ca891118
Support scaled fp8 t5xxl model.
2024-10-20 22:27:00 -04:00
comfyanonymous
f9f9faface
Fixed model merging issue with scaled fp8.
2024-10-20 06:24:31 -04:00
comfyanonymous
471cd3eace
fp8 casting is fast on GPUs that support fp8 compute.
2024-10-20 00:54:47 -04:00
comfyanonymous
a68bbafddb
Support diffusion models with scaled fp8 weights.
2024-10-19 23:47:42 -04:00
comfyanonymous
73e3a9e676
Clamp output when rounding weight to prevent Nan.
2024-10-19 19:07:10 -04:00
comfyanonymous
67158994a4
Use the lowvram cast_to function for everything.
2024-10-17 17:25:56 -04:00
comfyanonymous
0bedfb26af
Revert "Fix Transformers FutureWarning ( #5140 )"
...
This reverts commit 95b7cf9bbe
2024-10-16 12:36:19 -04:00
comfyanonymous
f584758271
Cleanup some useless lines.
2024-10-14 21:02:39 -04:00
svdc
95b7cf9bbe
Fix Transformers FutureWarning ( #5140 )
...
* Update sd1_clip.py
Fix Transformers FutureWarning
* Update sd1_clip.py
Fix comment
2024-10-14 20:12:20 -04:00
comfyanonymous
3c60ecd7a8
Fix fp8 ops staying enabled.
2024-10-12 14:10:13 -04:00
comfyanonymous
7ae6626723
Remove useless argument.
2024-10-12 07:16:21 -04:00
comfyanonymous
6632365e16
model_options consistency between functions.
...
weight_dtype -> dtype
2024-10-11 20:51:19 -04:00
Kadir Nar
ad07796777
🐛 Add device to variable c ( #5210 )
2024-10-11 20:37:50 -04:00
comfyanonymous
1b80895285
Make clip loader nodes support loading sd3 t5xxl in lower precision.
...
Add attention mask support in the SD3 text encoder code.
2024-10-10 15:06:15 -04:00
Dr.Lt.Data
5f9d5a244b
Hotfix for the div zero occurrence when memory_used_encode is 0 ( #5121 )
...
https://github.com/comfyanonymous/ComfyUI/issues/5069#issuecomment-2382656368
2024-10-09 23:34:34 -04:00
Jonathan Avila
4b2f0d9413
Increase maximum macOS version to 15.0.1 when forcing upcast attention ( #5191 )
2024-10-09 22:21:41 -04:00
comfyanonymous
e38c94228b
Add a weight_dtype fp8_e4m3fn_fast to the Diffusion Model Loader node.
...
This is used to load weights in fp8 and use fp8 matrix multiplication.
2024-10-09 19:43:17 -04:00
comfyanonymous
203942c8b2
Fix flux doras with diffusers keys.
2024-10-08 19:03:40 -04:00
comfyanonymous
8dfa0cc552
Make SD3 fast previews a little better.
2024-10-07 09:19:59 -04:00
comfyanonymous
e5ecdfdd2d
Make fast previews for SDXL a little better by adding a bias.
2024-10-06 19:27:04 -04:00
comfyanonymous
7d29fbf74b
Slightly improve the fast previews for flux by adding a bias.
2024-10-06 17:55:46 -04:00
comfyanonymous
7d2467e830
Some minor cleanups.
2024-10-05 13:22:39 -04:00
comfyanonymous
6f021d8aa0
Let --verbose have an argument for the log level.
2024-10-04 10:05:34 -04:00
comfyanonymous
d854ed0bcf
Allow using SD3 type te output on flux model.
2024-10-03 09:44:54 -04:00
comfyanonymous
abcd006b8c
Allow more permutations of clip/t5 in dual clip loader.
2024-10-03 09:26:11 -04:00
comfyanonymous
d985d1d7dc
CLIP Loader node now supports clip_l and clip_g only for SD3.
2024-10-02 04:25:17 -04:00
comfyanonymous
d1cdf51e1b
Refactor some of the TE detection code.
2024-10-01 07:08:41 -04:00
comfyanonymous
b4626ab93e
Add simpletuner lycoris format for SD unet.
2024-09-30 06:03:27 -04:00
comfyanonymous
a9e459c2a4
Use torch.nn.functional.linear in RGB preview code.
...
Add an optional bias to the latent RGB preview code.
2024-09-29 11:27:49 -04:00
comfyanonymous
3bb4dec720
Fix issue with loras, lowvram and --fast fp8.
2024-09-28 14:42:32 -04:00
City
8733191563
Flux torch.compile fix ( #5082 )
2024-09-27 22:07:51 -04:00
comfyanonymous
bdd4a22a2e
Fix flux TE not loading t5 embeddings.
2024-09-24 22:57:22 -04:00
chaObserv
479a427a48
Add dpmpp_2m_cfg_pp ( #4992 )
2024-09-24 02:42:56 -04:00
comfyanonymous
3a0eeee320
Make --listen listen on both ipv4 and ipv6 at the same time by default.
2024-09-23 04:38:19 -04:00
comfyanonymous
9c41bc8d10
Remove useless line.
2024-09-23 02:32:29 -04:00
comfyanonymous
7a415f47a9
Add an optional VAE input to the ControlNetApplyAdvanced node.
...
Deprecate the other controlnet nodes.
2024-09-22 01:24:52 -04:00
comfyanonymous
dc96a1ae19
Load controlnet in fp8 if weights are in fp8.
2024-09-21 04:50:12 -04:00
comfyanonymous
2d810b081e
Add load_controlnet_state_dict function.
2024-09-21 01:51:51 -04:00
comfyanonymous
9f7e9f0547
Add an error message when a controlnet needs a VAE but none is given.
2024-09-21 01:33:18 -04:00
comfyanonymous
70a708d726
Fix model merging issue.
2024-09-20 02:31:44 -04:00
yoinked
e7d4782736
add laplace scheduler [2407.03297] ( #4990 )
...
* add laplace scheduler [2407.03297]
* should be here instead lol
* better settings
2024-09-19 23:23:09 -04:00
comfyanonymous
ad66f7c7d8
Add model_options to load_controlnet function.
2024-09-19 08:23:35 -04:00
Simon Lui
de8e8e3b0d
Fix xpu Pytorch nightly build from calling optimize which doesn't exist. ( #4978 )
2024-09-19 05:11:42 -04:00
pharmapsychotic
0b7dfa986d
Improve tiling calculations to reduce number of tiles that need to be processed. ( #4944 )
2024-09-17 03:51:10 -04:00
comfyanonymous
d514bb38ee
Add some option to model_options for the text encoder.
...
load_device, offload_device and the initial_device can now be set.
2024-09-17 03:49:54 -04:00
comfyanonymous
0849c80e2a
get_key_patches now works without unloading the model.
2024-09-17 01:57:59 -04:00
comfyanonymous
e813abbb2c
Long CLIP L support for SDXL, SD3 and Flux.
...
Use the *CLIPLoader nodes.
2024-09-15 07:59:38 -04:00
comfyanonymous
f48e390032
Support AliMama SD3 and Flux inpaint controlnets.
...
Use the ControlNetInpaintingAliMamaApply node.
2024-09-14 09:05:16 -04:00
comfyanonymous
cf80d28689
Support loading controlnets with different input.
2024-09-13 09:54:37 -04:00
Robin Huang
b962db9952
Add cli arg to override user directory ( #4856 )
...
* Override user directory.
* Use overridden user directory.
* Remove prints.
* Remove references to global user_files.
* Remove unused replace_folder function.
* Remove newline.
* Remove global during get_user_directory.
* Add validation.
2024-09-12 08:10:27 -04:00
comfyanonymous
9d720187f1
types -> comfy_types to fix import issue.
2024-09-12 03:57:46 -04:00
comfyanonymous
9f4daca9d9
Doesn't really make sense for cfg_pp sampler to call regular one.
2024-09-11 02:51:36 -04:00
yoinked
b5d0f2a908
Add CFG++ to DPM++ 2S Ancestral ( #3871 )
...
* Update sampling.py
* Update samplers.py
* my bad
* "fix" the sampler
* Update samplers.py
* i named it wrong
* minor sampling improvements
mainly using a dynamic rho value (hey this sounds a lot like smea!!!)
* revert rho change
rho? r? its just 1/2
2024-09-11 02:49:44 -04:00
comfyanonymous
9c5fca75f4
Fix lora issue.
2024-09-08 10:10:47 -04:00
comfyanonymous
32a60a7bac
Support onetrainer text encoder Flux lora.
2024-09-08 09:31:41 -04:00
Jim Winkens
bb52934ba4
Fix import issue ( #4815 )
2024-09-07 05:28:32 -04:00
comfyanonymous
ea77750759
Support a generic Comfy format for text encoder loras.
...
This is a format with keys like:
text_encoders.clip_l.transformer.text_model.encoder.layers.9.self_attn.v_proj.lora_up.weight
Instead of waiting for me to add support for specific lora formats you can
convert your text encoder loras to this format instead.
If you want to see an example save a text encoder lora with the SaveLora
node with the commit right after this one.
2024-09-07 02:20:39 -04:00
comfyanonymous
c27ebeb1c2
Fix onnx export not working on flux.
2024-09-06 03:21:52 -04:00
comfyanonymous
5cbaa9e07c
Mistoline flux controlnet support.
2024-09-05 00:05:17 -04:00
comfyanonymous
c7427375ee
Prioritize freeing partially offloaded models first.
2024-09-04 19:47:32 -04:00
Jedrzej Kosinski
f04229b84d
Add emb_patch support to UNetModel forward ( #4779 )
2024-09-04 14:35:15 -04:00
Silver
f067ad15d1
Make live preview size a configurable launch argument ( #4649 )
...
* Make live preview size a configurable launch argument
* Remove import from testing phase
* Update cli_args.py
2024-09-03 19:16:38 -04:00
comfyanonymous
483004dd1d
Support newer glora format.
2024-09-03 17:02:19 -04:00
comfyanonymous
00a5d08103
Lower fp8 lora memory usage.
2024-09-03 01:25:05 -04:00
comfyanonymous
d043997d30
Flux onetrainer lora.
2024-09-02 08:22:15 -04:00
comfyanonymous
8d31a6632f
Speed up inference on nvidia 10 series on Linux.
2024-09-01 17:29:31 -04:00
comfyanonymous
b643eae08b
Make minimum_inference_memory() depend on --reserve-vram
2024-09-01 01:18:34 -04:00
comfyanonymous
935ae153e1
Cleanup.
2024-08-30 12:53:59 -04:00
Chenlei Hu
e91662e784
Get logs endpoint & system_stats additions ( #4690 )
...
* Add route for getting output logs
* Include ComfyUI version
* Move to own function
* Changed to memory logger
* Unify logger setup logic
* Fix get version git fallback
---------
Co-authored-by: pythongosssss <125205205+pythongosssss@users.noreply.github.com>
2024-08-30 12:46:37 -04:00
comfyanonymous
63fafaef45
Fix potential issue with hydit controlnets.
2024-08-30 04:58:41 -04:00
comfyanonymous
6eb5d64522
Fix glora lowvram issue.
2024-08-29 19:07:23 -04:00
comfyanonymous
10a79e9898
Implement model part of flux union controlnet.
2024-08-29 18:41:22 -04:00
comfyanonymous
ea3f39bd69
InstantX depth flux controlnet.
2024-08-29 02:14:19 -04:00
comfyanonymous
b33cd61070
InstantX canny controlnet.
2024-08-28 19:02:50 -04:00
comfyanonymous
d31e226650
Unify RMSNorm code.
2024-08-28 16:56:38 -04:00
comfyanonymous
38c22e631a
Fix case where model was not properly unloaded in merging workflows.
2024-08-27 19:03:51 -04:00
Chenlei Hu
6bbdcd28ae
Support weight padding on diff weight patch ( #4576 )
2024-08-27 13:55:37 -04:00
comfyanonymous
ab130001a8
Do RMSNorm in native type.
2024-08-27 02:41:56 -04:00
comfyanonymous
2ca8f6e23d
Make the stochastic fp8 rounding reproducible.
2024-08-26 15:12:06 -04:00
comfyanonymous
7985ff88b9
Use less memory in float8 lora patching by doing calculations in fp16.
2024-08-26 14:45:58 -04:00
comfyanonymous
c6812947e9
Fix potential memory leak.
2024-08-26 02:07:32 -04:00
comfyanonymous
9230f65823
Fix some controlnets OOMing when loading.
2024-08-25 05:54:29 -04:00
comfyanonymous
8ae23d8e80
Fix onnx export.
2024-08-23 17:52:47 -04:00
comfyanonymous
7df42b9a23
Fix dora.
2024-08-23 04:58:59 -04:00
comfyanonymous
5d8bbb7281
Cleanup.
2024-08-23 04:06:27 -04:00
comfyanonymous
2c1d2375d6
Fix.
2024-08-23 04:04:55 -04:00
Simon Lui
64ccb3c7e3
Rework IPEX check for future inclusion of XPU into Pytorch upstream and do a bit more optimization of ipex.optimize(). ( #4562 )
2024-08-23 03:59:57 -04:00
Scorpinaus
9465b23432
Added SD15_Inpaint_Diffusers model support for unet_config_from_diffusers_unet function ( #4565 )
2024-08-23 03:57:08 -04:00
comfyanonymous
c0b0da264b
Missing imports.
2024-08-22 17:20:51 -04:00
comfyanonymous
c26ca27207
Move calculate function to comfy.lora
2024-08-22 17:12:00 -04:00
comfyanonymous
7c6bb84016
Code cleanups.
2024-08-22 17:05:12 -04:00
comfyanonymous
c54d3ed5e6
Fix issue with models staying loaded in memory.
2024-08-22 15:58:20 -04:00
comfyanonymous
c7ee4b37a1
Try to fix some lora issues.
2024-08-22 15:32:18 -04:00
David
7b70b266d8
Generalize MacOS version check for force-upcast-attention ( #4548 )
...
This code automatically forces upcasting attention for MacOS versions 14.5 and 14.6. My computer returns the string "14.6.1" for `platform.mac_ver()[0]`, so this generalizes the comparison to catch more versions.
I am running MacOS Sonoma 14.6.1 (latest version) and was seeing black image generation on previously functional workflows after recent software updates. This PR solved the issue for me.
See comfyanonymous/ComfyUI#3521
2024-08-22 13:24:21 -04:00
comfyanonymous
8f60d093ba
Fix issue.
2024-08-22 10:38:24 -04:00
comfyanonymous
843a7ff70c
fp16 is actually faster than fp32 on a GTX 1080.
2024-08-21 23:23:50 -04:00
comfyanonymous
a60620dcea
Fix slow performance on 10 series Nvidia GPUs.
2024-08-21 16:39:02 -04:00
comfyanonymous
015f73dc49
Try a different type of flux fp16 fix.
2024-08-21 16:17:15 -04:00
comfyanonymous
904bf58e7d
Make --fast work on pytorch nightly.
2024-08-21 14:01:41 -04:00
Svein Ove Aas
5f50263088
Replace use of .view with .reshape ( #4522 )
...
When generating images with fp8_e4_m3 Flux and batch size >1, using --fast, ComfyUI throws a "view size is not compatible with input tensor's size and stride" error pointing at the first of these two calls to view.
As reshape is semantically equivalent to view except for working on a broader set of inputs, there should be no downside to changing this. The only difference is that it clones the underlying data in cases where .view would error out. I have confirmed that the output still looks as expected, but cannot confirm that no mutable use is made of the tensors anywhere.
Note that --fast is only marginally faster than the default.
2024-08-21 11:21:48 -04:00
comfyanonymous
03ec517afb
Remove useless line, adjust windows default reserved vram.
2024-08-21 00:47:19 -04:00
comfyanonymous
510f3438c1
Speed up fp8 matrix mult by using better code.
2024-08-20 22:53:26 -04:00
comfyanonymous
ea63b1c092
Simpletrainer lycoris format.
2024-08-20 12:05:13 -04:00
comfyanonymous
9953f22fce
Add --fast argument to enable experimental optimizations.
...
Optimizations that might break things/lower quality will be put behind
this flag first and might be enabled by default in the future.
Currently the only optimization is float8_e4m3fn matrix multiplication on
4000/ADA series Nvidia cards or later. If you have one of these cards you
will see a speed boost when using fp8_e4m3fn flux for example.
2024-08-20 11:55:51 -04:00
comfyanonymous
d1a6bd6845
Support loading long clipl model with the CLIP loader node.
2024-08-20 10:46:36 -04:00
