Here is the ComfyUI workflow pictured:<a target="_blank" rel="ugc" href="https://civarchive.com/models/1112672/fasthunyuanvideo6step">https://civarchive.com/models/1112672/fasthunyuanvideo6step</a>Posting two derivative HunyuanVideo models here for convenience for others. I originally found them here:<a target="_blank" rel="ugc" href="https://huggingface.co/Kijai/HunyuanVideo_comfy/tree/main">https://huggingface.co/Kijai/HunyuanVideo_comfy/tree/main</a>You can find the VAE there as well ^^^Files Section has two files ---&gt;<ol><li>Full model is the Regular HunyuanVideo FP8 model (CFG6, Flow 9).</li><li>Pruned model is the FastHunyuanVideo FP8 model (CFG 9, Flow 17).</li></ol>N.B. I realize that they are the exact same size, but they are in fact different files for different purposes.FastHunyuanVideo also has a LORA.LORA: <a target="_blank" rel="ugc" href="https://huggingface.co/Kijai/HunyuanVideo_comfy/blob/main/hyvideo_FastVideo_LoRA-fp8.safetensors">https://huggingface.co/Kijai/HunyuanVideo_comfy/blob/main/hyvideo_FastVideo_LoRA-fp8.safetensors</a>

Files with SHA256: af5dd30921d124b1e666827caec0e1fbe803fdd2128d31d75e9a6eba82564a68