LTX2.5-Studio / app.py

Commit History

3 days ago

  1. fix: the image preloads the prompt enhancer too: a third preload_from_hub entry, generated like the others, fetches the 8 files its loader reads at its pinned commit (2.49 GB), so a first enhanced call in a fresh container no longer risks paying the ~88 s Hub fetch inside its GPU reservation; the start-up prefetch stays as the fallback (#23)⁠

    Unverified signature
    72b989d
  2. fix: start-up refuses a fallback download the disk cannot hold, before writing a byte: the missing files, ZeroGPU's packed copy still to be written and a 10 GB margin must fit in the free space (on ZeroGPU, also under its 150 GB cap), or start-up stops with one message naming the directory, the count and GB, the free GB and the remedy (#23)⁠

    Unverified signature
    ff62c55
  3. fix: the diffusion decoder is built once at start-up, beside the pipeline, so ZeroGPU packs it and every run's worker uses that instance instead of loading it again; a start-up build that fails logs one line and leaves the per-run build as before (#17)⁠

    Unverified signature
    ed13532
  4. fix: the Space's weights come from the image: preload_from_hub is live for exactly the 35 files the int8 Space loads (71.92 GB; the temporal upsampler, which nothing loads, is no longer fetched), every file carries its size in model_files, and start-up downloads only what the image lacks, saying how much (#23)⁠

    Unverified signature
    41dcf05
  5. fix: bitsandbytes' int8 cast warning reaches the log once per process instead of once per matrix product, so the Space's log keeps its start-up report and its real warnings (#15)⁠

    Unverified signature
    18bcc7a

4 days ago

  1. fix: an output folder outside the working directory and the temp dir is passed to launch as allowed_paths, so Gradio serves the results written there⁠

    Unverified signature
    e7cde1a
  2. feat: one device resolver — CUDA on ZeroGPU, MPS/CPU by opt-in, and no silent 70 GB load anywhere else⁠

    Unverified signature
    0ed2aa1

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

    Unverified signature
    f967e30

  1. fix: bound uploads at launch — max_file_size from the LoRA ceiling, the one lever both sides read⁠

    Unverified signature
    db233ed

  1. fix: gate GPU work on capability, not on being a Space⁠

    Unverified signature
    bd190ee
  2. fix: download weights at runtime; a private Space cannot preload⁠

    Unverified signature
    f355817
  3. fix: thread one frame rate to both the pipeline and the container⁠

    Unverified signature
    3f5d8f4
  4. fix: actually wire ZeroGPU into the running app⁠

    Unverified signature
    efdddfc
  5. fix: wire output retention; expose latent_to_pixel_index⁠

    Unverified signature
    4b80aee
  6. feat: implement pipelines and wire app.py — suite green⁠

    Unverified signature
    55dc097
  7. chore: scaffold package, tooling config, and module stubs⁠

    Unverified signature
    ca5c091