Brandon Rising
66bbd62758
Run ruff and fix typing in torch patcher
2024-10-02 18:33:05 -04:00
Brandon Rising
0875e861f5
Various updates to gguf performance
2024-10-02 18:33:05 -04:00
Ryan Dick
807f458f13
Move FLUX_LORA_TRANSFORMER_PREFIX and FLUX_LORA_CLIP_PREFIX to a shared location.
2024-10-01 10:22:11 -04:00
Ryan Dick
ba8ef6ff0f
(minor) remove remaining incorrect references to T5 encoder in comments.
2024-09-30 07:59:14 -04:00
Ryan Dick
c256826015
Whoops, the 'lora_te1' prefix in FLUX kohya models refers to the CLIP text encoder - not the T5 as previously assumed. Update everything accordingly.
2024-09-30 07:59:14 -04:00
Ryan Dick
7d38a9b7fb
Add prefix to distinguish FLUX LoRA submodels.
2024-09-30 07:59:14 -04:00
Ryan Dick
249da858df
Add support for FLUX T5 text encoder LoRA models to invocations.
2024-09-30 07:59:14 -04:00
Ryan Dick
bdeec54886
Remove FLUX TrajectoryGuidanceExtension and revert to the InpaintExtension. Keep the improved inpaint gradient mask adjustment behaviour.
2024-09-26 19:54:28 -04:00
Ryan Dick
ba07e255f5
Add support for fractional denoise start and end with FLUX.
2024-09-26 19:54:28 -04:00
Ryan Dick
fae96f3b9f
Remove trajectory_guidance_strength parameter.
2024-09-26 19:54:28 -04:00
psychedelicious
12e54eb249
feat(nodes): mark core metadata internal
2024-09-23 16:16:51 +03:00
psychedelicious
c0609f760f
feat(app): use new signal_progress API for spandrel nodes
...
Both the vanilla and autoscale invocations report progress while processing each tile.
The autoscale version, which may run the spandrel model multiple times, also includes the current iteration.
2024-09-22 21:20:32 +03:00
Ryan Dick
183a67cb1e
Merge branch 'main' into ryan/flux-trajectory-guidance
2024-09-20 22:29:34 +00:00
maryhipp
e50f71ec53
bump version of flux_denoise node, update default workflows
2024-09-20 15:41:44 -04:00
psychedelicious
6540381fb5
feat(nodes): clean up canvas v2's output node
...
- Marked internal
- Changed output type to plain ol' `ImageOutput`
- Removed unused code
2024-09-20 16:01:02 +03:00
psychedelicious
2d617f6067
feat(nodes): add Classification.Internal
...
This can be used for nodes that Invoke uses internally. Internal nodes do not have API stability guarantees. For example, they may change if the needs of the linear UI change.
2024-09-20 16:01:02 +03:00
Ryan Dick
e8357afd3a
Add traj_guidance_strength to FluxDenoiseInvocation.
2024-09-20 02:41:52 +00:00
maryhipp
5fa0a9479d
fix type for transformer
2024-09-19 10:08:19 -04:00
maryhipp
3b16aca83a
updated node description
2024-09-19 10:08:19 -04:00
maryhipp
f4ac7489ea
ruff check again
2024-09-19 10:08:19 -04:00
maryhipp
1f667f044a
mark both FLUX LoRA nodes as prototype
2024-09-19 10:08:19 -04:00
maryhipp
ab3d239931
ruff checkk
2024-09-19 10:08:19 -04:00
maryhipp
d4a7e48109
lora collector node
2024-09-19 10:08:19 -04:00
Ryan Dick
3d6f60f63e
Merge branch 'main' into ryan/flux-lora-quantized
2024-09-18 13:22:39 -04:00
Mary Hipp
00de20d102
fix(nodes): add flux generation types to choices
2024-09-17 15:44:20 +10:00
Ryan Dick
02f27c750a
Add unit tests for LoRAPatcher.apply_lora_sidecar_patches(...) and fixup dtype handling in the sidecar layers.
2024-09-15 04:39:56 +03:00
Ryan Dick
61d3d566de
Minor cleanup and documentation updates.
2024-09-15 04:39:56 +03:00
Ryan Dick
45bc8fcd7f
WIP - Implement sidecar LoRA layers using functional API.
2024-09-15 04:39:56 +03:00
Ryan Dick
f5f894437c
Bug fixes to get LoRA sidecar patching working for the first time.
2024-09-15 04:39:56 +03:00
Ryan Dick
fef26a5f2f
Consolidate all LoRA patching logic in the LoRAPatcher.
2024-09-15 04:39:56 +03:00
Ryan Dick
50c9410121
WIP
2024-09-15 04:39:56 +03:00
Ryan Dick
01a15b4d80
WIP - add invocations to support FLUX LORAs.
2024-09-15 04:39:56 +03:00
Ryan Dick
51df5aa94d
Invert the expected denoise_mask parameter to the FLUX Denoise node to match the behaviour of Denoise Latents node used for SD.
2024-09-14 00:42:31 +03:00
Ryan Dick
2b3e4e123d
Split LoRA layer implementations into separate files.
2024-09-12 15:53:30 +00:00
psychedelicious
4f2fc65257
tidy(nodes): MLSDEdgeDetection -> MLSDDetection
...
It's a line segment detector, not general edge detector.
2024-09-11 08:12:48 -04:00
psychedelicious
1d09091a67
feat(nodes): add Classification.Deprecated, deprecated old cnet processors
2024-09-11 08:12:48 -04:00
psychedelicious
ee4c0efbf7
feat(nodes): update pidinet node
...
Human-readable field names.
2024-09-11 08:12:48 -04:00
psychedelicious
a4250e3ff2
feat(nodes): update mlsd node
...
Human-readable field names.
2024-09-11 08:12:48 -04:00
psychedelicious
67a234c1bb
feat(nodes): update content shuffle node
...
- Better field names
2024-09-11 08:12:48 -04:00
psychedelicious
420045cb34
feat(nodes): update color map node
...
- Changed name
- Better field names
2024-09-11 08:12:48 -04:00
psychedelicious
53792fafb3
feat(nodes): add DWOpenposeDetectionInvocation
...
Similar to the existing node, but without any resizing. The backend logic was consolidated and modified so that it the model loading can be managed by the model manager.
The ONNX Runtime `InferenceSession` class was added to the `AnyModel` union to satisfy the type checker.
2024-09-11 08:12:48 -04:00
psychedelicious
615eddea6f
feat(nodes): add PiDiNetEdgeDetectionInvocation
...
Similar to the existing node, but without any resizing and with a revised model loading API that uses the model manager.
All code related to the invocation now lives in the Invoke repo.
2024-09-11 08:12:48 -04:00
psychedelicious
b3d60bd56a
feat(nodes): add NormalMapInvocation
...
Similar to the existing node, but without any resizing and with a revised model loading API that uses the model manager.
All code related to the invocation now lives in the Invoke repo. Unfortunately, this includes a whole git repo for EfficientNet. I believe we could use the package `timm` instead of this, but it's beyond me.
2024-09-11 08:12:48 -04:00
psychedelicious
fd42da5a36
feat(nodes): add MLSDEdgeDetectionInvocation
...
Similar to the existing node, but without any resizing and with a revised model loading API that uses the model manager.
All code related to the invocation now lives in the Invoke repo.
2024-09-11 08:12:48 -04:00
psychedelicious
bc55791db1
feat(nodes): add MediaPipeFaceDetectionInvocation
...
Similar to the existing node, but without any resizing and with a revised model loading API that uses the model manager.
All code related to the invocation now lives in the Invoke repo.
2024-09-11 08:12:48 -04:00
psychedelicious
c5f3297841
feat(nodes): add LineartEdgeDetectionInvocation
...
Similar to the existing node, but without any resizing and with a revised model loading API that uses the model manager.
2024-09-11 08:12:48 -04:00
psychedelicious
cd2c2a7fde
feat(nodes): add LineartAnimeEdgeDetectionInvocation
...
Similar to the existing node, but without any resizing and with a revised model loading API that uses the model manager.
2024-09-11 08:12:48 -04:00
psychedelicious
1cffcc02a5
feat(nodes): add HEDEdgeDetectionInvocation
...
Similar to the existing node, but without any resizing and with a revised model loading API that uses the model manager.
2024-09-11 08:12:48 -04:00
psychedelicious
ac9950bdbb
feat(nodes): add DepthAnythingDepthEstimationInvocation
...
Similar to the existing node, but without any resizing and with a revised model loading API.
2024-09-11 08:12:48 -04:00
psychedelicious
059d57f447
feat(nodes): add ContentShuffleInvocation
...
Similar to the existing node, but without the resolution fields.
2024-09-11 08:12:48 -04:00
