psychedelicious
50cb27cd0b
feat(nodes): support collect -> iterate node connections w/ validation
2025-02-06 07:57:26 +11:00
psychedelicious
8556a2558e
chore(nodes): better naming for graph validation utils
2025-02-06 07:57:26 +11:00
psychedelicious
2fb35d25dd
feat(nodes): field type Any accepts collections
2025-02-06 07:57:26 +11:00
psychedelicious
592e45a078
feat(nodes): improved graph validation error messages
2025-02-06 07:57:26 +11:00
skunkworxdark
dfb9e300d4
typegen + Suggested changes (fix typo + remove asserts)
2025-02-04 21:37:04 +11:00
skunkworxdark
d7f80fc299
Update invokeai/app/invocations/flux_lora_loader.py
...
good catch
Co-authored-by: psychedelicious <4822129+psychedelicious@users.noreply.github.com >
2025-02-04 21:37:04 +11:00
skunkworxdark
c9b1eb2d83
update to include T5EncoderField lora changes
2025-02-04 21:37:04 +11:00
skunkworxdark
13d505a621
Fix github test errors
...
Fix errors with typegen and py3.10 macos-default github tests
2025-02-04 21:37:04 +11:00
skunkworxdark
6674d95dae
fix typegen error
...
fix typegen error
2025-02-04 21:37:04 +11:00
skunkworxdark
71690715db
fix typegen
...
fix typegen
2025-02-04 21:37:04 +11:00
skunkworxdark
641489c2f8
fix typegen error
...
fix typegen
2025-02-04 21:37:04 +11:00
skunkworxdark
5f0bd2e1db
Fix typegen issue
...
Fix typegen issue
2025-02-04 21:37:04 +11:00
skunkworxdark
98b8ab0147
LoRA Loader optional LoRA Collection
...
Update the LoRA Loaders to make the Lora Collection Optional
2025-02-04 21:37:04 +11:00
Riku
47dc954385
feat(app): add cancel all except current queue item functionality
2025-02-04 12:23:23 +11:00
psychedelicious
8fc5d3dd20
chore(nodes): bump versions of changed nodes
2025-02-04 12:06:17 +11:00
dunkeroni
9c7bac693b
fix image adjust hue handling
2025-02-04 12:06:17 +11:00
dunkeroni
cc27730cb4
fix: image channel invocations respect alpha
2025-02-04 12:06:17 +11:00
dunkeroni
58255ab7ba
add adjust image filter to canvas
2025-02-04 12:06:17 +11:00
Ryan Dick
cc9d215a9b
Add endpoint for emptying the model cache. Also, adds a threading lock to the ModelCache to make it thread-safe.
2025-01-30 09:18:28 -05:00
Ryan Dick
285313b282
Fix T5EncoderField initialization in SD3 model loader.
2025-01-29 09:27:52 -05:00
Ryan Dick
5357d6e08e
Rename ConcatenatedLoRALayer to MergedLayerPatch. And other minor cleanup.
2025-01-28 14:51:35 +00:00
Ryan Dick
7fef569e38
Update frontend graph building logic to support FLUX LoRAs that modify the T5 encoder weights.
2025-01-28 14:51:35 +00:00
Ryan Dick
f4a0b78a8d
Update FLUX invocations to support LoRAs that modify the T5 text encoder.
2025-01-28 14:51:35 +00:00
Ryan Dick
b681132da4
Update InvertTensorMaskInvocation to handle mask tensors with dim 2 or 3.
2025-01-24 22:04:46 +00:00
Ryan Dick
f60a5a5015
Update SegmentAnythingInvocation invocations to return masks with a channel dimension of size 1. This is the convention used by other nodes that produce a MaskOutput.
2025-01-24 22:04:10 +00:00
psychedelicious
b7b8f8a9e5
fix(nodes): remove WithMetadata from non-image-outputting node
2025-01-21 17:58:47 +11:00
psychedelicious
e926d2f24b
fix(nodes): add beta classification to new inpainting support nodes
2025-01-21 17:58:47 +11:00
psychedelicious
cf4c79fe2e
feat(nodes): add PasteImageIntoBoundingBoxInvocation
2025-01-21 17:45:32 +11:00
psychedelicious
e0edfe6c40
feat(nodes): add CropImageToBoundingBoxInvocation
2025-01-21 17:45:32 +11:00
psychedelicious
8a0a37191a
feat(nodes): add GetMaskBoundingBoxInvocation
2025-01-21 17:45:32 +11:00
psychedelicious
7dbd5f150a
feat(nodes): add BoundingBoxField.tuple() to get bbox as PIL tuple
2025-01-21 17:45:32 +11:00
psychedelicious
1ad65ffd53
feat(nodes): re-title "Mask from ID" -> "Mask from Segmented Image"
2025-01-21 17:45:32 +11:00
psychedelicious
14b5c871dc
feat(nodes): simplify MaskFromIDInvocation
2025-01-21 17:45:32 +11:00
psychedelicious
8d2b4e2bf5
feat(nodes): support FLUX, SD3 in ideal_size
2025-01-21 17:45:32 +11:00
psychedelicious
2b2ec67cd6
fix(nodes): allow connection input on string batch nodes
2025-01-21 07:17:29 +11:00
psychedelicious
81da5210f0
feat(api): add seed field to dynamicprompts
2025-01-20 08:57:42 +11:00
psychedelicious
526d64a5e2
feat(nodes): add string generator
2025-01-20 08:57:42 +11:00
psychedelicious
508c702289
feat(nodes): remove default values for generator; let UI handle it
2025-01-17 12:48:58 +11:00
psychedelicious
8fbd2f9a97
feat(nodes): add integer generator nodes
2025-01-17 12:48:58 +11:00
psychedelicious
2f9a0a250d
feat(nodes): generators as nodes
2025-01-17 12:48:58 +11:00
psychedelicious
5d03328dc6
tidy(nodes): code dedupe for batch node init errors
2025-01-17 12:48:58 +11:00
psychedelicious
1fb32aec28
tidy(nodes): move batch nodes to own file
2025-01-17 12:48:58 +11:00
psychedelicious
26e6e28a13
feat(nodes): add title for batch_group_id field
2025-01-17 12:34:54 +11:00
psychedelicious
05f1026812
feat(nodes): batch_group_id is a literal of options
2025-01-17 12:34:54 +11:00
psychedelicious
c23a2abc82
feat(nodes): rename "link_id" -> "batch_group_id"
2025-01-17 12:34:54 +11:00
psychedelicious
7ee51f3e14
feat(nodes): add link_id field to batch nodes
...
This is used to link batch nodes into zipped batch data collections.
2025-01-17 12:34:54 +11:00
psychedelicious
5bff6123b9
feat(nodes): add default value for batch nodes
2025-01-17 12:19:04 +11:00
psychedelicious
db5f016826
fix(nodes): allow batch datum items to mix ints and floats
...
Unfortunately we cannot do strict floats or ints.
The batch data models don't specify the value types, it instead relies on pydantic parsing. JSON doesn't differentiate between float and int, so a float `1.0` gets parsed as `1` in python.
As a result, we _must_ accept mixed floats and ints for BatchDatum.items.
Tests and validation updated to handle this.
Maybe we should update the BatchDatum model to have a `type` field? Then we could parse as float or int, depending on the inputs...
2025-01-17 12:19:04 +11:00
psychedelicious
0f1e632117
feat(nodes): add float batch node
2025-01-17 12:19:04 +11:00
psychedelicious
90a91ff438
feat(nodes): add integer batch node
2025-01-17 12:19:04 +11:00
