5f450d3351
Started scaffolding for other hook types, refactored get_hooks_from_cond to organize hooks by type
2024-09-21 10:37:18 +09:00
59d72b4050
Added wrappers to ModelPatcher to facilitate standardized function wrapping
2024-09-20 20:05:29 +09:00
38c69080c7
Add docstring
2024-09-20 03:16:23 -04:00
70a708d726
Fix model merging issue.
2024-09-20 02:31:44 -04:00
e7d4782736
add laplace scheduler [2407.03297] ( #4990 )
...
* add laplace scheduler [2407.03297]
* should be here instead lol
* better settings
2024-09-19 23:23:09 -04:00
3326bdfd4e
add internal /folder_paths route ( #4980 )
...
returns a json maps of folder paths
2024-09-19 09:52:55 -04:00
68bb885d22
add 'is_default' to model paths config ( #4979 )
...
* add 'is_default' to model paths config
including impl and doc in example file
* update weirdly overspecific test expectations
* oh there's two
* sigh
2024-09-19 08:59:55 -04:00
55014293b1
Added injections support to ModelPatcher + necessary bookkeeping, added additional_models support in ModelPatcher, conds, and hooks
2024-09-19 21:43:58 +09:00
ad66f7c7d8
Add model_options to load_controlnet function.
2024-09-19 08:23:35 -04:00
de8e8e3b0d
Fix xpu Pytorch nightly build from calling optimize which doesn't exist. ( #4978 )
2024-09-19 05:11:42 -04:00
a1e71cfad1
very simple strong-cache on model list ( #4969 )
...
* very simple strong-cache on model list
* store the cache after validation too
* only cache object_info for now
* use a 'with' context
2024-09-19 04:40:14 -04:00
e80dc96627
Fix incorrect ref to create_hook_patches_clone after moving function
2024-09-19 11:57:19 +09:00
787ef34842
Continued work on simpler Create Hook Model As LoRA node, started to implement ModelPatcher callbacks, attachments, and additional_models
2024-09-19 11:47:25 +09:00
0bfc7cc998
Create the temp directory on ComfyUI startup instead.
2024-09-18 09:55:57 -04:00
7183fd1665
Add route to list model types ( #4846 )
...
* Add list models route
* Better readable model types list
2024-09-17 04:22:05 -04:00
254838f23c
add simple error check to model loading ( #4950 )
2024-09-17 03:57:17 -04:00
0b7dfa986d
Improve tiling calculations to reduce number of tiles that need to be processed. ( #4944 )
2024-09-17 03:51:10 -04:00
d514bb38ee
Add some option to model_options for the text encoder.
...
load_device, offload_device and the initial_device can now be set.
2024-09-17 03:49:54 -04:00
6b14fc8795
Merge branch 'master' into patch_hooks
2024-09-17 15:31:03 +09:00
c29006e669
Initial work on adding 'model_as_lora' lora type to calculate_weight
2024-09-17 15:30:33 +09:00
0849c80e2a
get_key_patches now works without unloading the model.
2024-09-17 01:57:59 -04:00
cfb145187d
Made Set Clip Hooks node work with hooks from Create Hook nodes, began work on better Create Hook Model As LoRA node
2024-09-17 09:55:14 +09:00
4b472ba44c
Added support for adding weight hooks that aren't registered on the ModelPatcher at sampling time
2024-09-17 06:22:41 +09:00
56e8f5e4fd
VAEDecodeAudio now does some normalization on the audio.
2024-09-16 00:30:36 -04:00
f5c899f42a
Fixed MaxSpeed and default conds implementations
2024-09-15 21:00:45 +09:00
e813abbb2c
Long CLIP L support for SDXL, SD3 and Flux.
...
Use the *CLIPLoader nodes.
2024-09-15 07:59:38 -04:00
5a9aa5817c
Added initial hook scheduling nodes, small renaming/refactoring
2024-09-15 18:39:31 +09:00
a5034df6db
Made CLIP work with hook patches
2024-09-15 15:47:09 +09:00
5e68a4ce67
Reduce repeated calls of INPUT_TYPES in cache ( #4922 )
2024-09-15 01:03:09 -04:00
9ded65a616
Added initial set of hook-related nodes, added code to register hooks for loras/model-as-loras, small renaming/refactoring
2024-09-15 08:33:17 +09:00
ca08597670
Make the inpaint controlnet node work with non inpaint ones.
2024-09-14 09:17:13 -04:00
f48e390032
Support AliMama SD3 and Flux inpaint controlnets.
...
Use the ControlNetInpaintingAliMamaApply node.
2024-09-14 09:05:16 -04:00
f5abdc6f86
Merge branch 'master' into patch_hooks
2024-09-14 17:29:30 +09:00
5dadd97583
Added default_conds support in calc_cond_batch func
2024-09-14 17:21:50 +09:00
f160d46340
Added call to initialize_timesteps on hooks in process_conds func, and added call prepare current keyframe on hooks in calc_cond_batch
2024-09-14 16:10:42 +09:00
1268d04295
Consolidated add_hook_patches_as_diffs into add_hook_patches func, fixed fp8 support for model-as-lora feature
2024-09-14 14:09:43 +09:00
369a6dd2c4
Remove empty spaces in user_manager.py ( #4917 )
2024-09-13 23:30:44 -04:00
b3ce8fb9fd
Revert "Reduce repeated calls of get_immediate_node_signature for ancestors in cache ( #4871 )"
...
This reverts commit f6b7194f64
2024-09-13 23:24:47 -04:00
cf80d28689
Support loading controlnets with different input.
2024-09-13 09:54:37 -04:00
9ae758175d
Added current_patcher property to BaseModel
2024-09-13 21:35:35 +09:00
6fb44c4b7c
Make adding links/nodes to ExecutionList non-recursive ( #4886 )
...
Graphs with 300+ chained nodes run into maximum recursion depth error (limit is 1000 in CPython)
2024-09-13 08:25:11 -04:00
3cbd40ada3
Initial changes to calc_cond_batch to eventually support hook_patches
2024-09-13 18:31:52 +09:00
069ec7a64b
Added hook_patches to ModelPatcher for weights (model)
2024-09-13 17:20:22 +09:00
d2247c1e61
Normalize path returned by /userdata to always use / as separator ( #4906 )
2024-09-13 03:45:31 -04:00
cb12ad7049
Add full_info flag in /userdata endpoint to list out file size and last modified timestamp ( #4905 )
...
* Add full_info flag in /userdata endpoint to list out file size and last modified timestamp
* nit
2024-09-13 02:40:59 -04:00
f6b7194f64
Reduce repeated calls of get_immediate_node_signature for ancestors in cache ( #4871 )
2024-09-12 23:02:52 -04:00
7c6eb4fb29
Set some nodes as DEPRECATED.
2024-09-12 20:27:07 -04:00
b962db9952
Add cli arg to override user directory ( #4856 )
...
* Override user directory.
* Use overridden user directory.
* Remove prints.
* Remove references to global user_files.
* Remove unused replace_folder function.
* Remove newline.
* Remove global during get_user_directory.
* Add validation.
2024-09-12 08:10:27 -04:00
d0b7ab88ba
Add a simple experimental TorchCompileModel node.
...
It probably only works on Linux.
For maximum speed on Flux with Nvidia 40 series/ada and newer try using
this node with fp8_e4m3fn and the --fast argument.
2024-09-12 05:24:25 -04:00
405b529545
Minor: update tests-unit README.md ( #4896 )
2024-09-12 04:53:08 -04:00
kosinkadink1@gmail.com
huchenlei
comfyanonymous
yoinked
Alex "mcmonkey" Goodwin
Simon Lui
Tom
pharmapsychotic
JettHu
Acly
Robin Huang
Yoland Yan