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
afa2399f79
Add a way to set output block patches to modify the h and hsp.
1 year ago
1938f5c5fe
Add a force argument to soft_empty_cache to force a cache empty.
1 year ago
bed116a1f9
Remove optimization that caused border.
2 years ago
1c794a2161
Fallback to slice attention if xformers doesn't support the operation.
2 years ago
d935ba50c4
Make --bf16-vae work on torch 2.0
2 years ago
cf5ae46928
Controlnet/t2iadapter cleanup.
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
2b13939044
Remove some useless code.
2 years ago
95d796fc85
Faster VAE loading.
2 years ago
4b957a0010
Initialize the unet directly on the target device.
2 years ago
ddc6f12ad5
Disable autocast in unet for increased speed.
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
fa28d7334b
Remove useless code.
2 years ago
f87ec10a97
Support base SDXL and SDXL refiner models.
...
Large refactor of the model detection and loading code.
2 years ago
ae43f09ef7
All the unet weights should now be initialized with the right dtype.
2 years ago
7bf89ba923
Initialize more unet weights as the right dtype.
2 years ago
e21d9ad445
Initialize transformer unet block weights in right dtype at the start.
2 years ago
21f04fe632
Disable default weight values in unet conv2d for faster loading.
2 years ago
b8636a44aa
Make scaled_dot_product switch to sliced attention on OOM.
2 years ago
797c4e8d3b
Simplify and improve some vae attention code.
2 years ago
cb1551b819
Lowvram mode for gligen and fix some lowvram issues.
2 years ago
bae4fb4a9d
Fix imports.
2 years ago
ba8a4c3667
Change latent resolution step to 8.
2 years ago
66c8aa5c3e
Make unet work with any input shape.
2 years ago
3696d1699a
Add support for GLIGEN textbox model.
2 years ago
73c3e11e83
Fix model_management import so it doesn't get executed twice.
2 years ago
e46b1c3034
Disable xformers in VAE when xformers == 0.0.18
2 years ago
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.
2 years ago
61ec3c9d5d
Add a way to pass options to the transformers blocks.
2 years ago
3ed4a4e4e6
Try again with vae tiled decoding if regular fails because of OOM.
2 years ago
c692509c2b
Try to improve VAEEncode memory usage a bit.
2 years ago
54dbfaf2ec
Remove omegaconf dependency and some ci changes.
2 years ago
83f23f82b8
Add pytorch attention support to VAE.
2 years ago
a256a2abde
--disable-xformers should not even try to import xformers.
2 years ago
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.
2 years ago
1de86851b1
Try to fix memory issue.
2 years ago
cc8baf1080
Make VAE use common function to get free memory.
2 years ago
fcb25d37db
Prepare for t2i adapter.
2 years ago
09f1d76ed8
Fix an OOM issue.
2 years ago
4efa67fa12
Add ControlNet support.
2 years ago
509c7dfc6d
Use real softmax in split op to fix issue with some images.
2 years ago
1f6a467e92
Update ldm dir with latest upstream stable diffusion changes.
2 years ago
773cdabfce
Same thing but for the other places where it's used.
2 years ago
e8c499ddd4
Split optimization for VAE attention block.
2 years ago
5b4e312749
Use inplace operations for less OOM issues.
2 years ago
220afe3310
Initial commit.
2 years ago
comfyanonymous