Here is my workflow for HunyuanVideo - using the hunyuanvideo-wrapper.The example prompt in the workflow is nsfw.Upscaler model download: <a target="_blank" rel="ugc" href="https://github.com/Phhofm/models/releases/download/1xDeJPG_realplksr_otf/1xDeJPG_realplksr_otf.safetensors">https://github.com/Phhofm/models/releases/download/1xDeJPG_realplksr_otf/1xDeJPG_realplksr_otf.safetensors</a>ComfyUI_windows_portable\ComfyUI\models\upscale_modelsHunyuanVideoWrapper download links:Transformer and VAE (single files, no autodownload):<a target="_blank" rel="ugc" href="https://huggingface.co/Kijai/HunyuanVideo_comfy/tree/main">https://huggingface.co/Kijai/HunyuanVideo_comfy/tree/main</a>Go to the usual ComfyUI folders (diffusion_models and vae)LLM text encoder (has autodownload):<a target="_blank" rel="ugc" href="https://huggingface.co/Kijai/llava-llama-3-8b-text-encoder-tokenizer">https://huggingface.co/Kijai/llava-llama-3-8b-text-encoder-tokenizer</a>Files go to <code>ComfyUI/models/LLM/llava-llama-3-8b-text-encoder-tokenizer</code>Clip text encoder (has autodownload)Either use any Clip_L model supported by ComfyUI by disabling the clip_model in the text encoder loader and plugging in ClipLoader to the text encoder node, or allow the autodownloader to fetch the original clip model from:<a target="_blank" rel="ugc" href="https://huggingface.co/openai/clip-vit-large-patch14">https://huggingface.co/openai/clip-vit-large-patch14</a>, (only need the .safetensor from the weights, and all the config files) to:<code>ComfyUI/models/clip/clip-vit-large-patch14</code>

Files with SHA256: fc8cff006f2ed9537da304ccd7925eadb8a94b6a724e6de944f224b4c3b8f3ed