De-diffuser README (native backend; backlinks -> Lightricks/LTX-2.3)

Revert README (keep name + card unchanged)

Switch backend to native LTX-2 (ICLoraPipeline)

metadata: point models: to the official Lightricks LoRA repo (fix model-card backlink)

seed: write the used seed back into the Seed slider (drop separate 'Seed used' field)

point LoRA to official Lightricks LTX-2.3 Creative Lab repos

trim GPU duration estimate to ~2.3x measured runtime (quota efficiency)

raise default resolution/frames to training bucket (quality fix)

revert to plain track_tqdm progress (Z-Image pattern), drop generator/gr.skip

fix progress flicker: yield gr.skip() during progress (no output re-render)

randomize seed by default; move 'Seed used' into advanced settings

merge: keep AOTI speedup + native progress-bar generator

native progress bar via generator (forwards on ZeroGPU)

Use precompiled AOTI transformer blocks (ZeroGPU speedup) (#1)

concise description: base model + LoRA links, via diffusers

ingredients rename + multi-image sheet builder + real example sheets/clips

audio folded into single prompt; inpaint example None->placeholder mask

fixes: natural-speed/aspect, audio, progress, prompts, examples

Upload examples/slicing_veggie_gray.mp4 with huggingface_hub

Upload examples/surfing_gray.mp4 with huggingface_hub

Upload examples/cat_on_a_tree_gray.mp4 with huggingface_hub

Upload app.py with huggingface_hub

Upload app.py with huggingface_hub

Upload app.py with huggingface_hub

Upload README.md with huggingface_hub

Upload requirements.txt with huggingface_hub

Upload app.py with huggingface_hub

initial commit