"""Preprocess 122 isometric Grok videos for SCD training. Encodes MP4+TXT pairs into precomputed latents + text embeddings for SCD LoRA training. Uses combined prompts (_combined.txt from ...
from sglang.multimodal_gen.configs.pipeline_configs.qwen_image import ( from sglang.multimodal_gen.runtime.models.registry import ModelRegistry from sglang.multimodal ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results