Expose guide-adherence (condition strength) slider; defaults 0.7/1.0 for actual head swap (pipeline.py)

Fix ZeroGPU lifecycle + V2V guide-video conditioning (pipeline.py)

Fix: load full pipeline from distilled repo to fix VAE/scheduler version mismatch

Diagnostic: set BFS LoRA weight=0 to isolate base pipeline vs LoRA corruption

Fix scrambled output: switch output_type pt→np (no tensor permute guessing)

Switch to LTX-Video-0.9.8-13B-distilled + ltx-2 BFS LoRA; fix 22B architecture mismatch

Switch base model to SulphurAI/Sulphur-2-base (fp8mixed transformer + Sulphur distill LoRA)

Upload folder using huggingface_hub