comfyanonymous
ec96f6d03a
Move text_projection to base clip model.
1 year ago
comfyanonymous
30eb92c3cb
Code cleanups.
1 year ago
comfyanonymous
51dde87e97
Try to free enough vram for control lora inference.
1 year ago
comfyanonymous
e3d0a9a490
Fix potential issue with text projection matrix multiplication.
1 year ago
comfyanonymous
cc44ade79e
Always shift text encoder to GPU when the device supports fp16.
1 year ago
comfyanonymous
a6ef08a46a
Even with forced fp16 the cpu device should never use it.
1 year ago
comfyanonymous
00c0b2c507
Initialize text encoder to target dtype.
1 year ago
comfyanonymous
f081017c1a
Save memory by storing text encoder weights in fp16 in most situations.
...
Do inference in fp32 to make sure quality stays the exact same.
1 year ago
comfyanonymous
d7b3b0f8c1
Don't hardcode node names for image upload widget.
1 year ago
comfyanonymous
afcb9cb1df
All resolutions now work with t2i adapter for SDXL.
1 year ago
comfyanonymous
85fde89d7f
T2I adapter SDXL.
1 year ago
comfyanonymous
f2a7cc9121
Add control lora links to colab notebook.
1 year ago
comfyanonymous
e2256b4087
Add clip_vision_g download command to colab notebook for ReVision.
1 year ago
comfyanonymous
cf5ae46928
Controlnet/t2iadapter cleanup.
1 year ago
comfyanonymous
763b0cf024
Fix control lora not working in fp32.
1 year ago
comfyanonymous
bc76b3829f
Merge branch 'custom-node-js' of https://github.com/pythongosssss/ComfyUI
1 year ago
comfyanonymous
199d73364a
Fix ControlLora on lowvram.
1 year ago
comfyanonymous
d08e53de2e
Remove autocast from controlnet code.
1 year ago
pythongosssss
cdaf65ceb1
remove log
1 year ago
comfyanonymous
0d7b0a4dc7
Small cleanups.
1 year ago
pythongosssss
9b1d5a587c
Allow loading js extensions without copying to /web folder
1 year ago
Simon Lui
9225465975
Further tuning and fix mem_free_total.
1 year ago
Simon Lui
2c096e4260
Add ipex optimize and other enhancements for Intel GPUs based on recent memory changes.
1 year ago
comfyanonymous
8ee0473687
Merge branch 'parallel-extensions-load' of https://github.com/NoCrypt/ComfyUI
1 year ago
comfyanonymous
e9469e732d
--disable-smart-memory now disables loading model directly to vram.
1 year ago
comfyanonymous
c9b562aed1
Free more memory before VAE encode/decode.
1 year ago
ncpt
81ccacaa7c
Make the extensions loads in parallel instead of waiting one by one
1 year ago
comfyanonymous
b80c3276dc
Fix issue with gligen.
1 year ago
comfyanonymous
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.
1 year ago
comfyanonymous
39ac856a33
ReVision support: unclip nodes can now be used with SDXL.
1 year ago
comfyanonymous
76d53c4622
Add support for clip g vision model to CLIPVisionLoader.
1 year ago
comfyanonymous
fc99fa56a9
Add node to scale image to a total amount of pixels keeping aspect.
1 year ago
comfyanonymous
eb5c991a8c
Merge branch 'add-user-css' of https://github.com/pythongosssss/ComfyUI
1 year ago
comfyanonymous
bd7321c8ac
Update aiohttp in nightly workflow.
1 year ago
Alexopus
e59fe0537a
Fix referenced before assignment
...
For https://github.com/BlenderNeko/ComfyUI_TiledKSampler/issues/13
1 year ago
comfyanonymous
be9c5e25bc
Fix issue with not freeing enough memory when sampling.
1 year ago
comfyanonymous
ac0758a1a4
Fix bug with lowvram and controlnet advanced node.
1 year ago
comfyanonymous
c28db1f315
Fix potential issues with patching models when saving checkpoints.
1 year ago
pythongosssss
c828543a77
Allow user customizable css
1 year ago
comfyanonymous
1498f1a342
Merge branch 'add-growmask-node' of https://github.com/coreyryanhanson/ComfyUI
1 year ago
comfyanonymous
3aee33b54e
Add --disable-smart-memory for those that want the old behaviour.
1 year ago
comfyanonymous
2be2742711
Fix issue with regular torch version.
1 year ago
comfyanonymous
89a0767abf
Smarter memory management.
...
Try to keep models on the vram when possible.
Better lowvram mode for controlnets.
1 year ago
comfyanonymous
2c97c30256
Support small diffusers controlnet so both types are now supported.
1 year ago
comfyanonymous
53f326a3d8
Support diffusers mini controlnets.
1 year ago
comfyanonymous
58f0c616ed
Fix clip vision issue with old transformers versions.
1 year ago
comfyanonymous
ae270f79bc
Fix potential issue with batch size and clip vision.
1 year ago
Corey
18e86a4010
add a node to allow growing of masks through dilation
1 year ago
comfyanonymous
27b87c25a1
Add an EmptyImage node.
...
TODO: implement color picker in the frontend.
1 year ago
comfyanonymous
6dc02c7bac
Add a "resize_source" option to Image and Latent CompositeMasked.
1 year ago