CalamitousFelicitousness 9c11929780 fix(ltx): place the 0.9 latent upsampler on the compute device ...

Its 2.x sibling always did, so only the 0.9 path hit a cpu weight against cuda
latents. Also logs why a run is refused, which until now travelled only in the
raised error.

2026-08-19 01:45:46 +01:00

..

__init__.py

linting

2026-07-03 22:05:33 +02:00

ltx_capabilities.py

feat(ltx): add the ltx-2.5 model family

2026-08-14 03:39:01 +01:00

ltx_diffusers_patch.py

fix(ltx): apply the 2.5 stage-2 lora to the text connectors

2026-08-14 03:39:01 +01:00

ltx_process.py

fix(ltx): place the 0.9 latent upsampler on the compute device

2026-08-19 01:45:46 +01:00

ltx_ui.py

fix(video): resolve dropdown model selection through the registry

2026-08-18 00:46:16 +01:00

ltx_util.py

fix(ltx): place the 0.9 latent upsampler on the compute device

2026-08-19 01:45:46 +01:00