3e5ea74ad3
Make buggy xformers fall back on pytorch attention.
2023-11-24 03:55:35 -05:00
871cc20e13
Support SVD img2vid model.
2023-11-23 19:41:33 -05:00
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
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
bb064c9796
Add a separate optimized_attention_masked function.
2023-10-16 02:31:24 -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
1938f5c5fe
Add a force argument to soft_empty_cache to force a cache empty.
2023-09-04 00:58:18 -04:00
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
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
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
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
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
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
ae43f09ef7
All the unet weights should now be initialized with the right dtype.
2023-06-15 18:42:30 -04:00
e21d9ad445
Initialize transformer unet block weights in right dtype at the start.
2023-06-15 14:29:26 -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
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
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
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
3ed4a4e4e6
Try again with vae tiled decoding if regular fails because of OOM.
2023-03-22 14:49:00 -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
798c90e1c0
Fix pytorch 2.0 cross attention not working.
2023-03-05 14:14:54 -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
c9daec4c89
Remove prints that are useless when xformers is enabled.
2023-02-21 22:16:13 -05:00
773cdabfce
Same thing but for the other places where it's used.
2023-02-09 12:43:29 -05:00
50db297cf6
Try to fix OOM issues with cards that have less vram than mine.
2023-01-29 00:50:46 -05:00
comfyanonymous
Simon Lui
EllangoK