Commit Graph

1414 Commits

Author SHA1 Message Date
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
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
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
psychedelicious
236c0d89e7 feat(nodes): add string batch node 2025-01-17 12:19:04 +11:00
psychedelicious
3f70e947fd chore: ruff 2025-01-16 09:27:36 +11:00
dunkeroni
157290bef4 add: size option for image noise node and filter 2025-01-16 09:27:36 +11:00
dunkeroni
b7389da89b add: Noise filter on Canvas 2025-01-16 09:27:36 +11:00
dunkeroni
2b122d7882 add: image noise invocation 2025-01-16 09:27:36 +11:00
dunkeroni
ded9213eb4 trim blur splitting logic 2025-01-16 09:27:36 +11:00
dunkeroni
9d51eb49cd fix: ImageBlurInvocation handles transparency now 2025-01-16 09:27:36 +11:00
dunkeroni
0a6e22bc9e fix: ImagePasteInvocation respects transparency 2025-01-16 09:27:36 +11:00
Ryan Dick
b301785dc8 Normalize the T5 model identifiers so that a FLUX T5 or an SD3 T5 model can be used interchangeably. 2025-01-16 08:33:58 +11:00
Ryan Dick
497bc916cc Add unet_config to get_scheduler(...) call in TiledMultiDiffusionDenoiseLatents. 2025-01-15 08:44:08 -05:00
dunkeroni
ebe1873712 fix: only add prediction type if it exists 2025-01-15 08:44:08 -05:00
dunkeroni
59926c320c support v-prediction in denoise_latents.py 2025-01-15 08:44:08 -05:00
David Burnett
afc9d3b98f more ruff formating 2025-01-07 20:18:19 -05:00
David Burnett
7ddc757bdb ruff format changes 2025-01-07 20:18:19 -05:00
David Burnett
d8da9b45cc Fix for DEIS / DPM clash 2025-01-07 20:18:19 -05:00
Ryan Dick
607d19f4dd We should not trust the value of since the model could be partially-loaded. 2025-01-07 19:22:31 -05:00
Ryan Dick
85eb4f0312 Fix an edge case with model offloading from VRAM to RAM. If a GGML-quantized model is offloaded from VRAM inside of a torch.inference_mode() context manager, this will cause the following error: 'RuntimeError: Cannot set version_counter for inference tensor'. 2025-01-07 15:59:50 +00:00
Ryan Dick
71b97ce7be Reduce the likelihood of encountering https://github.com/invoke-ai/InvokeAI/issues/7513 by elminating places where the door was left open for this to happen. 2025-01-07 01:20:15 +00:00
Ryan Dick
4abfb35321 Tune SD3 VAE decode working memory estimate. 2025-01-07 01:20:15 +00:00
Ryan Dick
cba6528ea7 Add a 20% buffer to all VAE decode working memory estimates. 2025-01-07 01:20:15 +00:00
Ryan Dick
6a5cee61be Tune the working memory estimate for FLUX VAE decoding. 2025-01-07 01:20:15 +00:00