Lincoln Stein
28f1d25973
unpin dependencies; fix typo in sd3.py
2024-06-21 15:59:47 -04:00
Lincoln Stein
95377ea159
add non-commercial use message to sd3 starter; rebuild frontend
2024-06-20 21:59:28 -04:00
Lincoln Stein
445561e3a4
add sd3 to starter models
2024-06-20 18:13:46 -04:00
blessedcoolant
66260fd345
fix: Update Clip 3 slot title & lint issues
2024-06-20 08:53:35 +05:30
blessedcoolant
c403efa83f
fix: Make TE5 Optional
2024-06-20 08:45:36 +05:30
blessedcoolant
cd99ef2f46
Merge branch 'main' into lstein/feat/sd3-model-loading
2024-06-20 08:43:34 +05:30
Lincoln Stein
b03073d888
[MM] Add support for probing and loading SDXL VAE checkpoint files ( #6524 )
...
* add support for probing and loading SDXL VAE checkpoint files
* broaden regexp probe for SDXL VAEs
---------
Co-authored-by: Lincoln Stein <lstein@gmail.com>
2024-06-20 02:57:27 +00:00
steffylo
a43d602f16
fix(queue): add clear_queue_on_startup config to clear problematic queues
2024-06-19 11:39:25 +10:00
Ryan Dick
79ceac2f82
(minor) Use SilenceWarnings as a decorator rather than a context manager to save an indentation level.
2024-06-18 15:06:22 -04:00
Ryan Dick
8e47e005a7
Tidy SilenceWarnings context manager:
...
- Fix type errors
- Enable SilenceWarnings to be used as both a context manager and a decorator
- Remove duplicate implementation
- Check the initial verbosity on __enter__() rather than __init__()
2024-06-18 15:06:22 -04:00
Ryan Dick
d13aafb514
Tidy denoise_latents.py imports to all use absolute import paths.
2024-06-18 15:06:22 -04:00
Lincoln Stein
9dce4f09ae
scale default RAM cache by size of system evirtual memory
2024-06-18 13:49:12 -04:00
Brandon Rising
63a7e19dbf
Run ruff
2024-06-18 10:38:29 -04:00
Brandon Rising
fbc5a8ec65
Ignore validation on improperly formatted hashes (pytest)
2024-06-18 10:38:29 -04:00
Brandon Rising
8ce6e4540e
Run ruff
2024-06-18 10:38:29 -04:00
Brandon Rising
f14f377ede
Update validator list
2024-06-18 10:38:29 -04:00
Brandon Rising
1925f83f5e
Update validator list
2024-06-18 10:38:29 -04:00
Brandon Rising
3a5ad6d112
Update validator list
2024-06-18 10:38:29 -04:00
Brandon Rising
41a6bb45f3
Initial functionality
2024-06-18 10:38:29 -04:00
blessedcoolant
22b5c036aa
Revert "fix: height and weight not working on sd3 node"
...
This reverts commit be14fd59c9
2024-06-17 06:41:49 +05:30
blessedcoolant
be14fd59c9
fix: height and weight not working on sd3 node
2024-06-17 06:34:01 +05:30
psychedelicious
cd70937b7f
feat(api): improved model install confirmation page styling & messaging
2024-06-17 10:51:08 +10:00
psychedelicious
f002bca2fa
feat(ui): handle new model_install_download_started event
...
When a model install is initiated from outside the client, we now trigger the model manager tab's model install list to update.
- Handle new `model_install_download_started` event
- Handle `model_install_download_complete` event (this event is not new but was never handled)
- Update optimistic updates/cache invalidation logic to efficiently update the model install list
2024-06-17 10:07:10 +10:00
psychedelicious
56771de856
feat(ui): add redux actions for model_install_download_started event
2024-06-17 09:52:46 +10:00
psychedelicious
c11478a94a
chore(ui): typegen
2024-06-17 09:51:18 +10:00
psychedelicious
fb694b3e17
feat(app): add model_install_download_started event
...
Previously, we used `model_install_download_progress` for both download starting and progressing. When handling this event, we don't know which actual thing it represents.
Add `model_install_download_started` event to explicitly represent a model download started event.
2024-06-17 09:50:25 +10:00
psychedelicious
1bc98abc76
docs(ui): explain model install events
2024-06-17 09:33:46 +10:00
Lincoln Stein
423057a2e8
add config variable to suppress loading of sd3 text_encoder_3 T5 model
2024-06-16 16:28:39 -04:00
blessedcoolant
f65d50a4dd
wip: basic wrapper for generating sd3 images
2024-06-16 04:18:20 +05:30
Lincoln Stein
554809c647
return correct base type for sd3 VAEs
2024-06-15 18:17:03 -04:00
chainchompa
7f03b04b2f
Merge branch 'main' into chainchompa/model-install-deeplink
2024-06-14 17:16:25 -04:00
chainchompa
4029972530
formatting
2024-06-14 17:15:55 -04:00
chainchompa
328f160e88
refetch model installs when a new model install starts
2024-06-14 17:09:07 -04:00
chainchompa
aae318425d
added route for installing huggingface model from model marketplace
2024-06-14 17:08:39 -04:00
Lincoln Stein
ac0396e6f7
Merge branch 'lstein/feat/sd3-model-loading' of github.com:invoke-ai/InvokeAI into lstein/feat/sd3-model-loading
2024-06-14 16:48:20 -04:00
Lincoln Stein
78f704e7d5
tweak installer to select correct components of HF SD3 diffusers models
2024-06-14 16:46:24 -04:00
blessedcoolant
41236031b2
chore: remove unrequired changes to v1 workflow field types
2024-06-15 00:00:44 +05:30
Ryan Dick
785bb1d9e4
Fix all comparisons against the DEFAULT_PRECISION constant. DEFAULT_PRECISION is a torch.dtype. Previously, it was compared to a str in a number of places where it would always resolve to False. This is a bugfix that results in a change to the default behavior. In practice, this will not change the behavior for many users, because it only causes a change in behavior if a users has configured float32 as their default precision.
2024-06-14 11:26:10 -07:00
blessedcoolant
ddbd2ebd9d
wip: add Transformer Field to Node UI
2024-06-14 22:25:26 +05:30
blessedcoolant
0c970bc880
wip: add SD3 Model Loader Invocation
2024-06-14 22:21:09 +05:30
blessedcoolant
c79d9b9ecf
wip: Add Initial support for select SD3 models in UI
2024-06-14 16:04:16 +05:30
Lincoln Stein
a3cb5da130
Improve RAM<->VRAM memory copy performance in LoRA patching and elsewhere ( #6490 )
...
* allow model patcher to optimize away the unpatching step when feasible
* remove lazy_offloading functionality
* allow model patcher to optimize away the unpatching step when feasible
* remove lazy_offloading functionality
* do not save original weights if there is a CPU copy of state dict
* Update invokeai/backend/model_manager/load/load_base.py
Co-authored-by: Ryan Dick <ryanjdick3@gmail.com>
* documentation fixes requested during penultimate review
* add non-blocking=True parameters to several torch.nn.Module.to() calls, for slight performance increases
* fix ruff errors
* prevent crash on non-cuda-enabled systems
---------
Co-authored-by: Lincoln Stein <lstein@gmail.com>
Co-authored-by: Kent Keirsey <31807370+hipsterusername@users.noreply.github.com>
Co-authored-by: Ryan Dick <ryanjdick3@gmail.com>
2024-06-13 17:10:03 +00:00
Lincoln Stein
03b9d17d0b
draft sd3 loading; probable VRAM leak when using quantized submodels
2024-06-13 00:51:00 -04:00
Lincoln Stein
002f8242a1
add draft SD3 probing; there is an issue with FromOriginalControlNetMixin in backend.util.hotfixes due to new diffusers
2024-06-12 22:44:34 -04:00
blessedcoolant
568a4844f7
fix: other recursive imports
2024-06-10 04:12:20 -07:00
blessedcoolant
b1e56e2485
fix: SchedulerOutput not being imported correctly
2024-06-10 04:12:20 -07:00
Lincoln Stein
7d19af2caa
Merge branch 'main' into lstein/feat/simple-mm2-api
2024-06-08 18:55:06 -04:00
Ryan Dick
52c0c4a32f
Rename latent.py -> denoise_latents.py.
2024-06-07 09:28:42 -04:00
Ryan Dick
8f1afc032a
Move SchedulerInvocation to a new file. No functional changes.
2024-06-07 09:28:42 -04:00
Ryan Dick
854bca668a
Move CreateDenoiseMaskInvocation to its own file. No functional changes.
2024-06-07 09:28:42 -04:00
