2a813c3b09
Switch some more prints to logging.
12 months ago
6bcf57ff10
Fix attention masks properly for multiple batches.
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
89507f8adf
Remove some unused imports.
1 year ago
6a7bc35db8
Use basic attention implementation for small inputs on old pytorch.
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
a5056cfb1f
Remove useless code.
1 year ago
77755ab8db
Refactor comfy.ops
...
comfy.ops -> comfy.ops.disable_weight_init
This should make it more clear what they actually do.
Some unused code has also been removed.
1 year ago
fbdb14d4c4
Cleaner CLIP text encoder implementation.
...
Use a simple CLIP model implementation instead of the one from
transformers.
This will allow some interesting things that would too hackish to implement
using the transformers implementation.
1 year ago
1bbd65ab30
Missed this one.
1 year ago
af365e4dd1
All the unet ops with weights are now handled by comfy.ops
1 year ago
39e75862b2
Fix regression from last commit.
1 year ago
50dc39d6ec
Clean up the extra_options dict for the transformer patches.
...
Now everything in transformer_options gets put in extra_options.
1 year ago
3e5ea74ad3
Make buggy xformers fall back on pytorch attention.
1 year ago
871cc20e13
Support SVD img2vid model.
1 year ago
c837a173fa
Fix some memory issues in sub quad attention.
1 year ago
125b03eead
Fix some OOM issues with split attention.
1 year ago
a373367b0c
Fix some OOM issues with split and sub quad attention.
1 year ago
8b65f5de54
attention_basic now works with hypertile.
1 year ago
e6bc42df46
Make sub_quad and split work with hypertile.
1 year ago
9906e3efe3
Make xformers work with hypertile.
1 year ago
bb064c9796
Add a separate optimized_attention_masked function.
1 year ago
ac7d8cfa87
Allow attn_mask in attention_pytorch.
1 year ago
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.
1 year ago
fff491b032
Model patches can now know which batch is positive and negative.
1 year ago
1938f5c5fe
Add a force argument to soft_empty_cache to force a cache empty.
1 year ago
4a0c4ce4ef
Some fixes to generalize CUDA specific functionality to Intel or other GPUs.
2 years ago
0e3b641172
Remove xformers related print.
2 years ago
b80c3276dc
Fix issue with gligen.
2 years ago
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.
2 years ago
4b957a0010
Initialize the unet directly on the target device.
2 years ago
9ba440995a
It's actually possible to torch.compile the unet now.
2 years ago
ddc6f12ad5
Disable autocast in unet for increased speed.
2 years ago
103c487a89
Cleanup.
2 years ago
78d8035f73
Fix bug with controlnet.
2 years ago
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.
2 years ago
f87ec10a97
Support base SDXL and SDXL refiner models.
...
Large refactor of the model detection and loading code.
2 years ago
9fccf4aa03
Add original_shape parameter to transformer patch extra_options.
2 years ago
8883cb0f67
Add a way to set patches that modify the attn2 output.
...
Change the transformer patches function format to be more future proof.
2 years ago
ae43f09ef7
All the unet weights should now be initialized with the right dtype.
2 years ago
e21d9ad445
Initialize transformer unet block weights in right dtype at the start.
2 years ago
9d54066ebc
This isn't needed for inference.
2 years ago
6971646b8b
Speed up model loading a bit.
...
Default pytorch Linear initializes the weights which is useless and slow.
2 years ago
cb1551b819
Lowvram mode for gligen and fix some lowvram issues.
2 years ago
bae4fb4a9d
Fix imports.
2 years ago
5282f56434
Implement Linear hypernetworks.
...
Add a HypernetworkLoader node to use hypernetworks.
2 years ago
comfyanonymous
Simon Lui