c837a173fa
Fix some memory issues in sub quad attention.
2023-10-30 15:30:49 -04:00
125b03eead
Fix some OOM issues with split attention.
2023-10-30 13:14:11 -04:00
6ec3f12c6e
Support SSD1B model and make it easier to support asymmetric unets.
2023-10-27 14:45:15 -04:00
a373367b0c
Fix some OOM issues with split and sub quad attention.
2023-10-25 20:17:28 -04:00
8b65f5de54
attention_basic now works with hypertile.
2023-10-22 03:59:53 -04:00
e6bc42df46
Make sub_quad and split work with hypertile.
2023-10-22 03:51:29 -04:00
9906e3efe3
Make xformers work with hypertile.
2023-10-21 13:23:03 -04:00
d44a2de49f
Make VAE code closer to sgm.
2023-10-17 15:18:51 -04:00
23680a9155
Refactor the attention stuff in the VAE.
2023-10-17 03:19:29 -04:00
bb064c9796
Add a separate optimized_attention_masked function.
2023-10-16 02:31:24 -04:00
9a55dadb4c
Refactor code so model can be a dtype other than fp32 or fp16.
2023-10-13 14:41:17 -04:00
88733c997f
pytorch_attention_enabled can now return True when xformers is enabled.
2023-10-11 21:30:57 -04:00
ac7d8cfa87
Allow attn_mask in attention_pytorch.
2023-10-11 20:38:48 -04:00
1a4bd9e9a6
Refactor the attention functions.
...
There's no reason for the whole CrossAttention object to be repeated when
only the operation in the middle changes.
2023-10-11 20:38:48 -04:00
fff491b032
Model patches can now know which batch is positive and negative.
2023-09-27 12:04:07 -04:00
446caf711c
Sampling code refactor.
2023-09-26 13:45:15 -04:00
afa2399f79
Add a way to set output block patches to modify the h and hsp.
2023-09-22 20:26:47 -04:00
94e4fe39d8
This isn't used anywhere.
2023-09-15 12:03:03 -04:00
1938f5c5fe
Add a force argument to soft_empty_cache to force a cache empty.
2023-09-04 00:58:18 -04:00
2da73b7073
Revert changes in comfy/ldm/modules/diffusionmodules/util.py, which is unused.
2023-09-02 20:07:52 -07:00
4a0c4ce4ef
Some fixes to generalize CUDA specific functionality to Intel or other GPUs.
2023-09-02 18:22:10 -07:00
0e3b641172
Remove xformers related print.
2023-09-01 02:12:03 -04:00
bed116a1f9
Remove optimization that caused border.
2023-08-29 11:21:36 -04:00
1c794a2161
Fallback to slice attention if xformers doesn't support the operation.
2023-08-27 22:24:42 -04:00
d935ba50c4
Make --bf16-vae work on torch 2.0
2023-08-27 21:33:53 -04:00
cf5ae46928
Controlnet/t2iadapter cleanup.
2023-08-22 01:06:26 -04:00
b80c3276dc
Fix issue with gligen.
2023-08-18 16:32:23 -04:00
d6e4b342e6
Support for Control Loras.
...
Control loras are controlnets where some of the weights are stored in
"lora" format: an up and a down low rank matrice that when multiplied
together and added to the unet weight give the controlnet weight.
This allows a much smaller memory footprint depending on the rank of the
matrices.
These controlnets are used just like regular ones.
2023-08-18 11:59:51 -04:00
2b13939044
Remove some useless code.
2023-07-30 14:13:33 -04:00
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
9ba440995a
It's actually possible to torch.compile the unet now.
2023-07-18 21:36:35 -04:00
3ded1a3a04
Refactor of sampler code to deal more easily with different model types.
2023-07-17 01:22:12 -04:00
ddc6f12ad5
Disable autocast in unet for increased speed.
2023-07-05 21:58:29 -04:00
103c487a89
Cleanup.
2023-07-02 11:58:23 -04:00
c71a7e6b20
Fix ddim + inpainting not working.
2023-06-26 00:48:48 -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
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
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
45be2e92c1
Fix DDIM v-prediction.
2023-06-17 20:48:21 -04:00
ae43f09ef7
All the unet weights should now be initialized with the right dtype.
2023-06-15 18:42:30 -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
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
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
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
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
d9e088ddfd
minor changes for tiled sampler
2023-05-12 23:49:09 +02:00
cb1551b819
Lowvram mode for gligen and fix some lowvram issues.
2023-05-05 18:11:41 -04:00
bae4fb4a9d
Fix imports.
2023-05-04 18:10:29 -04:00
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
d3293c8339
Properly disable all progress bars when disable_pbar=True
2023-05-01 15:52:17 -04:00
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
3696d1699a
Add support for GLIGEN textbox model.
2023-04-19 11:06:32 -04:00
73c3e11e83
Fix model_management import so it doesn't get executed twice.
2023-04-15 19:04:33 -04:00
e5e587b1c0
seperates out arg parser and imports args
2023-04-05 23:41:23 -04:00
e46b1c3034
Disable xformers in VAE when xformers == 0.0.18
2023-04-04 22:22:02 -04:00
539ff487a8
Pull latest tomesd code from upstream.
2023-04-03 15:49:28 -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
f5365c9c81
Fix ddim for Mac: #264
2023-03-26 00:36:54 -04:00
3ed4a4e4e6
Try again with vae tiled decoding if regular fails because of OOM.
2023-03-22 14:49:00 -04:00
c692509c2b
Try to improve VAEEncode memory usage a bit.
2023-03-22 02:45:18 -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
1de86851b1
Try to fix memory issue.
2023-03-11 15:15:13 -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
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
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
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
9502ee45c3
Hopefully fix a strange issue with xformers + lowvram.
2023-02-28 13:48:52 -05:00
fcb25d37db
Prepare for t2i adapter.
2023-02-24 23:36:17 -05:00
f04dc2c2f4
Implement DDIM sampler.
2023-02-22 21:10:19 -05:00
c9daec4c89
Remove prints that are useless when xformers is enabled.
2023-02-21 22:16:13 -05:00
09f1d76ed8
Fix an OOM issue.
2023-02-17 16:21:01 -05:00
4efa67fa12
Add ControlNet support.
2023-02-16 10:38:08 -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
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
047775615b
Lower the chances of an OOM.
2023-02-08 14:24:27 -05:00
1daccf3678
Run softmax in place if it OOMs.
2023-01-30 19:55:01 -05:00
comfyanonymous
Simon Lui
BlenderNeko
EllangoK
edikius