Ryan Dick
8cfb032051
Add utility ImagePanelLayoutInvocation for working with In-Context LoRA workflows.
2024-11-26 20:58:31 -08:00
Ryan Dick
06a9d4e2b2
Use a Textarea component for the FluxTextEncoderInvocation prompt field.
2024-11-26 20:58:31 -08:00
Brandon Rising
ed46acee79
fix: Fail scan on InvalidMagicError in picklescan, update default for read_checkpoint_meta to scan unless explicitly told not to
2024-11-26 16:17:12 -05:00
Ryan Dick
b54463d294
Allow regional prompting background regions to attend to themselves and to the entire txt embedding.
2024-11-26 17:57:31 +00:00
Ryan Dick
faee79dc95
Distinguish between restricted and unrestricted attn masks in FLUX regional prompting.
2024-11-26 16:55:52 +00:00
Mary Hipp
965cd76e33
lint fix
2024-11-26 11:25:53 -05:00
Mary Hipp
e5e8cbf34c
shorten reference image mode descriptions;
2024-11-26 11:25:53 -05:00
Mary Hipp
3412a52594
(ui): updates various informational tooltips, adds descriptons to IP adapter method options
2024-11-26 11:25:53 -05:00
Ryan Dick
e01f66b026
Apply regional attention masks in the single stream blocks in addition to the double stream blocks.
2024-11-25 22:40:08 +00:00
Ryan Dick
53abdde242
Update Flux RegionalPromptingExtension to prepare both a mask with restricted image self-attention and a mask with unrestricted image self attention.
2024-11-25 22:04:23 +00:00
Ryan Dick
94c088300f
Be smarter about selecting the global CLIP embedding for FLUX regional prompting.
2024-11-25 20:15:04 +00:00
Ryan Dick
3741a6f5e0
Fix device handling for regional masks and apply the attention mask in the FLUX double stream block.
2024-11-25 16:02:03 +00:00
Kent Keirsey
059336258f
Create SECURITY.md
2024-11-25 04:10:03 -08:00
Ryan Dick
2c23b8414c
Use a single global CLIP embedding for FLUX regional guidance.
2024-11-22 23:01:43 +00:00
Mary Hipp
271cc52c80
fix(ui): use token for download if its in store
2024-11-22 12:08:05 -05:00
Ryan Dick
20356c0746
Fixup the logic for preparing FLUX regional prompt attention masks.
2024-11-21 22:46:25 +00:00
psychedelicious
e44458609f
chore: bump version to v5.4.3rc1
2024-11-21 10:32:43 -08:00
psychedelicious
69d86a7696
feat(ui): address feedback
2024-11-21 09:54:35 -08:00
Hippalectryon
56db1a9292
Use proxyrect and setEntityPosition to sync transformer position
2024-11-21 09:54:35 -08:00
Hippalectryon
cf50e5eeee
Make sure the canvas is focused
2024-11-21 09:54:35 -08:00
Hippalectryon
c9c07968d2
lint
2024-11-21 09:54:35 -08:00
Hippalectryon
97d0757176
use $isInteractable instead of $isDisabled
2024-11-21 09:54:35 -08:00
Hippalectryon
0f51b677a9
refactor
2024-11-21 09:54:35 -08:00
Hippalectryon
56ca94c3a9
Don't move if the layer is disabled
...
Lint
2024-11-21 09:54:35 -08:00
Hippalectryon
28d169f859
Allow moving layers using the keyboard
2024-11-21 09:54:35 -08:00
psychedelicious
92f71d99ee
tweak(ui): use X icon for rg ref image delete button
2024-11-21 08:50:39 -08:00
psychedelicious
0764c02b1d
tweak(ui): code style
2024-11-21 08:50:39 -08:00
psychedelicious
081c7569fe
feat(ui): add global ref image empty state
2024-11-21 08:50:39 -08:00
psychedelicious
20f6532ee8
feat(ui): add empty state for regional guidance ref image
2024-11-21 08:50:39 -08:00
Mary Hipp
b9e8910478
feat(ui): add actions for video modal clicks
2024-11-21 11:15:55 -05:00
Mary Hipp
ded8391e3c
use nanostore for schema parsed instead
2024-11-20 20:13:31 -05:00
Mary Hipp
e9dd2c396a
limit to one hook
2024-11-20 20:13:31 -05:00
Mary Hipp
0d86de0cb5
fix(ui): make sure schema has loaded before trying to load any workflows
2024-11-20 20:13:31 -05:00
Ryan Dick
bad1149504
WIP - add rough logic for preparing the FLUX regional prompting attention mask.
2024-11-20 22:29:36 +00:00
Ryan Dick
fda7aaa7ca
Pass RegionalPromptingExtension down to the CustomDoubleStreamBlockProcessor in FLUX.
2024-11-20 19:48:04 +00:00
Ryan Dick
85c616fa34
WIP - Pass prompt masks to FLUX model during denoising.
2024-11-20 18:51:43 +00:00
psychedelicious
549f4e9794
feat(ui): set default infill method to lama
2024-11-20 11:19:17 -05:00
psychedelicious
ef8ededd2f
fix(ui): disable width and height output on image batch output
...
There's a technical challenge with outputting these values directly. `ImageField` does not store them, so the batch's `ImageField` collection does not have width and height for each image.
In order to set up the batch and pass along width and height for each image, we'd need to make a network request for each image when the user clicks Invoke. It would often be cached, but this will eventually create a scaling issue and poor user experience.
As a very simple workaround, users can output the batch image output into an `Image Primitive` node to access the width and height.
This change is implemented by adding some simple special handling when parsing the output fields for the `image_batch` node.
I'll keep this situation in mind when extending the batching system to other field types.
2024-11-20 11:16:54 -05:00
Mary Hipp
1948ffe106
make sure Soft Edge Detection has preprocessor applied
2024-11-20 08:46:02 -05:00
psychedelicious
c70f4404c4
fix(ui): special node icon tooltip
2024-11-19 14:29:09 -08:00
psychedelicious
b157ae928c
chore(ui): update what's new copy
2024-11-19 14:29:09 -08:00
psychedelicious
7a0871992d
chore: bump version to v5.4.2
2024-11-19 14:29:09 -08:00
Hosted Weblate
b38e2e14f4
translationBot(ui): update translation files
...
Updated by "Cleanup translation files" hook in Weblate.
translationBot(ui): update translation files
Updated by "Cleanup translation files" hook in Weblate.
Co-authored-by: Hosted Weblate <hosted@weblate.org >
Translate-URL: https://hosted.weblate.org/projects/invokeai/web-ui/
Translation: InvokeAI/Web UI
2024-11-19 14:12:00 -08:00
psychedelicious
7c0e70ec84
tweak(ui): "Watch on YouTube" -> "Watch"
2024-11-19 14:02:11 -08:00
psychedelicious
a89ae9d2bf
feat(ui): add links to studio sessions/discord
2024-11-19 14:02:11 -08:00
psychedelicious
ad1fcb3f07
chore(ui): bump @invoke-ai/ui-library
...
Brings in a fix for `ExternalLink`
2024-11-19 14:02:11 -08:00
psychedelicious
87d74b910b
feat(ui): support videos modal
2024-11-19 14:02:11 -08:00
psychedelicious
7ad1c297a4
feat(ui): add actions for reset canvas layers / generation settings to session menus
2024-11-19 13:55:16 -08:00
psychedelicious
fbc629faa6
feat(ui): change reset canvas button to new session menu
2024-11-19 13:55:16 -08:00
psychedelicious
7baa6b3c09
feat(ui): split up new from image into submenus
...
- `New Canvas from Image` -> `As Raster Layer`, `As Raster Layer (Resize)`, `As Control Layer`, `As Control Layer (Resize)`
- `New Layer from Image` -> (each layer type)
2024-11-19 10:34:00 -08:00
