comfyanonymous
|
57beace324
|
Fix VAEDecodeTiled minimum.
|
1 year ago |
|
comfyanonymous
|
1c012d69af
|
It doesn't make sense for c_crossattn and c_concat to be lists.
|
1 year ago |
|
comfyanonymous
|
5f101f4da1
|
Update litegraph with upstream: middle mouse dragging.
|
1 year ago |
Ridan Vandenbergh
|
2cd3980199
|
Remove forced lowercase on embeddings endpoint
|
1 year ago |
|
comfyanonymous
|
7e941f9f24
|
Clean up DiffusersLoader node.
|
1 year ago |
Simon Lui
|
18617967e5
|
Fix error message in model_patcher.py
Found while tinkering.
|
1 year ago |
|
comfyanonymous
|
fe4c07400c
|
Fix "Load Checkpoint with config" node.
|
1 year ago |
|
comfyanonymous
|
d70b0bc43c
|
Use the GPU for the canny preprocessor when available.
|
1 year ago |
|
comfyanonymous
|
81d9200e18
|
Add node to convert a specific colour in an image to a mask.
|
1 year ago |
|
comfyanonymous
|
f2f5e5dcbb
|
Support SDXL t2i adapters with 3 channel input.
|
1 year ago |
|
comfyanonymous
|
15adc3699f
|
Move beta_schedule to model_config and allow disabling unet creation.
|
1 year ago |
|
comfyanonymous
|
968078b149
|
Merge branch 'feat/mute_bypass_nodes_in_group' of https://github.com/M1kep/ComfyUI
|
1 year ago |
|
comfyanonymous
|
66c690e698
|
Merge branch 'preserve-pnginfo' of https://github.com/chrisgoringe/ComfyUI
|
1 year ago |
|
comfyanonymous
|
bed116a1f9
|
Remove optimization that caused border.
|
1 year ago |
Chris
|
18379dea36
|
check for text attr and save
|
1 year ago |
|
Chris
|
edcff9ab8a
|
copy metadata into modified image
|
1 year ago |
Michael Poutre
|
6944288aff
|
refactor(ui): Switch statement, and handle other modes in group actions
|
1 year ago |
|
Michael Poutre
|
e30d546e38
|
feat(ui): Add node mode toggles to group context menu
|
1 year ago |
|
comfyanonymous
|
8ddd081b09
|
Use the same units for tile size in VAEDecodeTiled and VAEEncodeTiled.
|
1 year ago |
|
comfyanonymous
|
fbf375f161
|
Merge branch 'master' of https://github.com/bvhari/ComfyUI
|
1 year ago |
|
comfyanonymous
|
65cae62c71
|
No need to check filename extensions to detect shuffle controlnet.
|
1 year ago |
|
comfyanonymous
|
4e89b2c25a
|
Put clip vision outputs on the CPU.
|
1 year ago |
|
comfyanonymous
|
a094b45c93
|
Load clipvision model to GPU for faster performance.
|
1 year ago |
|
comfyanonymous
|
1300a1bb4c
|
Text encoder should initially load on the offload_device not the regular.
|
1 year ago |
|
comfyanonymous
|
f92074b84f
|
Move ModelPatcher to model_patcher.py
|
1 year ago |
BVH
|
d86b222fe9
|
Reduce min tile size for encode
|
1 year ago |
|
comfyanonymous
|
4798cf5a62
|
Implement loras with norm keys.
|
1 year ago |
|
BVH
|
9196588088
|
Make tile size in Tiled VAE encode/decode user configurable
|
1 year ago |
Dr.Lt.Data
|
0faee1186f
|
support on prompt event handler (#765)
Co-authored-by: Lt.Dr.Data <lt.dr.data@gmail.com>
|
1 year ago |
|
comfyanonymous
|
b8c7c770d3
|
Enable bf16-vae by default on ampere and up.
|
1 year ago |
|
comfyanonymous
|
1c794a2161
|
Fallback to slice attention if xformers doesn't support the operation.
|
1 year ago |
|
comfyanonymous
|
d935ba50c4
|
Make --bf16-vae work on torch 2.0
|
1 year ago |
|
comfyanonymous
|
412596d325
|
Merge branch 'increase_client_max_size' of https://github.com/ramyma/ComfyUI
|
1 year ago |
|
Dr.Lt.Data
|
d9f4922993
|
fix: cannot disable dynamicPrompts (#1327)
* fix: cannot disable dynamicPrompts
* indent fix
---------
Co-authored-by: Lt.Dr.Data <lt.dr.data@gmail.com>
|
1 year ago |
ramyma
|
0b6cf7a558
|
Increase client_max_size to allow bigger request bodies
|
1 year ago |
|
comfyanonymous
|
a57b0c797b
|
Fix lowvram model merging.
|
1 year ago |
|
comfyanonymous
|
f72780a7e3
|
The new smart memory management makes this unnecessary.
|
1 year ago |
|
comfyanonymous
|
c77f02e1c6
|
Move controlnet code to comfy/controlnet.py
|
1 year ago |
|
comfyanonymous
|
15a7716fa6
|
Move lora code to comfy/lora.py
|
1 year ago |
|
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 |
