b12b48e170
cleanup.
1 year ago
329c571993
Improve code legibility.
1 year ago
6c5990f7db
Fix cfg being calculated more than once if sampler_cfg_function.
1 year ago
ba04a87d10
Refactor and improve the sag node.
...
Moved all the sag related code to comfy_extras/nodes_sag.py
1 year ago
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
1 year ago
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
1 year ago
b454a67bb9
Support segmind vega model.
1 year ago
824e4935f5
Add dtype parameter to VAE object.
1 year ago
32b7e7e769
Add manual cast to controlnet.
1 year ago
3152023fbc
Use inference dtype for unet memory usage estimation.
1 year ago
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
b0aab1e4ea
Add an option --fp16-unet to force using fp16 for the unet.
1 year ago
ba07cb748e
Use faster manual cast for fp8 in unet.
1 year ago
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
57926635e8
Switch text encoder to manual cast.
...
Use fp16 text encoder weights for CPU inference to lower memory usage.
1 year ago
69033081c5
mask editor bugfix
...
- Addressing the issue where an unnecessary hidden panel disrupts the drawing.
1 year ago
340177e6e8
Disable non blocking on mps.
1 year ago
614b7e731f
Implement GLora.
1 year ago
cb63e230b4
Make lora code a bit cleaner.
1 year ago
9e411073e9
Add instructions for those that have python 3.12
1 year ago
eccc9e64a6
Merge branch 'group-reroute-fix' of https://github.com/pythongosssss/ComfyUI
1 year ago
da74e3bbe3
Update pytorch nightly packaging workflow.
1 year ago
174eba8e95
Use own clip vision model implementation.
1 year ago
080ef75c31
fix
1 year ago
9aaf368a41
Fix internal reroutes connected to other groups
1 year ago
97015b6b38
Cleanup.
1 year ago
a4ec54a40d
Add linear_start and linear_end to model_config.sampling_settings
1 year ago
9ac0b487ac
Make --gpu-only put intermediate values in GPU memory instead of cpu.
1 year ago
cdff081023
Fix hypertile.
1 year ago
efb704c758
Support attention masking in CLIP implementation.
1 year ago
248d9125b0
Merge branch 'ht_deterministic' of https://github.com/asagi4/ComfyUI
1 year ago
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
03eadbb53c
Make HyperTile deterministic
1 year ago
2db86b4676
Slightly faster lora applying.
1 year ago
e134547341
Merge branch 'reroute-converted-inputs' of https://github.com/pythongosssss/ComfyUI
...
# Conflicts:
# web/extensions/core/widgetInputs.js
1 year ago
8112a0d9fc
improve: Mask Editor ( #2171 )
...
* renewal mask editor
* fix: ignoring keydown when 2nd open
1 year ago
ef29542030
Merge branch 'primitive-text-replacement' of https://github.com/pythongosssss/ComfyUI
1 year ago
8de6f94f5c
Allow widget placeholder replacement on primitives
1 year ago
bcc469a2c9
try to stop test failing
1 year ago
a99da6667f
reroute + primitive tests
1 year ago
44265e0810
Allow connecting primitivenode to reroutes
1 year ago
1bbd65ab30
Missed this one.
1 year ago
9b655d4fd7
Fix memory issue with control loras.
1 year ago
26b1c0a771
Fix control lora on fp8.
1 year ago
be3468ddd5
Less useless downcasting.
1 year ago
ca82ade765
Use .itemsize to get dtype size for fp8.
1 year ago
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
af365e4dd1
All the unet ops with weights are now handled by comfy.ops
1 year ago
6efe561c2a
Merge branch 'fix-template-sorting' of https://github.com/pythongosssss/ComfyUI
1 year ago
77ab2c3f69
fix template sorting
1 year ago
comfyanonymous
Rafie Walker
pythongosssss
Dr.Lt.Data
asagi4
Dr.Lt.Data