推理效果

您好，我在Wan2.1-T2V-1.3B-480P模型上运行以下推理生成的视频和您提供在github中的视频效果有些差距，请问一下是我哪里需要修改吗
python turbodiffusion/inference/wan2.1_t2v_infer.py
--model Wan2.1-1.3B
--dit_path checkpoints/TurboWan2.1-T2V-1.3B-480P-quant.pth
--resolution 480p
--prompt "A stylish woman walks down a Tokyo street filled with warm glowing neon and animated city signage. She wears a black leather jacket, a long red dress, and black boots, and carries a black purse. She wears sunglasses and red lipstick. She walks confidently and casually. The street is damp and reflective, creating a mirror effect of the colorful lights. Many pedestrians walk about."
--num_samples 1
--num_steps 4
--quant_linear
--attention_type sagesla
--sla_topk 0.1

还有一个问题就是我看您并没有提供使用origin注意力所使用的模型权重，我使用wan2.1的原始模型权重生成的视频噪声很大，请问这个是需要使用您训练的权重吗

Start with turbodiffusion/inference/wan2.1_t2v_infer.py and reproduce the reported command using the listed Wan2.1 and TurboWan checkpoints. Compare the generated result with the repository’s reference video, then determine which model weights and attention settings are required for equivalent output. Done means the required configuration or reproducible discrepancy is documented.