guill
7d4530f6f5
Rework Caching ( #2 )
...
This commit solves a number of bugs and adds some caching related
functionality. Specifically:
1. Caching is now input-based. In cases of completely identical nodes,
the output will be reused (for example, if you have multiple
LoadCheckpoint nodes loading the same checkpoint). If a node doesn't
want this behavior (e.g. a `RandomInteger` node, it should set
`NOT_IDEMPOTENT = True`.
2. This means that nodes within a component will now be cached and will
only change if the input actually changes. Note that types that can't
be hashed by default will always count as changed (though the
component itself will only expand if one of its inputs changes).
3. A new LRU caching strategy is now available by starting with
`--cache-lru 100`. With this strategy, in addition to the latest
workflow being cached, up to N (100 in the example) node outputs will
be retained. This allows users to work on multiple workflows or
experiment with different inputs without losing the benefits of
caching (at the cost of more RAM and VRAM). I intentionally left some
additional debug print statements in for this strategy for the
moment.
4. A new endpoint `/debugcache` has been temporarily added to assist
with tracking down issues people encounter. It allows you to browse
the contents of the cache.
5. Outputs from ephemeral nodes will now be communicated to the
front-end with both the ephemeral node id, the 'parent' node id, and
the 'display' node id. The front-end has been updated to deal with
this.
2023-09-11 19:53:41 -07:00
comfyanonymous
861fd58819
Add a warning if a card that doesn't support cuda malloc has it enabled.
2023-08-13 12:37:53 -04:00
comfyanonymous
2bc12d3d22
Add --temp-directory argument to set temp directory.
2023-08-11 05:13:03 -04:00
comfyanonymous
eb5191f911
0.0.0.0 doesn't work on windows.
2023-08-01 01:15:18 -04:00
comfyanonymous
ccb6b70de1
Move image encoding outside of sampling loop for better preview perf.
2023-07-19 18:06:58 -04:00
comfyanonymous
799c08a4ce
Auto disable cuda malloc on some GPUs on windows.
2023-07-19 14:43:55 -04:00
comfyanonymous
9871a15cf9
Enable --cuda-malloc by default on torch 2.0 and up.
...
Add --disable-cuda-malloc to disable it.
2023-07-17 15:12:10 -04:00
comfyanonymous
1679abd86d
Add a command line argument to enable backend:cudaMallocAsync
2023-07-17 11:00:14 -04:00
comfyanonymous
6f914fb77d
Print prestartup times for custom nodes.
2023-07-13 13:01:45 -04:00
Dr.Lt.Data
99abcbef41
feat/startup-script: Feature to avoid package installation errors when installing custom nodes. ( #856 )
...
* support startup script for installation without locking on windows
* modified: Instead of executing scripts from the startup-scripts directory, I will change it to execute the prestartup_script.py for each custom node.
2023-07-11 02:33:21 -04:00
comfyanonymous
103c487a89
Cleanup.
2023-07-02 11:58:23 -04:00
comfyanonymous
d52ed407a7
Send websocket message only when prompt is actually done executing.
2023-06-13 13:38:43 -04:00
reaper47
5cf4079923
Give linux some love
2023-06-07 15:15:38 +02:00
space-nuko
48f7ec750c
Make previews into cli option
2023-06-05 13:19:02 -05:00
space-nuko
38bc02bb40
Fix
2023-06-05 09:20:20 -05:00
space-nuko
b4f434ee66
Preview sampled images with TAESD
2023-06-05 09:20:17 -05:00
comfyanonymous
1dd846a7ba
Fix outputs gone from history.
2023-05-15 00:27:28 -04:00
comfyanonymous
dfc74c19d9
Add the prompt_id to some websocket messages.
2023-05-11 01:22:40 -04:00
comfyanonymous
d6dee8af1d
Only validate each input once.
2023-05-10 00:29:31 -04:00
EllangoK
8e03c789a2
auto-launch cli arg
2023-05-06 16:59:40 -04:00
comfyanonymous
93c64afaa9
Use sampler callback instead of tqdm hook for progress bar.
2023-05-02 23:00:49 -04:00
comfyanonymous
74fc7b7726
custom_nodes paths can now be set in the extra_model_paths.yaml
2023-04-16 01:46:43 -04:00
EllangoK
28fff5d1db
fixes lack of support for multi configs
...
also adds some metavars to argarse
2023-04-06 19:06:39 -04:00
EllangoK
e5e587b1c0
seperates out arg parser and imports args
2023-04-05 23:41:23 -04:00
EllangoK
dd29966f8a
changes main.py to use argparse
2023-04-05 22:36:40 -04:00
comfyanonymous
f816964847
Add a way to set output directory with --output-directory
2023-04-05 14:29:30 -04:00
comfyanonymous
6be7c64245
Merge branch 'custom_routes' of https://github.com/pythongosssss/ComfyUI
2023-04-02 01:55:05 -04:00
comfyanonymous
66f1f57615
Add --extra-model-paths-config to --help.
2023-04-02 01:54:44 -04:00
pythongosssss
313f1f83a6
Tweak server/custom node load order
...
- Load custom nodes after creating server
- Add routes after loading custom nodes
Custom nodes can now add routes via PromptServer.instance
2023-04-01 12:44:29 +01:00
comfyanonymous
5218e5d596
Command line option to set CUDA device.
2023-03-29 23:28:21 -04:00
comfyanonymous
31dd6c0531
Add way to specify listen ip with --listen.
2023-03-28 01:42:34 -04:00
comfyanonymous
51d6427ddf
Add support for loading extra paths from yaml file.
...
Rename extra_model_paths.yaml.example to extra_model_paths.yaml and edit
it to point to your other UI.
2023-03-18 02:52:43 -04:00
comfyanonymous
5ad9f86514
Do a quick test on the CI to see if ComfyUI actually runs before pushing
...
the build.
2023-03-14 23:02:57 -04:00
comfyanonymous
ff255d9dcd
Make sure windows permission issues don't mess things up.
2023-03-14 18:07:09 -04:00
pythongosssss
6db777b348
Added ability to save images to temp dir
2023-03-13 19:34:05 +00:00
comfyanonymous
83f23f82b8
Add pytorch attention support to VAE.
2023-03-13 12:45:54 -04:00
comfyanonymous
a256a2abde
--disable-xformers should not even try to import xformers.
2023-03-13 11:36:48 -04:00
comfyanonymous
0f3ba7482f
Xformers is now properly disabled when --cpu used.
...
Added --windows-standalone-build option, currently it only opens
makes the code open up comfyui in the browser.
2023-03-12 15:44:16 -04:00
comfyanonymous
afff30fc0a
Add --cpu to use the cpu for inference.
2023-03-06 10:50:50 -05:00
comfyanonymous
49d2e5bb5a
Move some stuff from main.py to execution.py
2023-02-27 19:44:58 -05:00
comfyanonymous
c0fb0c848f
Update colab notebook.
2023-02-25 22:49:22 -05:00
comfyanonymous
6de6246dd4
Fix some potential issues related to threads.
2023-02-25 18:36:29 -05:00
pythongosssss
9f391ab656
changed to store history by uniqueid
...
fixed removing history items
2023-02-23 21:25:08 +00:00
pythongosssss
5c5725dac0
Remove extra args
2023-02-23 20:21:58 +00:00
pythongosssss
9bd7bfa648
Added workflow history
...
Moved socket output updates to all node executions
Made image rendering on nodes more generic
2023-02-23 20:12:57 +00:00
pythongosssss
a52aa9f4b5
Moved api out to server
...
Reworked sockets to use socketio
Added progress to nodes
Added highlight to active node
Added preview to saveimage node
2023-02-21 19:29:49 +00:00
comfyanonymous
5f375f0d16
Remove my "deleted" debug print that confused people.
2023-02-21 01:28:08 -05:00
masterpiecebestquality
3a83da7281
empty cache after execute()
2023-02-20 13:56:34 -05:00
comfyanonymous
a38a30cb87
Document --highvram and enable it in colab.
2023-02-17 21:32:27 -05:00
pythongosssss
0787299610
Hide Triton warning on Windows
...
Triton doesnt work on Windows so hide the error
2023-02-16 18:19:26 +00:00
