LTX2.5-Studio / docs /PLAN.md

Commit History

3 days ago

  1. docs: every sentence stays true after the deploy: README and the release notes say this is deploy 2's code and point to issue #32 for what the Space shows, and no doc says the Space still runs deploy 1, is not deployed, or has not been redeployed since August (#32)⁠

    Unverified signature
    abc9150
  2. docs: the diffusion decoder is built once at start-up, beside the pipeline, and packed with it on the Space, with each run building its own only if that build failed: the README's decoder paragraph and two PLAN passages say so (#17)

    Unverified signature
    d8bbbdb
  3. docs: the weights come from the image: the README, PLAN and the handoff say preload_from_hub fetches the 35 model files (71.92 GB, no temporal upsampler) and the prompt enhancer's 8 (2.49 GB) before the app starts, and start-up downloads only what is missing, if the disk can hold it (#23)⁠

    Unverified signature
    38e36e9
  4. docs: the reservation follows size and length: the README's table is the estimator's (the default run 60 s, needing 120 s of quota), the measured envelope is a stated limit, and SPACE_MODE_MATRIX §10.3 records the six size-and-length runs and the answer to the operator's question (#21)⁠

    Unverified signature
    ca1f2a8

4 days ago

  1. docs: the output folder is described: one outside the working directory and the temp dir is passed to Gradio as the one allowed path, and a result the page cannot show ends with a card, never on "Generating…"⁠

    Unverified signature
    c3c8672
  2. docs: the local memory check is described as it now works: it waits for memory just freed to leave the gauge, reads a failing check again before it refuses, and its refusal is a kind of its own⁠

    Unverified signature
    68c528c
  3. docs: the local matrix records the final pass: every mode, the adapter, the enhancer and the model-chosen length run again on the final code, identical wherever compared with a run made after the RoPE fix⁠

    Unverified signature
    0300944
  4. docs: running locally is described as one code path with the Space: the same stage graph, with the local runner supplying only what is resident when⁠

    Unverified signature
    1f05c04
  5. docs: the audio modes are described as measured after the audio-encoding fix, and the API's noise_scale default is said to snap to "a little"⁠

    Unverified signature
    67c1514
  6. docs: video to video is described as verified on real weights: a variation of the clip at three levels, with the prompt acting at the highest⁠

    Unverified signature
    41d0e94
  7. docs: PLAN says the enhancer prefetch failure was seen in one boot log, with a cause that applies to every boot⁠

    Unverified signature
    c09685b
  8. docs: PLAN states the exact pins, the local Apple-silicon path, and corrects what the code and the measurements overtook⁠

    Unverified signature
    f92f481

  1. docs: the app ran its whole life on half a GPU — `auto` cannot promote, and four documents said otherwise⁠

    Unverified signature
    caf1083
  2. fix: the enhancer's nine-minute wall — the rewrite moves onto the GPU it was priced for⁠

    Unverified signature
    f967e30
  3. feat: prompt enhancement ships — a real toggle, in the web process, at zero GPU cost⁠

    Unverified signature
    2f36d8a

  1. docs: every Space generation result was garbage — the invalidation, stated at the top⁠

    Unverified signature
    898dad2
  2. docs: the audit's stale claims annotated — measurements stand, corrections dated on top⁠

    Unverified signature
    fd85c87

  1. docs: the ladder gains a rung, added by a failed deploy⁠

    Unverified signature
    2eca23e

  1. docs: two rules from the day's last two errors⁠

    Unverified signature
    3d4ff9c
  2. docs: what H17 does not cover, and the four-attribute hand-off⁠

    Unverified signature
    de2596c
  3. docs: re-attribute H9, record the intervention, and rule 9⁠

    Unverified signature
    5d73ea4
  4. docs: four rules the hardware taught, and the ladder's last rung⁠

    Unverified signature
    a7367c9
  5. docs: we can prove a function ran, not that it ran with the right arguments⁠

    Unverified signature
    1f07845
  6. docs: the refetch fits the timing the packing peak does not⁠

    Unverified signature
    77286f0
  7. docs: two rules whose shape does not depend on the author being right⁠

    Unverified signature
    c5ba0bb
  8. feat: mechanical stream-layout verification; record two prose rules⁠

    Unverified signature
    609c2a3
  9. docs: add the ZeroGPU disk decision document; correct a false reason⁠

    Unverified signature
    0e1b747
  10. feat: fail loudly if the tensors stop being mmap-backed⁠

    Unverified signature
    6fd68ea
  11. docs: reconcile the disk arithmetic; the peak precedes the prune⁠

    Unverified signature
    29e399d
  12. docs: the dtype is load-bearing for ZeroGPU's snapshot cleanup⁠

    Unverified signature
    92aea11
  13. docs: split the test plan by the question each host can answer⁠

    Unverified signature
    66ca545
  14. docs: the single-load fix is necessary, not sufficient⁠

    Unverified signature
    f51840e
  15. fix: load the model once; derive the second workflow from it⁠

    Unverified signature
    43f432f
  16. fix: no advertised lever may be attached to nothing⁠

    Unverified signature
    9829d39
  17. fix: download weights at runtime; a private Space cannot preload⁠

    Unverified signature
    f355817
  18. docs: warn the next reader not to trust the gate the way we did⁠

    Unverified signature
    86ce43f
  19. docs: name the common cause behind the five blockers⁠

    Unverified signature
    d99f134
  20. docs: record what this build actually taught⁠

    Unverified signature
    118d513
  21. docs: batched corrections pass⁠

    Unverified signature
    3f740e9
  22. feat: preflight cache-completeness check; retract HF_HOME advice⁠

    Unverified signature
    b17d455
  23. feat: env-driven config; 9-stage LoRA validator design⁠

    Unverified signature
    5516933
  24. feat: implement errors, constraints and model_files⁠

    Unverified signature
    706048e
  25. docs: fold in gated-repo evidence; add GPU test plan⁠

    Unverified signature
    ca6e2de
  26. docs: fold in ZeroGPU recon; add pinned requirements⁠

    Unverified signature
    bfaee84
  27. docs: add LTX-2.5 Studio design plan⁠

    Unverified signature
    1324740