comfyanonymous
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
comfyanonymous
b0aab1e4ea
Add an option --fp16-unet to force using fp16 for the unet.
1 year ago
comfyanonymous
ba07cb748e
Use faster manual cast for fp8 in unet.
1 year ago
pythongosssss
ab93abd4b2
Prevent cleaning graph state on undo/redo ( #2255 )
...
* Prevent cleaning graph state on undo/redo
* Remove pause rendering due to LG bug
1 year ago
comfyanonymous
57926635e8
Switch text encoder to manual cast.
...
Use fp16 text encoder weights for CPU inference to lower memory usage.
1 year ago
Dr.Lt.Data
69033081c5
mask editor bugfix
...
- Addressing the issue where an unnecessary hidden panel disrupts the drawing.
1 year ago
comfyanonymous
340177e6e8
Disable non blocking on mps.
1 year ago
comfyanonymous
614b7e731f
Implement GLora.
1 year ago
comfyanonymous
cb63e230b4
Make lora code a bit cleaner.
1 year ago
comfyanonymous
9e411073e9
Add instructions for those that have python 3.12
1 year ago
comfyanonymous
eccc9e64a6
Merge branch 'group-reroute-fix' of https://github.com/pythongosssss/ComfyUI
1 year ago
comfyanonymous
da74e3bbe3
Update pytorch nightly packaging workflow.
1 year ago
comfyanonymous
174eba8e95
Use own clip vision model implementation.
1 year ago
pythongosssss
080ef75c31
fix
1 year ago
pythongosssss
9aaf368a41
Fix internal reroutes connected to other groups
1 year ago
comfyanonymous
97015b6b38
Cleanup.
1 year ago
comfyanonymous
a4ec54a40d
Add linear_start and linear_end to model_config.sampling_settings
1 year ago
comfyanonymous
9ac0b487ac
Make --gpu-only put intermediate values in GPU memory instead of cpu.
1 year ago
comfyanonymous
cdff081023
Fix hypertile.
1 year ago
comfyanonymous
efb704c758
Support attention masking in CLIP implementation.
1 year ago
comfyanonymous
248d9125b0
Merge branch 'ht_deterministic' of https://github.com/asagi4/ComfyUI
1 year ago
comfyanonymous
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
asagi4
03eadbb53c
Make HyperTile deterministic
1 year ago
comfyanonymous
2db86b4676
Slightly faster lora applying.
1 year ago
comfyanonymous
e134547341
Merge branch 'reroute-converted-inputs' of https://github.com/pythongosssss/ComfyUI
...
# Conflicts:
# web/extensions/core/widgetInputs.js
1 year ago
Dr.Lt.Data
8112a0d9fc
improve: Mask Editor ( #2171 )
...
* renewal mask editor
* fix: ignoring keydown when 2nd open
1 year ago
comfyanonymous
ef29542030
Merge branch 'primitive-text-replacement' of https://github.com/pythongosssss/ComfyUI
1 year ago
pythongosssss
8de6f94f5c
Allow widget placeholder replacement on primitives
1 year ago
pythongosssss
bcc469a2c9
try to stop test failing
1 year ago
pythongosssss
a99da6667f
reroute + primitive tests
1 year ago
pythongosssss
44265e0810
Allow connecting primitivenode to reroutes
1 year ago
comfyanonymous
1bbd65ab30
Missed this one.
1 year ago
comfyanonymous
9b655d4fd7
Fix memory issue with control loras.
1 year ago
comfyanonymous
26b1c0a771
Fix control lora on fp8.
1 year ago
comfyanonymous
be3468ddd5
Less useless downcasting.
1 year ago
comfyanonymous
ca82ade765
Use .itemsize to get dtype size for fp8.
1 year ago
comfyanonymous
31b0f6f3d8
UNET weights can now be stored in fp8.
...
--fp8_e4m3fn-unet and --fp8_e5m2-unet are the two different formats
supported by pytorch.
1 year ago
comfyanonymous
af365e4dd1
All the unet ops with weights are now handled by comfy.ops
1 year ago
comfyanonymous
6efe561c2a
Merge branch 'fix-template-sorting' of https://github.com/pythongosssss/ComfyUI
1 year ago
pythongosssss
77ab2c3f69
fix template sorting
1 year ago
pythongosssss
44d8abadf0
allow muting group node
1 year ago
pythongosssss
496de0891d
Allow removing erroring embedded groups
...
Unregister group nodes on workflow change
1 year ago
comfyanonymous
61a123a1e0
A different way of handling multiple images passed to SVD.
...
Previously when a list of 3 images [0, 1, 2] was used for a 6 frame video
they were concated like this:
[0, 1, 2, 0, 1, 2]
now they are concated like this:
[0, 0, 1, 1, 2, 2]
1 year ago
comfyanonymous
b2517b4ceb
Load api workflow if regular workflow isn't in loaded image.
1 year ago
comfyanonymous
88e2c9746b
Merge branch 'image-cache' of https://github.com/jn-jairo/ComfyUI
1 year ago
pythongosssss
28220fa839
Fix node growing with DOM widgets when adding image even if enough space
1 year ago
Jairo Correa
c92f3dca73
Merge branch 'master' into image-cache
1 year ago
comfyanonymous
2995a24725
Update readme.
1 year ago
pythongosssss
8491280504
Add Extension tests ( #2125 )
...
* Add test for extension hooks
Add afterConfigureGraph callback
* fix comment
1 year ago
comfyanonymous
ec7a00aa96
Fix extension widgets not working.
1 year ago