Drop module-load pre-warming (Triton/fp8+LoRA needs real CUDA)

Revert to shipped scene-emb .pt; pre-warm pipeline blocks for ZeroGPU

Skip Gemma bootstrap at module-load; write placeholder .pt (ZeroGPU safe)

Switch to HDR IC-LoRA app with on-the-fly PromptEncoder + bundled ltx-2-internal

Update app.py

Update app.py

Model: Update spatial upscaler model to latest v1.1

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update README.md

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Update requirements.txt

Update requirements.txt

Update requirements.txt

Update app.py

Update app.py

Update app.py

Update requirements.txt

Update app.py

Update app.py

Update app.py

Update app.py

Update app.py

Create requirements.txt

Create app.py

initial commit