<span style="background-color:rgba(34, 139, 230, 0.15);color:rgb(254, 254, 254);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">☕KOFI <a target="_blank" rel="ugc" href="https://docs.google.com/forms/d/e/1FAIpQLScltzaQXTF2VFWRWVaqPSzJXYyNBF9hUQOLI8aBCyLrpCM1_w/viewform?usp=dialog">https://docs.google.com/forms/d/e/1FAIpQLScltzaQXTF2VFWRWVaqPSzJXYyNBF9hUQOLI8aBCyLrpCM1_w/viewform?usp=dialog</a><h2 id="wan-2.2-t2v-i2v-s2v-t2i4-6-stepsloop-svi-video-extend-wanvideowrapper-workflowk3nk">WAN 2.2 💠 T2V / I2V / S2V / T2I🔹4-6 steps🔹Loop 🔹SVI Video extend 🔹WanVideoWrapper Workflow🔹K3NK</h2><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/872b135f-025f-4391-9205-2a23d716f4a4/width=525/872b135f-025f-4391-9205-2a23d716f4a4.jpeg" />NOTICE: IF YOU ARE NEW TO COMFYUI, I DONT RECOMMEND STARTING WITH THIS WORKFLOW, IS AN ALL IN ONE WORKFLOW YOU WILL GET CONFUSED.I UPDATED v2.3, YOU CAN CHOOSE IF YOU WANT RES4LYF OR WVW SIGMA SPLITTING<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/327228a6-7a17-45c7-9f97-6ff690fd87fe/width=525/327228a6-7a17-45c7-9f97-6ff690fd87fe.jpeg" />Since v1.8 im using subgraphs, you need latest comfyui with the latest frontend updates, also probably you will need to update Comfyui Manager.For me was: setting nightly vers on the manager then update confy from the manager too.<hr />* i allways leave the image overlay enabled, it will error if you dont have an image on it, sorry :Sv2.0<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/7ece3913-14f3-44b7-9c3a-72e104cc430c/width=525/7ece3913-14f3-44b7-9c3a-72e104cc430c.jpeg" />You can choose whether to merge with the loras or not, change the lora connection from the model loader to the set loras node, after that uncheck merge_lorasThe toggled i added for radial sage, requieres Sage Attention to be installed, if you dont have it you should unplug the conexion i made to the attention type on the model loaders..Be sure to update WanVideoWrapper nodes .. <img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/872b135f-025f-4391-9205-2a23d716f4a4/width=525/872b135f-025f-4391-9205-2a23d716f4a4.jpeg" />The workflow works just fine with Wan2.1 if you bypass first sampler and model loaderThis workflow is included with all my uploads as metadata, drag and drop a vid to comfyui.I run a 4090 locally<hr /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/d7ddcc33-3809-4da9-9b5c-91e112825c83/width=525/d7ddcc33-3809-4da9-9b5c-91e112825c83.jpeg" />You can use it as other modes if you activate this option for enabling the required nodes.<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/58ae139e-b5cc-41e3-8e7a-f8a45c3a4344/width=525/58ae139e-b5cc-41e3-8e7a-f8a45c3a4344.jpeg" />Make sure you load the correct models on the model loaders <img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/adf0e1b4-a0d4-4b89-882f-66b0095ace16/width=525/adf0e1b4-a0d4-4b89-882f-66b0095ace16.jpeg" /> Kijai's WanVideoWrapper Node<ul><li><a target="_blank" rel="ugc" href="https://github.com/kijai/ComfyUI-WanVideoWrapper">https://github.com/kijai/ComfyUI-WanVideoWrapper</a></li></ul>Wan2.2 Kijai's models<ul><li><a target="_blank" rel="ugc" href="https://huggingface.co/Kijai/WanVideo_comfy_fp8_scaled/tree/main">https://huggingface.co/Kijai/WanVideo_comfy_fp8_scaled/tree/main</a></li><li><a target="_blank" rel="ugc" href="https://huggingface.co/Kijai/WanVideo_comfy/tree/main">https://huggingface.co/Kijai/WanVideo_comfy/tree/main</a></li></ul>Lightx2v LoRa needed for lower steps (faster generations)<ul><li><a target="_blank" rel="ugc" href="https://huggingface.co/Kijai/WanVideo_comfy/tree/main/Lightx2v">https://huggingface.co/Kijai/WanVideo_comfy/tree/main/Lightx2v</a></li></ul>Wan22-Lightning Lightx2v alternative, newer and better in some scenarios<ul><li><a target="_blank" rel="ugc" href="https://huggingface.co/lightx2v/Wan2.2-Lightning/tree/main/Wan2.2-I2V-A14B-4steps-lora-rank64-Seko-V1">https://huggingface.co/lightx2v/Wan2.2-Lightning/tree/main/Wan2.2-I2V-A14B-4steps-lora-rank64-Seko-V1</a></li><li><a target="_blank" rel="ugc" href="https://huggingface.co/lightx2v/Wan2.2-Lightning/tree/main/Wan2.2-T2V-A14B-4steps-lora-250928">https://huggingface.co/lightx2v/Wan2.2-Lightning/tree/main/Wan2.2-T2V-A14B-4steps-lora-250928</a></li></ul>NSFW Clip Vision (not really needed in wan2.2)<ul><li><a target="_blank" rel="ugc" href="https://huggingface.co/ricecake/wan21NSFWClipVisionH_v10/tree/main">https://huggingface.co/ricecake/wan21NSFWClipVisionH_v10/tree/main</a></li></ul>RES4LYF Nodes<ul><li><a target="_blank" rel="ugc" href="https://github.com/ClownsharkBatwing/RES4LYF">https://github.com/ClownsharkBatwing/RES4LYF</a></li></ul>MMAUDIO<ul><li><a target="_blank" rel="ugc" href="https://huggingface.co/Kijai/MMAudio_safetensors/tree/main">https://huggingface.co/Kijai/MMAudio_safetensors/tree/main</a> once installed replace <a target="_blank" rel="ugc" href="http://nodes.py">nodes.py</a> file in the mmaudio node folder with this one: <a target="_blank" rel="ugc" href="https://github.com/phazei/ComfyUI-MMAudio/blob/master/nodes.py">https://github.com/phazei/ComfyUI-MMAudio/blob/master/nodes.py</a></li></ul><h2 id="wan-2.2-t2v-i2v">WAN 2.2 💠 T2V / I2V</h2>MMAUDIO NSFW<ul><li><a target="_blank" rel="ugc" href="https://huggingface.co/phazei/NSFW_MMaudio">https://huggingface.co/phazei/NSFW_MMaudio</a> (download and rename it to "mmaudio_nsfw_large_44k_v2_fp16.safetensors")</li></ul>BOYONODES<ul><li><a target="_blank" rel="ugc" href="https://github.com/DragonDiffusionbyBoyo/Boyonodes">https://github.com/DragonDiffusionbyBoyo/Boyonodes</a></li></ul>K3NK IMAGE GRAB<ul><li><a target="_blank" rel="ugc" href="https://github.com/K3NK3/ComfyUI-K3NK-ComfyUI-Nodes">https://github.com/K3NK3/ComfyUI-K3NK-ComfyUI-Nodes</a></li></ul><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/d36ec0a0-0bcb-4bff-b063-a82cc4b8f60c/width=525/d36ec0a0-0bcb-4bff-b063-a82cc4b8f60c.jpeg" />

WAN 2.2  AIO💠 T2V / I2V / S2V / T2I / MMAudio 🔹4-6 steps🔹Loop 🔹SVI Video extend🔹WanVideoWrapper Workflow🔹K3NK

<ul><li>Fixed NAG and text_embeds, negative needs to go on the first field of the negative text_encoder</li><li>Added new section for continue video from last frame (I2V only) and video combiner</li><li>Added Florence for "prompt helper" , works good for describing the image and the setting</li><li>Added image overlay on the input image</li><li>Added back context nodes (is a bit tricky to make it work propperly)</li><li>Added a batch image loader for i2v</li></ul>

Files with SHA256: c3b84709862c2ab0677070c69b5a0e5f9589869c3203731ed2455041af738daf