Prompt assist: call a separate prompt-crafter ZeroGPU Space via gradio_client (instead of Inference Providers)

Add prompt assist: auto-describe reference sheet + suggest shot (Qwen2.5-VL via Inference Providers)

add aoti for speed up (#5)

Use black background for sheet padding (#4)

Fix sheet builder cropping subjects (contain instead of cover) (#3)

Update app.py

Switch backend to native LTX-2 (ICLoraPipeline) (#2)

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

add diffusers two-stage (x2 upsample + distilled refine); AOTI commented for validation

elaborate garden + horse example prompts to traveler-level detail

update traveler example: detailed reference-sheet + cinematic target prompt

revert to plain track_tqdm progress (Z-Image pattern), drop generator/callback

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)

image-tab + gallery-build tab; progress fix; speech examples

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 app.py with huggingface_hub

Upload app.py with huggingface_hub

Upload app.py with huggingface_hub

Upload app.py with huggingface_hub