Sergey Borisov
3b2a054f7a
Add model loader node; unet, clip, vae fields; change compel node to clip field
2023-05-13 04:37:20 +03:00
Sergey Borisov
4492044d29
Redo compel node to separate model loading
2023-05-12 23:09:33 +03:00
Sergey Borisov
5431dd5f50
Fix event args
2023-05-12 23:08:03 +03:00
Sergey Borisov
79fecba274
Fix model manager initialization in web ui
2023-05-12 23:05:08 +03:00
Lincoln Stein
2ef79b8bf3
fix bug in persistent model scheme
2023-05-12 00:14:56 -04:00
Lincoln Stein
11ecf438f5
latents.py converted to use model manager service; events emitted
2023-05-11 23:33:24 -04:00
Lincoln Stein
df5b968954
model manager now running as a service
2023-05-11 21:24:29 -04:00
Lincoln Stein
8ad8c5c67a
resolve conflicts with main
2023-05-11 00:19:20 -04:00
Lincoln Stein
590942edd7
Merge branch 'main' into lstein/new-model-manager
2023-05-11 00:16:03 -04:00
Lincoln Stein
4627910c5d
added a wrapper model_manager_service and model events
2023-05-11 00:09:19 -04:00
psychedelicious
f488b1a7f2
fix(nodes): fix usage of Optional
2023-05-11 11:55:51 +10:00
psychedelicious
34f3a0f0e3
feat(nodes): improve default model choosing output
2023-05-11 11:55:51 +10:00
psychedelicious
d0bac1675e
fix(nodes): fix ImageOutput Config
2023-05-11 11:55:51 +10:00
psychedelicious
4e56c962f4
fix(nodes): fix infill docstrings
2023-05-11 11:55:51 +10:00
psychedelicious
4ef0e43759
fix(nodes): remove dataURL invocation
2023-05-11 11:55:51 +10:00
psychedelicious
a7786d5ff2
fix(nodes): restore seamless to TextToLatents
2023-05-11 11:55:51 +10:00
psychedelicious
6c1de975d9
feat(nodes): add infill nodes
2023-05-11 11:55:51 +10:00
psychedelicious
a1079e455a
feat(nodes): cleanup unused params, seed generation
2023-05-11 11:55:51 +10:00
psychedelicious
da4eacdffe
feat(nodes): add InfillInvocation
2023-05-11 11:55:51 +10:00
psychedelicious
6102e560ba
feat(nodes): add LatentsToImage node (VAE encode)
2023-05-11 11:55:51 +10:00
psychedelicious
20f6a597ab
fix(nodes): add MetadataColorField
2023-05-11 11:55:51 +10:00
psychedelicious
206e6b1730
feat(nodes): wip inpaint node
2023-05-11 11:55:51 +10:00
psychedelicious
357cee2849
fix(nodes): fix cfg scale min value
2023-05-11 11:55:51 +10:00
psychedelicious
0b49997bb6
feat(nodes): allow uploaded images to be any ImageType (eg intermediates)
2023-05-11 11:55:51 +10:00
psychedelicious
5e09dd380d
Revert "feat(nodes): free gpu mem after invocation"
...
This reverts commit 99cb33f477306d5dcc455efe04053ce41b8d85bd.
2023-05-11 11:55:51 +10:00
psychedelicious
a75148cb16
feat(nodes): free gpu mem after invocation
2023-05-11 11:55:51 +10:00
psychedelicious
e0b9b5cc6c
feat(nodes): add dataURL to image node
2023-05-11 11:55:51 +10:00
psychedelicious
ee24ad7b13
fix(nodes): fix broken docs routes
2023-05-10 08:28:17 -04:00
psychedelicious
f8e90ba3f0
feat(nodes): add ui build static route
2023-05-10 08:28:17 -04:00
psychedelicious
7dfa135b2c
fix(nodes): fix #3306
...
Check if the cache has the object before deleting it.
2023-05-10 15:29:10 +10:00
Lincoln Stein
fa6a580452
merge with main
2023-05-10 00:03:32 -04:00
Lincoln Stein
4649920074
adjust t2i to work with new model structure
2023-05-07 19:06:49 -04:00
Lincoln Stein
667171ed90
cap model cache size using bytes, not # models
2023-05-07 18:07:28 -04:00
Lincoln Stein
647ffb2a0f
defined abstract baseclass for model manager service
2023-05-06 22:41:19 -04:00
Lincoln Stein
a8cfa3565c
Merge branch 'lstein/new-model-manager' of github.com:invoke-ai/InvokeAI into lstein/new-model-manager
2023-05-06 08:14:15 -04:00
Lincoln Stein
e0214a32bc
mostly ported to new manager API; needs testing
2023-05-06 00:44:12 -04:00
StAlKeR7779
a80fe05e23
Rename compel node
2023-05-05 21:30:16 +03:00
StAlKeR7779
58d7833c5c
Review changes
2023-05-05 21:09:29 +03:00
StAlKeR7779
5012f61599
Separate conditionings back to positive and negative
2023-05-05 15:47:51 +03:00
blessedcoolant
85c33823c3
Merge branch 'main' into feat/compel_node
2023-05-05 14:41:45 +12:00
psychedelicious
e04ada1319
Merge branch 'main' into patch-1
2023-05-05 10:38:45 +10:00
StAlKeR7779
81ec476f3a
Revert seed field addition
2023-05-04 21:50:40 +03:00
StAlKeR7779
1e6adf0a06
Fix default graph and test
2023-05-04 21:14:31 +03:00
StAlKeR7779
7d221e2518
Combine conditioning to one field(better fits for multiple type conditioning like perp-neg)
2023-05-04 20:14:22 +03:00
StAlKeR7779
56d3cbead0
Merge branch 'main' into feat/compel_node
2023-05-04 00:28:33 +03:00
Lincoln Stein
4687ad4ed6
Merge branch 'main' into enhance/invokeai-logs
2023-05-03 13:36:06 -04:00
psychedelicious
f9f40adcdc
fix(nodes): fix t2i graph
...
Removed width and height edges.
2023-05-02 13:11:28 +10:00
psychedelicious
3264d30b44
feat(nodes): allow multiples of 8 for dimensions
2023-05-02 12:01:52 +10:00
Eugene
d39de0ad38
fix(nodes): fix duplicate Invoker start/stop events
2023-05-01 18:24:37 -04:00
Eugene
d14a7d756e
nodes-api: enforce single thread for the processor
...
On hyperthreaded CPUs we get two threads operating on the queue by
default on each core. This cases two threads to process queue items.
This results in pytorch errors and sometimes generates garbage.
Locking this to single thread makes sense because we are bound by the
number of GPUs in the system, not by CPU cores. And to parallelize
across GPUs we should just start multiple processors (and use async
instead of threading)
Fixes #3289
2023-05-01 18:24:37 -04:00
