<h3 id="wan-2.2-svi-pro-2-i2v-for-12gb-vram">WAN 2.2 / SVI Pro 2 / I2V for 12GB VRAM</h3>v1.2 - Please update to this version.Seed per Sample - fixed.<ol><li>Seed arrangement were out of order. (I'm not sure how this slipped through.)</li><li>Added labels on seed per sample.</li><li>Tested each seed on each clip and changed seed to make sure its working correctly.</li></ol>Added a preview image after Resize Image so you can check and compare your image to the original.For 832x1216 Images use 576x832 resolution if you're using the crop option on resize.Modified version of <a target="_blank" rel="ugc" href="https://civarchive.com/models/2280989/svi-pro-20-for-low-vram-8gb">[SVI Pro 2.0 for Low VRAM (8GB)]</a>And <a target="_blank" rel="ugc" href="https://github.com/user-attachments/files/24359648/wan22_SVI_Pro_native_example_KJ.json">[Wan2.2 SVI Pro Example KJ]</a><ul><li>7 Stage Sample Setup, with each Stage having their own Loras, combined with Sage Attention Cuda for faster speeds.</li><li>Can save each stage clip if needed.</li><li>Final Output w/ Upscaler + RIFE for smooth 60FPS.</li><li>Fast Group Bypasser - for quick access.</li></ul>### Required Models &amp; LoRAsGGUF Main Models:* <a target="_blank" rel="ugc" href="https://civarchive.com/models/2190659/dasiwa-wan-22-i2v-14b-tastysin-v8-or-lightspeed-or-gguf">[DaSiWa-Wan 2.2 I2V]</a> or* <a target="_blank" rel="ugc" href="https://civarchive.com/models/1995784?modelVersionId=2323420">[Smooth Mix Version]</a> or* <a target="_blank" rel="ugc" href="https://civarchive.com/models/2053259?modelVersionId=2540892">[Enhanced NSFW Camera Prompt Adherence]</a>&gt; Note: Use a suitable quantization (e.g., Q4 or Q5) based on your available VRAM. I highly recommend DaSiWa-Wan high/low Models, as the Lightning Loras are BAKED in, leaving you only with SVI Loras being required.SVI PRO LoRAs (Wan2.2-I2V-A14B):* Both Required<a target="_blank" rel="ugc" href="https://huggingface.co/Kijai/WanVideo_comfy/blob/main/LoRAs/Stable-Video-Infinity/v2.0/SVI_v2_PRO_Wan2.2-I2V-A14B_HIGH_lora_rank_128_fp16.safetensors">[SVI PRO - HIGH (Rank 128)]</a><a target="_blank" rel="ugc" href="https://huggingface.co/Kijai/WanVideo_comfy/blob/main/LoRAs/Stable-Video-Infinity/v2.0/SVI_v2_PRO_Wan2.2-I2V-A14B_LOW_lora_rank_128_fp16.safetensors">[SVI PRO - LOW (Rank 128)]</a>Text Encoders:<a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/Wan_2.2_ComfyUI_Repackaged/blob/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors">[WAN UMT5]</a> or<a target="_blank" rel="ugc" href="https://huggingface.co/NSFW-API/NSFW-Wan-UMT5-XXL/blob/main/nsfw_wan_umt5-xxl_fp8_scaled.safetensors">[NSFW WAN UMT5]</a>VAE:<a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/blob/main/split_files/vae/wan_2.1_vae.safetensors">[Wan 2.1 VAE]</a><h3 id="the-following-is-for-speed-boosts-for-nvidia-cards-if-its-already-working-then-skip-this!">The following is for Speed Boosts for nVidia Cards - If its already working then skip this!</h3>Patch Sage Attention Node (sageattn_qk_int8_pv_fp16_cuda) + Model Patch Torch Settings Node (Faster Speed Times):Prompt executed in 136.56 seconds &lt;- Sage Attention Disable/FP16 Accumulation = Disable/Allow Compile = FalsePrompt executed in 104.38 seconds &lt;- Sage Attention Enabled/FP16 Accumulation = Enabled/Allow Compile = FalsePrompt executed in 96.26 seconds &lt;-- Sage Attention Enabled/FP16 Accumulation = True/Allow Compile = TrueWith this setup you can save a massive 40+ seconds just for one Stage!If Sage Attention is not working/crashing comfyui then do the following or use (CTRL+B to bypass the nodes but I highly recommend getting it working for massive speed boost):<ul><li>The following is for Comfyui_windows_portable, do not do it this way if you are using a different setup!<ul><li>Step 1 — Check your PyTorch + CUDA version</li></ul></li></ul>Open CMD in your ComfyUI Portable folder (SAME directory as run_nvidia_gpu.bat) and run the following command:.\python_embeded\python.exe -c "import torch; print(torch.__version__, torch.version.cuda)"output = 2.9.1+cu130 13.0check Python embeded version:.\python_embeded\python.exe -Voutput = Python 3.13.9Which Means:Python: 3.13 (embeded)PyTorch: 2.9.1CUDA: 13.0Warning! If you are unsure how to proceed with the following steps, then paste your error code into Grok/ChatGPTfor a more detailed analysis.Pick the wheel that matches your Python + PyTorch + CUDA output from Step 1.That means the correct SageAttention wheel for your setup would be something like this:sageattention-2.2.0.post3+cu130torch2.9.0-cp313-cp313-win_amd64.whldownload the correct wheel for your setup from:<a target="_blank" rel="ugc" href="https://huggingface.co/Wildminder/AI-windows-whl/tree/main/">[List of Wheels]</a>It matches Python 3.13 (cp313-cp313), PyTorch 2.9.x, and CUDA 13.0.The slight difference in patch version (2.9.1 vs 2.9.0) is fine — this wheel works with PyTorch 2.9.x.<ul><li>Step 2 — Install Wheel (make sure the file is in \ComfyUI_windows_portable, same directory as run_nvidia_gpu.bat)</li></ul>Open CMD in your ComfyUI Portable folder and run with the correct wheel file (example below):.\python_embeded\python.exe -m pip install "sageattention-2.2.0.post3+cu130torch2.9.0-cp313-cp313-win_amd64.whl"<ul><li>Step 3 — How to check if it works:</li></ul>Open CMD in your ComfyUI Portable folder and run:.\python_embeded\python.exe -c "import sageattention; print('SageAttention import successful!'); print(dir(sageattention))"You should see:SageAttention import successful!['__builtins__', '__cached__', '__doc__', '__file__', '__loader__', '__name__', '__package__', '__path__', '__spec__', '_fused', '_qattn_sm80', '_qattn_sm89', '_qattn_sm90', 'core', 'quant', 'sageattn', 'sageattn_qk_int8_pv_fp16_cuda', 'sageattn_qk_int8_pv_fp16_triton', 'sageattn_qk_int8_pv_fp8_cuda', 'sageattn_qk_int8_pv_fp8_cuda_sm90', 'sageattn_varlen', 'triton']<ul><li>Step 4 — confirm if triton attention mode is available:</li></ul>Open CMD in your ComfyUI Portable folder and run:.\python_embeded\python.exe -c "import sageattention; print('SageAttention import successful!'); print('Triton mode available:' , hasattr(sageattention, 'sageattn_qk_int8_pv_fp16_triton'))"You should see:SageAttention import successful!Triton mode available: Trueif any triton errors run this command:.\python_embeded\python.exe -m pip install tritonStep 5 - now you should be able to use "sageattn_qk_int8_pv_fp16_cuda" with Patch Sage Attention + Model patch Torch Settings Nodes properly.

Files with SHA256: 25fc69aac8bda78e4b077a8b7f5c9d479e08873b33f04bdaa9e4e7ff096b7904