c0d54d5414
Revert "always enqueue with fresh bounding box"
...
This reverts commit fae51da278b39c61cbbea5de88661b4bc546f1ce.
2024-04-10 21:48:34 +10:00
98bfbb73ac
always enqueue with fresh bounding box
2024-04-10 21:48:34 +10:00
f9af32a6d1
Fix the padding behavior when max-pooling regional IP-Adapter masks to mirror the downscaling behavior of SD and SDXL. Prior to this change, denoising with input latent dimensions that were not evenly divisible by 8 would raise an exception.
2024-04-09 16:50:43 -04:00
fba40eb1bd
Fix the padding behavior when max-pooling regional prompt masks to mirror the downscaling behavior of SD and SDXL. Prior to this change, denoising with input latent dimensions that were not evenly divisible by 8 would raise an exception.
2024-04-09 16:50:43 -04:00
69f6c24f52
Fix field ordering ( #6186 )
...
Changed fields to go in w/h x/y order.
## Summary
The prior ordering of height, then width, and y, then x, doesn't match
up with the expected UX. This has been changed.
## Checklist
- [X] _The PR has a short but descriptive title, suitable for a
changelog_
- [ ] _Tests added / updated (if applicable)_
- [ ] _Documentation added / updated (if applicable)_
2024-04-10 01:00:22 +05:30
80d631118d
Fix field ordering
...
Changed fields to go in w/h x/y order.
2024-04-09 14:17:55 -05:00
0c6dd32ece
(minor) Fix IP-Adapter conditional logic in CustomAttnProcessor2_0.
2024-04-09 15:06:51 -04:00
0bdbfd4d1d
Add support for IP-Adapter masks.
2024-04-09 15:06:51 -04:00
2e27ed5f3d
Pass IP-Adapter scales through the cross_attn_kwargs pathway, since they are the same for all attention layers. This change also helps to prepare for adding IP-Adapter region masks.
2024-04-09 15:06:51 -04:00
babdc64b17
(minor) Fix typo in IP-Adapter field description.
2024-04-09 15:06:51 -04:00
54327ec4a7
Remove documentation references to prompt-to-prompt cross-attention control.
2024-04-09 10:57:02 -04:00
4a828818da
Remove support for Prompt-to-Prompt cross-attention control (aka .swap()). This feature is not widely used. It does not work with SDXL and is incompatible with IP-Adapter and regional prompting. The implementation is also intertwined with both text embedding and the UNet attention layers, resulting in a high maintenance burden. For all of these reasons, we have decided to drop support.
2024-04-09 10:57:02 -04:00
fe386252f3
Revert "feat(nodes): add prompt region from image nodes"
...
This reverts commit 3a531c5097
2024-04-09 08:12:12 -04:00
182810337c
Add utility to_standard_float_mask(...) to convert various mask formats to a standardized format.
2024-04-09 08:12:12 -04:00
338bf808d6
Rename MaskField to be a generice TensorField.
2024-04-09 08:12:12 -04:00
5b5a4204a1
Fix dimensions of mask produced by ExtractMasksAndPromptsInvocation. Also, added a clearer error message in case the same error is introduced in the future.
2024-04-09 08:12:12 -04:00
75ef473748
Pull the upstream changes from diffusers' AttnProcessor2_0 into CustomAttnProcessor2_0. This fixes a bug in CustomAttnProcessor2_0 that was being triggered when peft was not installed. The bug was present in a block of code that was previously copied from diffusers. The bug seems to have been introduced during diffusers' migration to PEFT for their LoRA handling. The upstream bug was fixed in 531e719163.
2024-04-09 08:12:12 -04:00
926b8d0efe
feat(nodes): add prompt region from image nodes
2024-04-09 08:12:12 -04:00
9d9d1761f3
(minor) The latest ruff version has _slightly_ different formatting preferences.
2024-04-09 08:12:12 -04:00
a78df8123f
Update the diffusion logic to use the new regional prompting feature.
2024-04-09 08:12:12 -04:00
7ca677578e
Create a UNetAttentionPatcher for patching UNet models with CustomAttnProcessor2_0 modules.
2024-04-09 08:12:12 -04:00
31c456c1e6
Update CustomAttention to support both IP-Adapters and regional prompting.
2024-04-09 08:12:12 -04:00
2ce79b61f5
Initialize a RegionalPromptAttnProcessor2_0 class by copying AttnProcessor2_0 from diffusers.
2024-04-09 08:12:12 -04:00
109e3f0e7f
Add RegionalPromptData class for managing prompt region masks.
2024-04-09 08:12:12 -04:00
dc64fec771
Add support for lists of prompt embeddings to be passed to the DenoiseLatents invocation, and add handling of the conditioning region masks in DenoiseLatents.
2024-04-09 08:12:12 -04:00
d1e45585d0
Add TextConditioningRegions to the TextConditioningData data structure.
2024-04-09 08:12:12 -04:00
aba023e0c5
Improve documentation of conditioning_data.py.
2024-04-09 08:12:12 -04:00
e354c29b52
Rename ConditioningData -> TextConditioningData.
2024-04-09 08:12:12 -04:00
a7f363e654
Split ip_adapter_conditioning out from ConditioningData.
2024-04-09 08:12:12 -04:00
9b2162e564
Remove scheduler_args from ConditioningData structure.
2024-04-09 08:12:12 -04:00
4e64b26702
Update compel nodes to accept an optional prompt mask.
2024-04-09 08:12:12 -04:00
c22d772062
Add RectangleMaskInvocation.
2024-04-09 08:12:12 -04:00
d6be7662c9
Add a MaskField primitive, and add a mask to the ConditioningField primitive type.
2024-04-09 08:12:12 -04:00
95050088d1
chore: lint fixes
2024-04-09 14:13:10 +10:00
94b5084cd5
fix: one man's max is another man's min
2024-04-09 14:13:10 +10:00
ca0d60bee6
fix: set coherence denoise to 0.2 min for refiner models
2024-04-09 14:13:10 +10:00
fd1f240853
fix: SDXL Refiner not working properly with Inpainting
2024-04-09 14:13:10 +10:00
381b41a56e
fix: Update SDXL Refiner graphs to use Gradient Mask
2024-04-09 14:13:10 +10:00
b58494c420
feat(ui): add graph-to-workflow debug helper
...
This is intended for debug usage, so it's hidden away in the workflow library `...` menu. Hold shift to see the button for it.
- Paste a graph (from a network request, for example) and then click the convert button to convert it to a workflow.
- Disable auto layout to stack the nodes with an offset (try it out). If you change this, you must re-convert to get the changes.
- Edit the workflow JSON if you need to tweak something before loading it.
2024-04-08 20:38:04 -04:00
dca30d5462
(feat) add a method to get the path of an image from the invocation context
...
Fixes #6175
2024-04-08 18:42:55 +10:00
9ab6655491
feat(backend): clean up choose_precision
...
- Allow user-defined precision on MPS.
- Use more explicit logic to handle all possible cases.
- Add comments.
- Remove the app_config args (they were effectively unused, just get the config using the singleton getter util)
2024-04-07 09:41:05 -04:00
29cfe5a274
fix(ui): handle multipleOf on number fields
...
This data is already in the template but it wasn't ever used.
One big place where this improves UX is the noise node. Previously, the UI let you change width and height in increments of 1, despite the template requiring a multiple of 8. It now works in multiples of 8.
2024-04-06 13:15:20 -04:00
2c45697f3d
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
2024-04-06 15:19:20 +11:00
9a0a90e2a2
chore: v4.0.4
2024-04-06 15:15:16 +11:00
69f17da1a2
fix(nodes): add WithBoard to public API
2024-04-06 15:02:28 +11:00
4d0a49298c
tidy(ui): remove extraneous zod schema
2024-04-06 14:54:12 +11:00
55f7a7737a
feat(ui): shift around init image recall logic
...
Retrieving the DTO happens as part of the metadata parsing, not recall. This way, we don't show the option to recall a nonexistent image.
This matches the flow for other metadata entities like models - we don't show the model recall button if the model isn't available.
2024-04-06 14:54:12 +11:00
adc30045a6
addressed pr feedback
2024-04-06 14:54:12 +11:00
fdd0e57976
actually use the schema
2024-04-06 14:54:12 +11:00
9ba5ec4b67
fix typo Params set set
2024-04-06 14:54:12 +11:00
