95d796fc85
Faster VAE loading.
2023-07-29 16:28:30 -04:00
4b957a0010
Initialize the unet directly on the target device.
2023-07-29 14:51:56 -04:00
c910b4a01c
Remove unused code and torchdiffeq dependency.
2023-07-28 21:32:27 -04:00
1141029a4a
Add --disable-metadata argument to disable saving metadata in files.
2023-07-28 12:31:41 -04:00
fbf5c51c1c
Merge branch 'fix_batch_timesteps' of https://github.com/asagi4/ComfyUI
2023-07-27 16:13:48 -04:00
68be24eead
Remove some prints.
2023-07-27 16:12:43 -04:00
1ea4d84691
Fix timestep ranges when batch_size > 1
2023-07-27 21:14:09 +03:00
5379051d16
Fix diffusers VAE loading.
2023-07-26 18:26:39 -04:00
727588d076
Fix some new loras.
2023-07-25 16:39:15 -04:00
4f9b6f39d1
Fix potential issue with Save Checkpoint.
2023-07-25 00:45:20 -04:00
5f75d784a1
Start is now 0.0 and end is now 1.0 for the timestep ranges.
2023-07-24 18:38:17 -04:00
7ff14b62f8
ControlNetApplyAdvanced can now define when controlnet gets applied.
2023-07-24 17:50:49 -04:00
d191c4f9ed
Add a ControlNetApplyAdvanced node.
...
The controlnet can be applied to the positive or negative prompt only by
connecting it correctly.
2023-07-24 13:35:20 -04:00
0240946ecf
Add a way to set which range of timesteps the cond gets applied to.
2023-07-24 09:25:02 -04:00
22f29d66ca
Try to fix memory issue with lora.
2023-07-22 21:38:56 -04:00
67be7eb81d
Nodes can now patch the unet function.
2023-07-22 17:01:12 -04:00
12a6e93171
Del the right object when applying lora.
2023-07-22 11:25:49 -04:00
78e7958d17
Support controlnet in diffusers format.
2023-07-21 22:58:16 -04:00
09386a3697
Fix issue with lora in some cases when combined with model merging.
2023-07-21 21:27:27 -04:00
58b2364f58
Properly support SDXL diffusers unet with UNETLoader node.
2023-07-21 14:38:56 -04:00
0115018695
Print errors and continue when lora weights are not compatible.
2023-07-20 19:56:22 -04:00
4760c29380
Merge branch 'fix-AttributeError-module-'torch'-has-no-attribute-'mps'' of https://github.com/KarryCharon/ComfyUI
2023-07-20 00:34:54 -04:00
0b284f650b
Fix typo.
2023-07-19 10:20:32 -04:00
e032ca6138
Fix ddim issue with older torch versions.
2023-07-19 10:16:00 -04:00
18885f803a
Add MX450 and MX550 to list of cards with broken fp16.
2023-07-19 03:08:30 -04:00
9ba440995a
It's actually possible to torch.compile the unet now.
2023-07-18 21:36:35 -04:00
51d5477579
Add key to indicate checkpoint is v_prediction when saving.
2023-07-18 00:25:53 -04:00
ff6b047a74
Fix device print on old torch version.
2023-07-17 15:18:58 -04:00
9871a15cf9
Enable --cuda-malloc by default on torch 2.0 and up.
...
Add --disable-cuda-malloc to disable it.
2023-07-17 15:12:10 -04:00
55d0fca9fa
--windows-standalone-build now enables --cuda-malloc
2023-07-17 14:10:36 -04:00
1679abd86d
Add a command line argument to enable backend:cudaMallocAsync
2023-07-17 11:00:14 -04:00
3a150bad15
Only calculate randn in some samplers when it's actually being used.
2023-07-17 10:11:08 -04:00
ee8f8ee07f
Fix regression with ddim and uni_pc when batch size > 1.
2023-07-17 09:35:19 -04:00
3ded1a3a04
Refactor of sampler code to deal more easily with different model types.
2023-07-17 01:22:12 -04:00
5f57362613
Lower lora ram usage when in normal vram mode.
2023-07-16 02:59:04 -04:00
490771b7f4
Speed up lora loading a bit.
2023-07-15 13:25:22 -04:00
50b1180dde
Fix CLIPSetLastLayer not reverting when removed.
2023-07-15 01:41:21 -04:00
6fb084f39d
Reduce floating point rounding errors in loras.
2023-07-15 00:53:00 -04:00
91ed2815d5
Add a node to merge CLIP models.
2023-07-14 02:41:18 -04:00
b2f03164c7
Prevent the clip_g position_ids key from being saved in the checkpoint.
...
This is to make it match the official checkpoint.
2023-07-12 20:15:02 -04:00
46dc050c9f
Fix potential tensors being on different devices issues.
2023-07-12 19:29:27 -04:00
3e2309f149
fix mps miss import
2023-07-12 10:06:34 +08:00
606a537090
Support SDXL embedding format with 2 CLIP.
2023-07-10 10:34:59 -04:00
6ad0a6d7e2
Don't patch weights when multiplier is zero.
2023-07-09 17:46:56 -04:00
d5323d16e0
latent2rgb matrix for SDXL.
2023-07-09 13:59:09 -04:00
0ae81c03bb
Empty cache after model unloading for normal vram and lower.
2023-07-09 09:56:03 -04:00
d3f5998218
Support loading clip_g from diffusers in CLIP Loader nodes.
2023-07-09 09:33:53 -04:00
a9a4ba7574
Fix merging not working when model2 of model merge node was a merge.
2023-07-08 22:31:10 -04:00
bb5fbd29e9
Merge branch 'condmask-fix' of https://github.com/vmedea/ComfyUI
2023-07-07 01:52:25 -04:00
e7bee85df8
Add arguments to run the VAE in fp16 or bf16 for testing.
2023-07-06 23:23:46 -04:00
608fcc2591
Fix bug with weights when prompt is long.
2023-07-06 02:43:40 -04:00
ddc6f12ad5
Disable autocast in unet for increased speed.
2023-07-05 21:58:29 -04:00
603f02d613
Fix loras not working when loading checkpoint with config.
2023-07-05 19:42:24 -04:00
af7a49916b
Support loading unet files in diffusers format.
2023-07-05 17:38:59 -04:00
e57cba4c61
Add gpu variations of the sde samplers that are less deterministic
...
but faster.
2023-07-05 01:39:38 -04:00
f81b192944
Add logit scale parameter so it's present when saving the checkpoint.
2023-07-04 23:01:28 -04:00
acf95191ff
Properly support SDXL diffusers loras for unet.
2023-07-04 21:15:23 -04:00
c61a95f9f7
Fix size check for conditioning mask
...
The wrong dimensions were being checked, [1] and [2] are the image size.
not [2] and [3]. This results in an out-of-bounds error if one of them
actually matches.
2023-07-04 16:34:42 +02:00
8d694cc450
Fix issue with OSX.
2023-07-04 02:09:02 -04:00
c3e96e637d
Pass device to CLIP model.
2023-07-03 16:09:37 -04:00
5e6bc824aa
Allow passing custom path to clip-g and clip-h.
2023-07-03 15:45:04 -04:00
dc9d1f31c8
Improvements for OSX.
2023-07-03 00:08:30 -04:00
103c487a89
Cleanup.
2023-07-02 11:58:23 -04:00
2c4e0b49b7
Switch to fp16 on some cards when the model is too big.
2023-07-02 10:00:57 -04:00
6f3d9f52db
Add a --force-fp16 argument to force fp16 for testing.
2023-07-01 22:42:35 -04:00
1c1b0e7299
--gpu-only now keeps the VAE on the device.
2023-07-01 15:22:40 -04:00
ce35d8c659
Lower latency by batching some text encoder inputs.
2023-07-01 15:07:39 -04:00
3b6fe51c1d
Leave text_encoder on the CPU when it can handle it.
2023-07-01 14:38:51 -04:00
b6a60fa696
Try to keep text encoders loaded and patched to increase speed.
...
load_model_gpu() is now used with the text encoder models instead of just
the unet.
2023-07-01 13:28:07 -04:00
97ee230682
Make highvram and normalvram shift the text encoders to vram and back.
...
This is faster on big text encoder models than running it on the CPU.
2023-07-01 12:37:23 -04:00
5a9ddf94eb
LoraLoader node now caches the lora file between executions.
2023-06-29 23:40:51 -04:00
9920367d3c
Fix embeddings not working with --gpu-only
2023-06-29 20:43:06 -04:00
62db11683b
Move unet to device right after loading on highvram mode.
2023-06-29 20:43:06 -04:00
4376b125eb
Remove useless code.
2023-06-29 00:26:33 -04:00
89120f1fbe
This is unused but it should be 1280.
2023-06-28 18:04:23 -04:00
2c7c14de56
Support for SDXL text encoder lora.
2023-06-28 02:22:49 -04:00
fcef47f06e
Fix bug.
2023-06-28 00:38:07 -04:00
8248babd44
Use pytorch attention by default on nvidia when xformers isn't present.
...
Add a new argument --use-quad-cross-attention
2023-06-26 13:03:44 -04:00
9b93b920be
Add CheckpointSave node to save checkpoints.
...
The created checkpoints contain workflow metadata that can be loaded by
dragging them on top of the UI or loading them with the "Load" button.
Checkpoints will be saved in fp16 or fp32 depending on the format ComfyUI
is using for inference on your hardware. To force fp32 use: --force-fp32
Anything that patches the model weights like merging or loras will be
saved.
The output directory is currently set to: output/checkpoints but that might
change in the future.
2023-06-26 12:22:27 -04:00
b72a7a835a
Support loras based on the stability unet implementation.
2023-06-26 02:56:11 -04:00
c71a7e6b20
Fix ddim + inpainting not working.
2023-06-26 00:48:48 -04:00
4eab00e14b
Set the seed in the SDE samplers to make them more reproducible.
2023-06-25 03:04:57 -04:00
cef6aa62b2
Add support for TAESD decoder for SDXL.
2023-06-25 02:38:14 -04:00
20f579d91d
Add DualClipLoader to load clip models for SDXL.
...
Update LoadClip to load clip models for SDXL refiner.
2023-06-25 01:40:38 -04:00
b7933960bb
Fix CLIPLoader node.
2023-06-24 13:56:46 -04:00
78d8035f73
Fix bug with controlnet.
2023-06-24 11:02:38 -04:00
05676942b7
Add some more transformer hooks and move tomesd to comfy_extras.
...
Tomesd now uses q instead of x to decide which tokens to merge because
it seems to give better results.
2023-06-24 03:30:22 -04:00
fa28d7334b
Remove useless code.
2023-06-23 12:35:26 -04:00
8607c2d42d
Move latent scale factor from VAE to model.
2023-06-23 02:33:31 -04:00
30a3861946
Fix bug when yaml config has no clip params.
2023-06-23 01:12:59 -04:00
9e37f4c7d5
Fix error with ClipVision loader node.
2023-06-23 01:08:05 -04:00
9f83b098c9
Don't merge weights when shapes don't match and print a warning.
2023-06-22 19:08:31 -04:00
f87ec10a97
Support base SDXL and SDXL refiner models.
...
Large refactor of the model detection and loading code.
2023-06-22 13:03:50 -04:00
9fccf4aa03
Add original_shape parameter to transformer patch extra_options.
2023-06-21 13:22:01 -04:00
51581dbfa9
Fix last commits causing an issue with the text encoder lora.
2023-06-20 19:44:39 -04:00
8125b51a62
Keep a set of model_keys for faster add_patches.
2023-06-20 19:08:48 -04:00
45beebd33c
Add a type of model patch useful for model merging.
2023-06-20 17:34:11 -04:00
036a22077c
Fix k_diffusion math being off by a tiny bit during txt2img.
2023-06-19 15:28:54 -04:00
8883cb0f67
Add a way to set patches that modify the attn2 output.
...
Change the transformer patches function format to be more future proof.
2023-06-18 22:58:22 -04:00
cd930d4e7f
pop clip vision keys after loading them.
2023-06-18 21:21:17 -04:00
c9e4a8c9e5
Not needed anymore.
2023-06-18 13:06:59 -04:00
fb4bf7f591
This is not needed anymore and causes issues with alphas_cumprod.
2023-06-18 03:18:25 -04:00
45be2e92c1
Fix DDIM v-prediction.
2023-06-17 20:48:21 -04:00
e6e50ab2dd
Fix an issue when alphas_comprod are half floats.
2023-06-16 17:16:51 -04:00
ae43f09ef7
All the unet weights should now be initialized with the right dtype.
2023-06-15 18:42:30 -04:00
f7edcfd927
Add a --gpu-only argument to keep and run everything on the GPU.
...
Make the CLIP model work on the GPU.
2023-06-15 15:38:52 -04:00
7bf89ba923
Initialize more unet weights as the right dtype.
2023-06-15 15:00:10 -04:00
e21d9ad445
Initialize transformer unet block weights in right dtype at the start.
2023-06-15 14:29:26 -04:00
bb1f45d6e8
Properly disable weight initialization in clip models.
2023-06-14 20:13:08 -04:00
21f04fe632
Disable default weight values in unet conv2d for faster loading.
2023-06-14 19:46:08 -04:00
9d54066ebc
This isn't needed for inference.
2023-06-14 13:05:08 -04:00
fa2cca056c
Don't initialize CLIPVision weights to default values.
2023-06-14 12:57:02 -04:00
6b774589a5
Set model to fp16 before loading the state dict to lower ram bump.
2023-06-14 12:48:02 -04:00
0c7cad404c
Don't initialize clip weights to default values.
2023-06-14 12:47:36 -04:00
6971646b8b
Speed up model loading a bit.
...
Default pytorch Linear initializes the weights which is useless and slow.
2023-06-14 12:09:41 -04:00
388567f20b
sampler_cfg_function now uses a dict for the argument.
...
This means arguments can be added without issues.
2023-06-13 16:10:36 -04:00
ff9b22d79e
Turn on safe load for a few models.
2023-06-13 10:12:03 -04:00
735ac4cf81
Remove pytorch_lightning dependency.
2023-06-13 10:11:33 -04:00
2b14041d4b
Remove useless code.
2023-06-13 02:40:58 -04:00
274dff3257
Remove more useless files.
2023-06-13 02:22:19 -04:00
f0a2b81cd0
Cleanup: Remove a bunch of useless files.
2023-06-13 02:19:08 -04:00
f8c5931053
Split the batch in VAEEncode if there's not enough memory.
2023-06-12 00:21:50 -04:00
c069fc0730
Auto switch to tiled VAE encode if regular one runs out of memory.
2023-06-11 23:25:39 -04:00
c64ca8c0b2
Refactor unCLIP noise augment out of samplers.py
2023-06-11 04:01:18 -04:00
de142eaad5
Simpler base model code.
2023-06-09 12:31:16 -04:00
23cf8ca7c5
Fix bug when embedding gets ignored because of mismatched size.
2023-06-08 23:48:14 -04:00
0e425603fb
Small refactor.
2023-06-06 13:23:01 -04:00
a3a713b6c5
Refactor previews into one command line argument.
...
Clean up a few things.
2023-06-06 02:13:05 -04:00
3e17971acb
preview method autodetection
2023-06-05 18:59:10 -05:00
d5a28fadaa
Add latent2rgb preview
2023-06-05 18:39:56 -05:00
48f7ec750c
Make previews into cli option
2023-06-05 13:19:02 -05:00
b4f434ee66
Preview sampled images with TAESD
2023-06-05 09:20:17 -05:00
fed0a4dd29
Some comments to say what the vram state options mean.
2023-06-04 17:51:04 -04:00
0a5fefd621
Cleanups and fixes for model_management.py
...
Hopefully fix regression on MPS and CPU.
2023-06-03 11:05:37 -04:00
700491d81a
Implement global average pooling for controlnet.
2023-06-03 01:49:03 -04:00
67892b5ac5
Refactor and improve model_management code related to free memory.
2023-06-02 15:21:33 -04:00
499641ebf1
More accurate total
2023-06-02 00:14:41 -05:00
b5dd15c67a
System stats endpoint
2023-06-01 23:26:23 -05:00
5c38958e49
Tweak lowvram model memory so it's closer to what it was before.
2023-06-01 04:04:35 -04:00
94680732d3
Empty cache on mps.
2023-06-01 03:52:51 -04:00
03da8a3426
This is useless for inference.
2023-05-31 13:03:24 -04:00
eb448dd8e1
Auto load model in lowvram if not enough memory.
2023-05-30 12:36:41 -04:00
b9818eb910
Add route to get safetensors metadata:
...
/view_metadata/loras?filename=lora.safetensors
2023-05-29 02:48:50 -04:00
a532888846
Support VAEs in diffusers format.
2023-05-28 02:02:09 -04:00
0fc483dcfd
Refactor diffusers model convert code to be able to reuse it.
2023-05-28 01:55:40 -04:00
eb4bd7711a
Remove einops.
2023-05-25 18:42:56 -04:00
87ab25fac7
Do operations in same order as the one it replaces.
2023-05-25 18:31:27 -04:00
2b1fac9708
Merge branch 'master' of https://github.com/BlenderNeko/ComfyUI
2023-05-25 14:44:16 -04:00
e1278fa925
Support old pytorch versions that don't have weights_only.
2023-05-25 13:30:59 -04:00
8b4b0c3188
vecorized bislerp
2023-05-25 19:23:47 +02:00
b8ccbec6d8
Various improvements to bislerp.
2023-05-23 11:40:24 -04:00
34887b8885
Add experimental bislerp algorithm for latent upscaling.
...
It's like bilinear but with slerp.
2023-05-23 03:12:56 -04:00
6cc450579b
Auto transpose images from exif data.
2023-05-22 00:22:24 -04:00
dc198650c0
sample_dpmpp_2m_sde no longer crashes when step == 1.
2023-05-21 11:34:29 -04:00
069657fbf3
Add DPM-Solver++(2M) SDE and exponential scheduler.
...
exponential scheduler is the one recommended with this sampler.
2023-05-21 01:46:03 -04:00
b8636a44aa
Make scaled_dot_product switch to sliced attention on OOM.
2023-05-20 16:01:02 -04:00
797c4e8d3b
Simplify and improve some vae attention code.
2023-05-20 15:07:21 -04:00
ef815ba1e2
Switch default scheduler to normal.
2023-05-15 00:29:56 -04:00
68d12b530e
Merge branch 'tiled_sampler' of https://github.com/BlenderNeko/ComfyUI
2023-05-14 15:39:39 -04:00
3a1f47764d
Print the torch device that is used on startup.
2023-05-13 17:11:27 -04:00
1201d2eae5
Make nodes map over input lists ( #579 )
...
* allow nodes to map over lists
* make work with IS_CHANGED and VALIDATE_INPUTS
* give list outputs distinct socket shape
* add rebatch node
* add batch index logic
* add repeat latent batch
* deal with noise mask edge cases in latentfrombatch
2023-05-13 11:15:45 -04:00
19c014f429
comment out annoying print statement
2023-05-12 23:57:40 +02:00
d9e088ddfd
minor changes for tiled sampler
2023-05-12 23:49:09 +02:00
f7c0f75d1f
Auto batching improvements.
...
Try batching when cond sizes don't match with smart padding.
2023-05-10 13:59:24 -04:00
314e526c5c
Not needed anymore because sampling works with any latent size.
2023-05-09 12:18:18 -04:00
c6e34963e4
Make t2i adapter work with any latent resolution.
2023-05-08 18:15:19 -04:00
a1f12e370d
Merge branch 'autostart' of https://github.com/EllangoK/ComfyUI
2023-05-07 17:19:03 -04:00
6fc4917634
Make maximum_batch_area take into account python2.0 attention function.
...
More conservative xformers maximum_batch_area.
2023-05-06 19:58:54 -04:00
678f933d38
maximum_batch_area for xformers.
...
Remove useless code.
2023-05-06 19:28:46 -04:00
8e03c789a2
auto-launch cli arg
2023-05-06 16:59:40 -04:00
cb1551b819
Lowvram mode for gligen and fix some lowvram issues.
2023-05-05 18:11:41 -04:00
af9cc1fb6a
Search recursively in subfolders for embeddings.
2023-05-05 01:28:48 -04:00
6ee11d7bc0
Fix import.
2023-05-05 00:19:35 -04:00
bae4fb4a9d
Fix imports.
2023-05-04 18:10:29 -04:00
fcf513e0b6
Refactor.
2023-05-03 17:48:35 -04:00
a74e176a24
Merge branch 'tiled-progress' of https://github.com/pythongosssss/ComfyUI
2023-05-03 16:24:56 -04:00
5eeecf3fd5
remove unused import
2023-05-03 18:21:23 +01:00
8912623ea9
use comfy progress bar
2023-05-03 18:19:22 +01:00
908dc1d5a8
Add a total_steps value to sampler callback.
2023-05-03 12:58:10 -04:00
fdf57325f4
Merge remote-tracking branch 'origin/master' into tiled-progress
2023-05-03 17:33:42 +01:00
27df74101e
reduce duplication
2023-05-03 17:33:19 +01:00
93c64afaa9
Use sampler callback instead of tqdm hook for progress bar.
2023-05-02 23:00:49 -04:00
06ad35b493
added progress to encode + upscale
2023-05-02 19:18:07 +01:00
ba8a4c3667
Change latent resolution step to 8.
2023-05-02 14:17:51 -04:00
66c8aa5c3e
Make unet work with any input shape.
2023-05-02 13:31:43 -04:00
9c335a553f
LoKR support.
2023-05-01 18:18:23 -04:00
d3293c8339
Properly disable all progress bars when disable_pbar=True
2023-05-01 15:52:17 -04:00
a2e18b1504
allow disabling of progress bar when sampling
2023-04-30 18:59:58 +02:00
071011aebe
Mask strength should be separate from area strength.
2023-04-29 20:06:53 -04:00
870fae62e7
Merge branch 'condition_by_mask_node' of https://github.com/guill/ComfyUI
2023-04-29 15:05:18 -04:00
af02393c2a
Default to sampling entire image
...
By default, when applying a mask to a condition, the entire image will
still be used for sampling. The new "set_area_to_bounds" option on the
node will allow the user to automatically limit conditioning to the
bounds of the mask.
I've also removed the dependency on torchvision for calculating bounding
boxes. I've taken the opportunity to fix some frustrating details in the
other version:
1. An all-0 mask will no longer cause an error
2. Indices are returned as integers instead of floats so they can be
used to index into tensors.
2023-04-29 00:16:58 -07:00
056e5545ff
Don't try to get vram from xpu or cuda when directml is enabled.
2023-04-29 00:28:48 -04:00
2ca934f7d4
You can now select the device index with: --directml id
...
Like this for example: --directml 1
2023-04-28 16:51:35 -04:00
3baded9892
Basic torch_directml support. Use --directml to use it.
2023-04-28 14:28:57 -04:00
e214c917ae
Add Condition by Mask node
...
This PR adds support for a Condition by Mask node. This node allows
conditioning to be limited to a non-rectangle area.
2023-04-27 20:03:27 -07:00
5a971cecdb
Add callback to sampler function.
...
Callback format is: callback(step, x0, x)
2023-04-27 04:38:44 -04:00
aa57136dae
Some fixes to the batch masks PR.
2023-04-25 01:12:40 -04:00
c50208a703
Refactor more code to sample.py
2023-04-24 23:25:51 -04:00
7983b3a975
This is cleaner this way.
2023-04-24 22:45:35 -04:00
0b07b2cc0f
gligen tuple
2023-04-24 21:47:57 +02:00
c8c9926eeb
Add progress to vae decode tiled
2023-04-24 11:55:44 +01:00
d9b1595f85
made sample functions more explicit
2023-04-24 12:53:10 +02:00
5818539743
add docstrings
2023-04-23 20:09:09 +02:00
8d2de420d3
Merge branch 'master' of https://github.com/BlenderNeko/ComfyUI
2023-04-23 20:02:18 +02:00
2a09e2aa27
refactor/split various bits of code for sampling
2023-04-23 20:02:08 +02:00
5282f56434
Implement Linear hypernetworks.
...
Add a HypernetworkLoader node to use hypernetworks.
2023-04-23 12:35:25 -04:00
6908f9c949
This makes pytorch2.0 attention perform a bit faster.
2023-04-22 14:30:39 -04:00
907010e082
Remove some useless code.
2023-04-20 23:58:25 -04:00
96b57a9ad6
Don't pass adm to model when it doesn't support it.
2023-04-19 21:11:38 -04:00
3696d1699a
Add support for GLIGEN textbox model.
2023-04-19 11:06:32 -04:00
884ea653c8
Add a way for nodes to set a custom CFG function.
2023-04-17 11:05:15 -04:00
73c3e11e83
Fix model_management import so it doesn't get executed twice.
2023-04-15 19:04:33 -04:00
81d1f00df3
Some refactoring: from_tokens -> encode_from_tokens
2023-04-15 18:46:58 -04:00
719c26c3c9
Merge branch 'master' of https://github.com/BlenderNeko/ComfyUI
2023-04-15 14:16:50 -04:00
d0b1b6c6bf
fixed improper padding
2023-04-15 19:38:21 +02:00
deb2b93e79
Move code to empty gpu cache to model_management.py
2023-04-15 11:19:07 -04:00
04d9bc13af
Safely load pickled embeds that don't load with weights_only=True.
2023-04-14 15:33:43 -04:00
da115bd78d
ensure backwards compat with optional args
2023-04-14 21:16:55 +02:00
752f7a162b
align behavior with old tokenize function
2023-04-14 21:02:45 +02:00
334aab05e5
Don't stop workflow if loading embedding fails.
2023-04-14 13:54:00 -04:00
73175cf58c
split tokenizer from encoder
2023-04-13 22:06:50 +02:00
8489cba140
add unique ID per word/embedding for tokenizer
2023-04-13 22:01:01 +02:00
92eca60ec9
Fix for new transformers version.
2023-04-09 15:55:21 -04:00
1e1875f674
Print xformers version and warning about 0.0.18
2023-04-09 01:31:47 -04:00
7e254d2f69
Clarify what --windows-standalone-build does.
2023-04-07 15:52:56 -04:00
44fea05064
Cleanup.
2023-04-07 02:31:46 -04:00
58ed0f2da4
Fix loading SD1.5 diffusers checkpoint.
2023-04-07 01:30:33 -04:00
8b9ac8fedb
Merge branch 'master' of https://github.com/sALTaccount/ComfyUI
2023-04-07 01:03:43 -04:00
64557d6781
Add a --force-fp32 argument to force fp32 for debugging.
2023-04-07 00:27:54 -04:00
bceccca0e5
Small refactor.
2023-04-06 23:53:54 -04:00
28a7205739
Merge branch 'ipex' of https://github.com/kwaa/ComfyUI-IPEX
2023-04-06 23:45:29 -04:00
05eeaa2de5
Merge branch 'master' into ipex
2023-04-07 09:11:30 +08:00
28fff5d1db
fixes lack of support for multi configs
...
also adds some metavars to argarse
2023-04-06 19:06:39 -04:00
f84f2508cc
Rename the cors parameter to something more verbose.
2023-04-06 15:24:55 -04:00
48efae1608
makes cors a cli parameter
2023-04-06 15:06:22 -04:00
01c1fc669f
set listen flag to listen on all if specifed
2023-04-06 13:19:00 -04:00
3e2608e12b
Fix auto lowvram detection on CUDA
2023-04-06 15:44:05 +08:00
60127a8304
diffusers loader
2023-04-05 23:57:31 -07:00
7cb924f684
Use separate variables instead of `vram_state`
2023-04-06 14:24:47 +08:00
84b9c0ac2f
Import intel_extension_for_pytorch as ipex
2023-04-06 12:27:22 +08:00
e5e587b1c0
seperates out arg parser and imports args
2023-04-05 23:41:23 -04:00
37713e3b0a
Add basic XPU device support
...
closed #387
2023-04-05 21:22:14 +08:00
e46b1c3034
Disable xformers in VAE when xformers == 0.0.18
2023-04-04 22:22:02 -04:00
1718730e80
Ignore embeddings when sizes don't match and print a WARNING.
2023-04-04 11:49:29 -04:00
23524ad8c5
Remove print.
2023-04-03 22:58:54 -04:00
539ff487a8
Pull latest tomesd code from upstream.
2023-04-03 15:49:28 -04:00
f50b1fec69
Add noise augmentation setting to unCLIPConditioning.
2023-04-03 13:50:29 -04:00
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.
2023-04-01 23:19:15 -04:00
0d972b85e6
This seems to give better quality in tome.
2023-03-31 18:36:18 -04:00
18a6c1db33
Add a TomePatchModel node to the _for_testing section.
...
Tome increases sampling speed at the expense of quality.
2023-03-31 17:19:58 -04:00
61ec3c9d5d
Add a way to pass options to the transformers blocks.
2023-03-31 13:04:39 -04:00
afd65d3819
Fix noise mask not working with > 1 batch size on ksamplers.
2023-03-30 03:50:12 -04:00
b2554bc4dd
Split VAE decode batches depending on free memory.
2023-03-29 02:24:37 -04:00
0d65cb17b7
Fix ddim_uniform crashing with 37 steps.
2023-03-28 16:29:35 -04:00
f55755f0d2
code cleanup
2023-03-27 06:48:09 +02:00
cf0098d539
no lowvram state if cpu only
2023-03-27 04:51:18 +02:00
f5365c9c81
Fix ddim for Mac: #264
2023-03-26 00:36:54 -04:00
4adcea7228
I don't think controlnets were being handled correctly by MPS.
2023-03-24 14:33:16 -04:00
3c6ff8821c
Merge branch 'master' of https://github.com/GaidamakUA/ComfyUI
2023-03-24 13:56:43 -04:00
fc71e7ea08
Fixed typo
2023-03-24 19:39:55 +02:00
7f0fd99b5d
Make ddim work with --cpu
2023-03-24 11:39:51 -04:00
4b943d2b60
Removed unnecessary comment
2023-03-24 14:15:30 +02:00
89fd5ed574
Added MPS device support
2023-03-24 14:12:56 +02:00
dd095efc2c
Support loha that use cp decomposition.
2023-03-23 04:32:25 -04:00
94a7c895f4
Add loha support.
2023-03-23 03:40:12 -04:00
3ed4a4e4e6
Try again with vae tiled decoding if regular fails because of OOM.
2023-03-22 14:49:00 -04:00
4039616ca6
Less seams in tiled outputs at the cost of more processing.
2023-03-22 03:29:09 -04:00
c692509c2b
Try to improve VAEEncode memory usage a bit.
2023-03-22 02:45:18 -04:00
9d0665c8d0
Add laptop quadro cards to fp32 list.
2023-03-21 16:57:35 -04:00
cc309568e1
Add support for locon mid weights.
2023-03-21 14:51:51 -04:00
edfc4ca663
Try to fix a vram issue with controlnets.
2023-03-19 10:50:38 -04:00
b4b21be707
Fix area composition feathering not working properly.
2023-03-19 02:00:52 -04:00
50099bcd96
Support multiple paths for embeddings.
2023-03-18 03:08:43 -04:00
2e73367f45
Merge T2IAdapterLoader and ControlNetLoader.
...
Workflows will be auto updated.
2023-03-17 18:17:59 -04:00
ee46bef03a
Make --cpu have priority over everything else.
2023-03-13 21:30:01 -04:00
0e836d525e
use half() on fp16 models loaded with config.
2023-03-13 21:12:48 -04:00
986dd820dc
Use half() function on model when loading in fp16.
2023-03-13 20:58:09 -04:00
54dbfaf2ec
Remove omegaconf dependency and some ci changes.
2023-03-13 14:49:18 -04:00
83f23f82b8
Add pytorch attention support to VAE.
2023-03-13 12:45:54 -04:00
a256a2abde
--disable-xformers should not even try to import xformers.
2023-03-13 11:36:48 -04:00
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.
2023-03-12 15:44:16 -04:00
e33dc2b33b
Add a VAEEncodeTiled node.
2023-03-11 15:28:15 -05:00
1de86851b1
Try to fix memory issue.
2023-03-11 15:15:13 -05:00
2b1fce2943
Make tiled_scale work for downscaling.
2023-03-11 14:58:55 -05:00
9db2e97b47
Tiled upscaling with the upscale models.
2023-03-11 14:04:13 -05:00
cd64111c83
Add locon support.
2023-03-09 21:41:24 -05:00
c70f0ac64b
SD2.x controlnets now work.
2023-03-08 01:13:38 -05:00
19415c3ace
Relative imports to test something.
2023-03-07 11:00:35 -05:00
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
2023-03-06 11:41:40 -05:00
501f19eec6
Fix clip_skip no longer being loaded from yaml file.
2023-03-06 11:34:02 -05:00
afff30fc0a
Add --cpu to use the cpu for inference.
2023-03-06 10:50:50 -05:00
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.
2023-03-05 18:39:25 -05:00
cc8baf1080
Make VAE use common function to get free memory.
2023-03-05 14:20:07 -05:00
798c90e1c0
Fix pytorch 2.0 cross attention not working.
2023-03-05 14:14:54 -05:00
16130c7546
Add support for new colour T2I adapter model.
2023-03-03 19:13:07 -05:00
9d00235b41
Update T2I adapter code to latest.
2023-03-03 18:46:49 -05:00
ebfcf0a9c9
Fix issue.
2023-03-03 13:18:01 -05:00
4215206281
Add a node to set CLIP skip.
...
Use a more simple way to detect if the model is -v prediction.
2023-03-03 13:04:36 -05:00
fed315a76a
To be really simple CheckpointLoaderSimple should pick the right type.
2023-03-03 11:07:10 -05:00
94bb0375b0
New CheckpointLoaderSimple to load checkpoints without a config.
2023-03-03 03:37:35 -05:00
c1f5855ac1
Make some cross attention functions work on the CPU.
2023-03-03 03:27:33 -05:00
1a612e1c74
Add some pytorch scaled_dot_product_attention code for testing.
...
--use-pytorch-cross-attention to use it.
2023-03-02 17:01:20 -05:00
69cc75fbf8
Add a way to interrupt current processing in the backend.
2023-03-02 14:42:03 -05:00
9502ee45c3
Hopefully fix a strange issue with xformers + lowvram.
2023-02-28 13:48:52 -05:00
b31daadc03
Try to improve memory issues with del.
2023-02-28 12:27:43 -05:00
2c5f0ec681
Small adjustment.
2023-02-27 20:04:18 -05:00
86721d5158
Enable highvram automatically when vram >> ram
2023-02-27 19:57:39 -05:00
75fa162531
Remove sample_ from some sampler names.
...
Old workflows will still work.
2023-02-27 01:43:06 -05:00
9f4214e534
Preparing to add another function to load checkpoints.
2023-02-26 17:29:01 -05:00
3cd7d84b53
Fix uni_pc sampler not working with 1 or 2 steps.
2023-02-26 04:01:01 -05:00
dfb397e034
Fix multiple controlnets not working.
2023-02-25 22:12:22 -05:00
af3cc1b5fb
Fixed issue when batched image was used as a controlnet input.
2023-02-25 14:57:28 -05:00
d2da346b0b
Fix missing variable.
2023-02-25 12:19:03 -05:00
4e6b83a80a
Add a T2IAdapterLoader node to load T2I-Adapter models.
...
They are loaded as CONTROL_NET objects because they are similar.
2023-02-25 01:24:56 -05:00
fcb25d37db
Prepare for t2i adapter.
2023-02-24 23:36:17 -05:00
cf5a211efc
Remove some useless imports
2023-02-24 12:36:55 -05:00
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.
2023-02-24 02:10:10 -05:00
62df8dd62a
Add a node to load diff controlnets.
2023-02-22 23:22:03 -05:00
f04dc2c2f4
Implement DDIM sampler.
2023-02-22 21:10:19 -05:00
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.
2023-02-22 02:21:06 -05:00
c9daec4c89
Remove prints that are useless when xformers is enabled.
2023-02-21 22:16:13 -05:00
a7328e4945
Add uni_pc bh2 variant.
2023-02-21 16:11:48 -05:00
d80af7ca30
ControlNetApply now stacks.
...
It can be used to apply multiple control nets at the same time.
2023-02-21 01:18:53 -05:00
00a9189e30
Support old pytorch.
2023-02-19 16:59:03 -05:00
137ae2606c
Support people putting commas after the embedding name in the prompt.
2023-02-19 02:50:48 -05:00
2326ff1263
Add: --highvram for when you want models to stay on the vram.
2023-02-17 21:27:02 -05:00
09f1d76ed8
Fix an OOM issue.
2023-02-17 16:21:01 -05:00
d66415c021
Low vram mode for controlnets.
2023-02-17 15:48:16 -05:00
220a72d36b
Use fp16 for fp16 control nets.
2023-02-17 15:31:38 -05:00
6135a21ee8
Add a way to control controlnet strength.
2023-02-16 18:08:01 -05:00
4efa67fa12
Add ControlNet support.
2023-02-16 10:38:08 -05:00
bc69fb5245
Use inpaint models the proper way by using VAEEncodeForInpaint.
2023-02-15 20:44:51 -05:00
cef2cc3cb0
Support for inpaint models.
2023-02-15 16:38:20 -05:00
07db00355f
Add masks to samplers code for inpainting.
2023-02-15 13:16:38 -05:00
e3451cea4f
uni_pc now works with KSamplerAdvanced return_with_leftover_noise.
2023-02-13 12:29:21 -05:00
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.
2023-02-11 14:59:42 -05:00
f10b8948c3
768-v support for uni_pc sampler.
2023-02-11 04:34:58 -05:00
ce0aeb109e
Remove print.
2023-02-11 03:41:40 -05:00
5489d5af04
Add uni_pc sampler to KSampler* nodes.
2023-02-11 03:34:09 -05:00
1a4edd19cd
Fix overflow issue with inplace softmax.
2023-02-10 11:47:41 -05:00
509c7dfc6d
Use real softmax in split op to fix issue with some images.
2023-02-10 03:13:49 -05:00
7e1e193f39
Automatically enable lowvram mode if vram is less than 4GB.
...
Use: --normalvram to disable it.
2023-02-10 00:47:56 -05:00
324273fff2
Fix embedding not working when on new line.
2023-02-09 14:12:02 -05:00
1f6a467e92
Update ldm dir with latest upstream stable diffusion changes.
2023-02-09 13:47:36 -05:00
773cdabfce
Same thing but for the other places where it's used.
2023-02-09 12:43:29 -05:00
df40d4f3bf
torch.cuda.OutOfMemoryError is not present on older pytorch versions.
2023-02-09 12:33:27 -05:00
e8c499ddd4
Split optimization for VAE attention block.
2023-02-08 22:04:20 -05:00
5b4e312749
Use inplace operations for less OOM issues.
2023-02-08 22:04:13 -05:00
3fd87cbd21
Slightly smarter batching behaviour.
...
Try to keep batch sizes more consistent which seems to improve things on
AMD GPUs.
2023-02-08 17:28:43 -05:00
bbdcf0b737
Use relative imports for k_diffusion.
2023-02-08 16:51:19 -05:00
comfyanonymous
asagi4
KarryCharon
mara
space-nuko
BlenderNeko
EllangoK
pythongosssss
Jacob Segal
藍+85CD
sALTaccount
Francesco Yoshi Gobbo
Yurii Mazurevich
edikius