LTX2.5-Studio / tests /test_modes.py

Commit History

4 days ago

  1. feat: video to video is a variation of the user's clip, noised to a level and denoised along the schedule's tail⁠

    Unverified signature
    85405e9
  2. fix: audio conditioning has its own noise level and schedule, so audio_to_video and audio_to_audio sample the video like every other mode⁠

    Unverified signature
    be9c1db
  3. fix: a run consumes only what its mode declares, and is validated before a GPU is reserved⁠

    Unverified signature
    6e07c8e

  1. fix: `audio_to_video` hands back YOUR audio — the model's track is silence when audio is supplied⁠

    Unverified signature
    e2f538a

  1. fix: audio-conditioned video came back silent — mode 11 now muxes the model's own track⁠

    Unverified signature
    4683a57

  1. docs: keep the record that the condition ceiling never binds⁠

    Unverified signature
    7d6980a
  2. Revert "fix: per-mode video condition strength; video_to_audio at 0.5"⁠

    Unverified signature
    18d387a
  3. fix: per-mode video condition strength; video_to_audio at 0.5⁠

    Unverified signature
    0734d2e
  4. test: spec output retention; align mode workflows with the upstream map⁠

    2941f37
  5. test: spec the mode registry, the never-empty-output invariant, app build and layering⁠

    1e0df90