Rafie Walker
6761233e9d
Implement Self-Attention Guidance ( #2201 )
...
* First SAG test
* need to put extra options on the model instead of patcher
* no errors and results seem not-broken
* Use @ashen-uncensored formula, which works better!!!
* Fix a crash when using weird resolutions. Remove an unnecessary UNet call
* Improve comments, optimize memory in blur routine
* SAG works with sampler_cfg_function
11 months ago
pythongosssss
390078904c
Group node fixes ( #2259 )
...
* Prevent cleaning graph state on undo/redo
* Remove pause rendering due to LG bug
* Fix crash on disconnected internal reroutes
* Fix widget inputs being incorrect order and value
* Fix initial primitive values on connect
* basic support for basic rerouted converted inputs
* Populate primitive to reroute input
* dont crash on bad primitive links
* Fix convert to group changing control value
* reduce restrictions
* fix random crash in tests
11 months ago
comfyanonymous
b454a67bb9
Support segmind vega model.
11 months ago
comfyanonymous
824e4935f5
Add dtype parameter to VAE object.
11 months ago
comfyanonymous
32b7e7e769
Add manual cast to controlnet.
11 months ago
comfyanonymous
3152023fbc
Use inference dtype for unet memory usage estimation.
11 months ago
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.
11 months ago
comfyanonymous
b0aab1e4ea
Add an option --fp16-unet to force using fp16 for the unet.
11 months ago
comfyanonymous
ba07cb748e
Use faster manual cast for fp8 in unet.
11 months 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
11 months ago
comfyanonymous
57926635e8
Switch text encoder to manual cast.
...
Use fp16 text encoder weights for CPU inference to lower memory usage.
11 months ago
Dr.Lt.Data
69033081c5
mask editor bugfix
...
- Addressing the issue where an unnecessary hidden panel disrupts the drawing.
11 months ago
comfyanonymous
340177e6e8
Disable non blocking on mps.
11 months ago
comfyanonymous
614b7e731f
Implement GLora.
11 months ago
comfyanonymous
cb63e230b4
Make lora code a bit cleaner.
11 months ago
comfyanonymous
9e411073e9
Add instructions for those that have python 3.12
11 months ago
comfyanonymous
eccc9e64a6
Merge branch 'group-reroute-fix' of https://github.com/pythongosssss/ComfyUI
11 months ago
comfyanonymous
da74e3bbe3
Update pytorch nightly packaging workflow.
11 months ago
comfyanonymous
174eba8e95
Use own clip vision model implementation.
11 months ago
pythongosssss
080ef75c31
fix
11 months ago
pythongosssss
9aaf368a41
Fix internal reroutes connected to other groups
11 months ago
comfyanonymous
97015b6b38
Cleanup.
12 months ago
comfyanonymous
a4ec54a40d
Add linear_start and linear_end to model_config.sampling_settings
12 months ago
comfyanonymous
9ac0b487ac
Make --gpu-only put intermediate values in GPU memory instead of cpu.
12 months ago
comfyanonymous
cdff081023
Fix hypertile.
12 months ago
comfyanonymous
efb704c758
Support attention masking in CLIP implementation.
12 months ago
comfyanonymous
248d9125b0
Merge branch 'ht_deterministic' of https://github.com/asagi4/ComfyUI
12 months 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.
12 months ago
asagi4
03eadbb53c
Make HyperTile deterministic
12 months ago
comfyanonymous
2db86b4676
Slightly faster lora applying.
12 months ago
comfyanonymous
e134547341
Merge branch 'reroute-converted-inputs' of https://github.com/pythongosssss/ComfyUI
...
# Conflicts:
# web/extensions/core/widgetInputs.js
12 months ago
Dr.Lt.Data
8112a0d9fc
improve: Mask Editor ( #2171 )
...
* renewal mask editor
* fix: ignoring keydown when 2nd open
12 months ago
comfyanonymous
ef29542030
Merge branch 'primitive-text-replacement' of https://github.com/pythongosssss/ComfyUI
12 months ago
pythongosssss
8de6f94f5c
Allow widget placeholder replacement on primitives
12 months ago
pythongosssss
bcc469a2c9
try to stop test failing
12 months ago
pythongosssss
a99da6667f
reroute + primitive tests
12 months ago
pythongosssss
44265e0810
Allow connecting primitivenode to reroutes
12 months ago
comfyanonymous
1bbd65ab30
Missed this one.
12 months ago
comfyanonymous
9b655d4fd7
Fix memory issue with control loras.
12 months ago
comfyanonymous
26b1c0a771
Fix control lora on fp8.
12 months ago
comfyanonymous
be3468ddd5
Less useless downcasting.
12 months ago
comfyanonymous
ca82ade765
Use .itemsize to get dtype size for fp8.
12 months 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.
12 months ago
comfyanonymous
af365e4dd1
All the unet ops with weights are now handled by comfy.ops
12 months ago
comfyanonymous
6efe561c2a
Merge branch 'fix-template-sorting' of https://github.com/pythongosssss/ComfyUI
12 months ago
pythongosssss
77ab2c3f69
fix template sorting
12 months ago
pythongosssss
44d8abadf0
allow muting group node
12 months ago
pythongosssss
496de0891d
Allow removing erroring embedded groups
...
Unregister group nodes on workflow change
12 months 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]
12 months ago
comfyanonymous
b2517b4ceb
Load api workflow if regular workflow isn't in loaded image.
12 months ago