2 stage workflow
Your github nodes mention several steps to do the two stages sampling but those aren't trivial. Please provide another workflow with your examples.
Your github nodes mention several steps to do the two stages sampling but those aren't trivial. Please provide another workflow with your examples.
The included sample workflow is already a complete two-stage workflow. The “Two-stage latent upscaling” section in the README is only explaining the internal sampling flow, not additional steps that need to be built manually. You can directly use LTX2.5-MSR-sample-workflow.json as the two-stage example.
please make this for wan2gp
I tried to disable the second stage, this gave better resolution, as I was able to up the resolution of the first stage, but audio was not generated. how to get audio with 1-step