<h2 id="wan-2.2-t2v-unet-(low-vram-fp8-clean-versions).">🌀 Wan 2.2 T2V UNet (Low VRAM FP8 CLEAN Versions). </h2>I’ve .repackaged the official Wan 2.2 T2V UNet checkpoints into low VRAM FP8 versions, so they’re easier to run on smaller GPUs while still working with ComfyUI video workflows.Note: Clean versions do not contains any lora(s)<h3 id="available-variants">✅ Available Variants</h3><ul><li>Wan2.2_T2V_High_Noise_14B_Fp8-LowVRAM</li><li>Wan2.2_T2V_Low_Noise_14B_Fp8-LowVRAM</li></ul><h3 id="original-models-(credit-goes-here-not-me)">🔗 Original Models (credit goes here, not me)</h3>These are directly converted from the official checkpoints released by Comfy-Org. I did not train or create these models — I only adapted them for lower VRAM use.<ul><li><a target="_new" rel="ugc" href="https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/blob/main/split_files/diffusion_models/wan2.2_t2v_high_noise_14B_fp16.safetensors">High Noise FP16 (original on HuggingFace)</a></li><li><a target="_new" rel="ugc" href="https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/blob/main/split_files/diffusion_models/wan2.2_t2v_low_noise_14B_fp16.safetensors">Low Noise FP16 (original on HuggingFace)</a></li></ul><h3 id="notes">📌 Notes</h3><ul><li>Works with WAN 2.2 ComfyUI pipelines.</li><li>FP8 format helps with VRAM efficiency, useful if you’re on GPUs &lt;8GB VRAM or higher.</li><li>Quality is close to FP16, but some precision differences may occur.</li><li>These are UNet-only checkpoints (not full model packages).</li></ul><h3 id="disclaimer">⚠️ Disclaimer</h3>I am not the creator of Wan 2.2 or these checkpoints. Full credit belongs to Comfy-Org and the original developers. This upload only provides low VRAM-converted versions of the original UNets.

Files with SHA256: 43688ef7441adad6f45b55fb2a72da42dfdc2f0bd7046824b447f793ab129d8b