christian-byrne 76cc69a2af Split the alpha off by image layout, not by model channel count ...

Keying the split off upscale_model.input_channels was wrong for any model
that does not take 3 channels: a single channel model fed a plain RGB image
took only the red channel and returned 1 - green as the alpha mask, where it
used to fail loudly. Alpha is channel 3 of an RGBA image, nothing else.

2026-08-10 13:56:57 -07:00

..

__init__.py

[feat] Add ImageStitch node for concatenating images (#8369)

2025-06-01 04:28:52 -04:00

compositor_blend_fixture_gen.py

[Partner Nodes] feat: ImageCompositor node with layer-state compositing, layer from bbox and Seedream Layer Separation node (#15317)

2026-08-07 13:25:37 -07:00

compositor_blend_golden.json

[Partner Nodes] feat: ImageCompositor node with layer-state compositing, layer from bbox and Seedream Layer Separation node (#15317)

2026-08-07 13:25:37 -07:00

compositor_blend_test.py

[Partner Nodes] feat: ImageCompositor node with layer-state compositing, layer from bbox and Seedream Layer Separation node (#15317)

2026-08-07 13:25:37 -07:00

compositor_node_test.py

[Partner Nodes] feat: ImageCompositor node with layer-state compositing, layer from bbox and Seedream Layer Separation node (#15317)

2026-08-07 13:25:37 -07:00

image_stitch_test.py

[V3] converted nodes_images.py to V3 schema (#11206)

2025-12-26 19:39:02 -08:00

nodes_math_test.py

Fix uncaught OverflowError in Math Expression node for large int results (#14214)

2026-06-01 18:15:04 -07:00

nodes_number_convert_test.py

fix(number-convert): preserve int precision for large numbers (#13147)

2026-03-25 18:06:34 -04:00

test_seedvr2_conditioning.py

Add SeedVR2 support (CORE-6) (#14424)

2026-07-10 15:07:42 +08:00

test_seedvr2_nodes.py

Add SeedVR2 support (CORE-6) (#14424)

2026-07-10 15:07:42 +08:00

test_seedvr2_post_processing.py

Add SeedVR2 support (CORE-6) (#14424)

2026-07-10 15:07:42 +08:00

test_seedvr2_temporal_chunk.py

Add SeedVR2 support (CORE-6) (#14424)

2026-07-10 15:07:42 +08:00

upscale_model_alpha_test.py

Split the alpha off by image layout, not by model channel count

2026-08-10 13:56:57 -07:00