Views
No views yet
ltx2_refine_enabled=True (or the equivalent refine
flags). The base model repo can reference this LoRA via
fastvideo_refine_lora_path in model_index.json, so users do not need to pass
the LoRA path manually.ltx-2-19b-distilled-lora-384.safetensors — distilled LoRA weights for the
stage-2 refine denoising pass.fastvideo_refine_lora_path="FastVideo/LTX2-Distilled-LoRA" in its
model_index.json. Then enable refinement:1from fastvideo import VideoGenerator
2
3generator = VideoGenerator.from_pretrained(
4 "FastVideo/LTX2-Distilled-Diffusers",
5 ltx2_refine_enabled=True,
6)