Mary Hipp
fa810e1d02
add gemini 2.5 to base model
2025-08-27 08:56:15 -04:00
psychedelicious
04d1958e93
feat(app): vendor in invisible-watermark
...
Fixes errors like `AttributeError: module 'cv2.ximgproc' has no
attribute 'thinning'` which occur because there is a conflict between
our own `opencv-contrib-python` dependency and the `invisible-watermark`
library's `opencv-python`.
2025-08-23 14:17:56 +10:00
Kent Keirsey
af58a75e97
Support PEFT Loras with Base_Model.model prefix ( #8433 )
...
* Support PEFT Loras with Base_Model.model prefix
* update tests
* ruff
* fix python complaints
* update kes
* format keys
* remove unneeded test
2025-08-18 09:14:46 -04:00
psychedelicious
fd4c3bd27a
refactor: estimate working vae memory during encode/decode
...
- Move the estimation logic to utility functions
- Estimate memory _within_ the encode and decode methods, ensuring we
_always_ estimate working memory when running a VAE
2025-08-18 21:43:14 +10:00
jiangmencity
5259693ed1
chore: fix some comments
...
Signed-off-by: jiangmencity <jiangmen@52it.net >
2025-08-14 09:32:54 +10:00
psychedelicious
23d59abbd7
chore: ruff
2025-08-12 10:51:05 +10:00
psychedelicious
cf7fa5bce8
perf(backend): clear torch cache after encoding each image in kontext extension
...
Slightly reduces VRAM allocations.
2025-08-12 10:51:05 +10:00
psychedelicious
c6eff71b74
fix(backend): bug in kontext canvas dimension tracking when concating in latent space
...
We weren't tracking the canvas dimensions properly which coudl result in
FLUX not "seeing" ref images after the first very well
2025-08-12 10:51:05 +10:00
psychedelicious
7d86f00d82
feat(mm): implement working memory estimation for VAE encode for all models
...
Tell the model manager that we need some extra working memory for VAE
encoding operations to prevent OOMs.
See previous commit for investigation and determination of the magic
numbers used.
This safety measure is especially relevant now that we have FLUX Kontext
and may be encoding rather large ref images. Without the working memory
estimation we can OOM as we prepare for denoising.
See #8405 for an example of this issue on a very low VRAM system. It's
possible we can have the same issue on any GPU, though - just a matter
of hitting the right combination of models loaded.
2025-08-12 10:51:05 +10:00
psychedelicious
111408c046
feat(mm): add flux krea to starter models
2025-08-05 10:25:14 +10:00
psychedelicious
d7619d465e
feat(mm): change anime upscaling model to one that doesn't trigger picklescan
2025-08-05 10:25:14 +10:00
psychedelicious
0cd77443a7
feat(app): add setting to disable picklescan
...
When unsafe_disable_picklescan is enabled, instead of erroring on
detections or scan failures, a warning is logged.
A warning is also logged on app startup when this setting is enabled.
The setting is disabled by default and there is no change in behaviour
when disabled.
2025-08-05 09:54:00 +10:00
psychedelicious
e522de33f8
refactor(nodes): roll back latent-space resizing of kontext images
2025-08-04 23:03:12 +10:00
psychedelicious
56d75e1c77
feat(backend): use VAE mean encoding for Kontext reference images
...
Use distribution mean without sampling noise for more stable and
consistent reference image encoding, matching ComfyUI implementation
2025-08-04 23:03:12 +10:00
psychedelicious
df77a12efe
refactor(backend): use torchvision transforms for Kontext image preprocessing
...
Replace numpy-based normalization with torchvision transforms for
consistency with other image processing in the codebase
2025-08-04 23:03:12 +10:00
psychedelicious
faf662d12e
refactor(backend): use BICUBIC resampling for Kontext images
...
Switch from LANCZOS to BICUBIC for smoother image resizing to reduce
artifacts in reference image processing
2025-08-04 23:03:12 +10:00
psychedelicious
44a7dfd486
fix(backend): use consistent idx_offset=1 for all Kontext images
...
Changes from per-image index offsets to a consistent value of 1 for
all reference images, matching the ComfyUI implementation
2025-08-04 23:03:12 +10:00
psychedelicious
bb15e5cf06
feat(backend): add spatial tiling for multiple Kontext reference images
...
Implements intelligent spatial tiling that arranges multiple reference
images in a virtual canvas, choosing between horizontal and vertical
placement to maintain a square-like aspect ratio
2025-08-04 23:03:12 +10:00
psychedelicious
1a1c846be3
feat(backend): include reference images in negative CFG pass for Kontext
...
Maintains consistency between positive and negative passes to prevent
CFG artifacts when using Kontext reference images
2025-08-04 23:03:12 +10:00
psychedelicious
93c896a370
fix(backend): use img_cond_seq to check for Kontext slicing
...
Was incorrectly checking img_input_ids instead of img_cond_seq
2025-08-04 23:03:12 +10:00
psychedelicious
1ed1fefa60
feat(nodes): support multiple kontext ref images
...
Images are concatenated in latent space.
2025-07-30 12:26:48 +10:00
Kent Keirsey
c3f6389291
fix ruff and remove unused API route
2025-07-22 07:33:48 +10:00
Kent Keirsey
b14d841d57
Extract util and fix model image logic
2025-07-22 07:33:48 +10:00
psychedelicious
e62d3f01a8
feat(app): better error message for failed model probe
...
- Old: No valid config found
- New: Unable to determine model type
2025-07-11 23:35:43 +10:00
Kent Keirsey
b5d1c47ef7
final link fix
2025-07-09 10:17:38 +10:00
Kent Keirsey
004a52ca65
fix to direct links
2025-07-09 10:17:38 +10:00
Kent Keirsey
b1d5a51ddf
add-quantized-kontext-dev
2025-07-09 10:17:38 +10:00
psychedelicious
68571ece8f
tidy(app): remove unused methods
2025-07-04 20:35:29 +10:00
psychedelicious
4887424ca3
chore: ruff
2025-07-04 20:35:29 +10:00
Kent Keirsey
28f6a20e71
format import block
2025-07-04 20:35:29 +10:00
Kent Keirsey
c4142e75b2
fix import
2025-07-04 20:35:29 +10:00
Kent Keirsey
fefe563127
fix resizing and versioning
2025-07-04 20:35:29 +10:00
Kent Keirsey
e7ce08cffa
ruff format
2025-07-04 19:24:44 +10:00
Kent Keirsey
983cb5ebd2
ruff ruff
2025-07-04 19:24:44 +10:00
Kent Keirsey
52dbdb7118
ruff
2025-07-04 19:24:44 +10:00
Kent Keirsey
71e6f00e10
test fixes
...
fix
test
fix 2
fix 3
fix 4
yet another
attempt new fix
pray
more pray
lol
2025-07-04 19:24:44 +10:00
skunkworxdark
604763d20f
Update flux.py
...
Replace T5Tokenizer with T5TokenizerFast
2025-07-03 08:04:08 +10:00
psychedelicious
075345bffd
feat(app): add flux kontext dev to starter modelss
2025-06-27 18:27:46 +10:00
Kent Keirsey
51e1c56636
ruff
2025-06-27 18:27:46 +10:00
Kent Keirsey
ca1df60e54
Explain the Magic
2025-06-27 18:27:46 +10:00
Cursor Agent
7549c1250d
Add FLUX Kontext conditioning support for reference images
...
Co-authored-by: kent <kent@invoke.ai >
Fix Kontext sequence length handling in Flux denoise invocation
Co-authored-by: kent <kent@invoke.ai >
Fix Kontext step callback to handle combined token sequences
Co-authored-by: kent <kent@invoke.ai >
fix ruff
Fix Flux Kontext
2025-06-27 18:27:46 +10:00
psychedelicious
6172c859ac
feat(api): enrich starer model bundle metadata
2025-06-27 14:37:30 +10:00
psychedelicious
e164451dfe
chore: ruff
2025-06-26 20:00:38 +10:00
psychedelicious
b2b42be51c
refactor: remove unused methods/routes, fix some gallery invalidation issues
2025-06-26 20:00:37 +10:00
Billy
6afbf31750
Ruff formatting
2025-06-26 19:47:06 +10:00
Billy
3cd4306eec
Update import path
2025-06-26 19:47:06 +10:00
Billy
827191d2fc
Use definitions in config
2025-06-26 19:47:06 +10:00
Billy
aaa34f717d
OMI files
2025-06-26 19:47:06 +10:00
Billy
fe83c2f81f
Add OMI vendor files
2025-06-26 19:47:06 +10:00
Billy
17dead3309
Remove OMI from dependencies
2025-06-26 19:47:06 +10:00
