<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/00626427-348e-4156-89c1-0ca68364152c/width=525/00626427-348e-4156-89c1-0ca68364152c.jpeg" /><a target="_blank" rel="ugc" href="https://civarchive.com/articles/13555"><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/42be6750-3055-49d6-9b35-b92ea7e90442/width=525/42be6750-3055-49d6-9b35-b92ea7e90442.jpeg" /></a><a target="_blank" rel="ugc" href="https://civarchive.com/models/1309415"><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/281c1151-1930-4c9b-a838-181b8ebb0e75/width=525/281c1151-1930-4c9b-a838-181b8ebb0e75.jpeg" /></a><a target="_blank" rel="ugc" href="https://civarchive.com/collections/9057652"><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/a9f7a3e8-c254-4f13-b697-c1ec728bf787/width=525/a9f7a3e8-c254-4f13-b697-c1ec728bf787.jpeg" /></a><h1 id="workflow-description-:-qme6cjn2r">Workflow description :</h1>The aim of this workflow is to generate video using the face from an existing photo in a simple window.<h1 id="resources-you-need:-3qxzvaxn0">Resources you need:</h1><h2 id="files-:-y9al08ucc">📂Files :</h2><h3 id="wan2.1-4dcazedq8">WAN2.1</h3>Recommendation : 24 gb Vram: Q8_0 16 gb Vram: Q5_K_S &lt;12 gb Vram: Q4_K_SI2V Quant Model: <a target="_blank" rel="ugc" href="https://huggingface.co/city96/Wan2.1-I2V-14B-480P-gguf/tree/main">Wan2.1-I2V-14B-480P-gguf </a>or <a target="_blank" rel="ugc" href="https://huggingface.co/city96/Wan2.1-I2V-14B-720P-gguf/tree/main">Wan2.1-I2V-14B-720P-gguf</a> In models/diffusion_modelsCLIP: <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/blob/main/split_files/text_encoders/umt5_xxl_fp8_e4m3fn_scaled.safetensors">umt5_xxl_fp8_e4m3fn_scaled.safetensors</a> in models/clipCLIP-VISION: <a target="_blank" rel="ugc" href="https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/blob/main/split_files/clip_vision/clip_vision_h.safetensors">clip_vision_h.safetensors</a> in models/clip_visionVAE: <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.safetensors</a> in models/vae<h3 id="flux-zqn9cavxk">FLUX</h3>GGUF_Model: <a target="_blank" rel="ugc" href="https://huggingface.co/city96/FLUX.1-dev-gguf/tree/main">FLUX.1-dev-gguf</a> "flux1-dev-Q8_0.gguf" in ComfyUI\models\unetGGUF_clip: <a target="_blank" rel="ugc" href="https://huggingface.co/city96/t5-v1_1-xxl-encoder-gguf/tree/main">t5-v1_1-xxl-encoder-gguf</a> "t5-v1_1-xxl-encoder-Q8_0.gguf" in \ComfyUI\models\clipText encoder: <a target="_blank" rel="ugc" href="https://huggingface.co/zer0int/CLIP-GmP-ViT-L-14/blob/main/ViT-L-14-TEXT-detail-improved-hiT-GmP-TE-only-HF.safetensors">ViT-L-14-TEXT-detail-improved-hiT-GmP-TE-only-HF.safetensors</a> "ViT-L-14-GmP-ft-TE-only-HF-format.safetensors" in \ComfyUI\models\clipVAE: <a target="_blank" rel="ugc" href="https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/ae.safetensors">ae.safetensors</a> "ae" in \ComfyUI\models\vaeFLUX PuLID : <a target="_blank" rel="ugc" href="https://huggingface.co/camenduru/PuLID/blob/main/pulid_flux_v0.9.0.safetensors">pulid_flux_v0.9.0.safetensors</a> "pulid_flux_v0.9.0" in \ComfyUI\models\pulidANY upscale model (depreciated):<ul><li>Realistic : <a target="_blank" rel="ugc" href="https://huggingface.co/spaces/Marne/Real-ESRGAN/blob/main/RealESRGAN_x4plus.pth">RealESRGAN_x4plus.pth</a></li><li>Anime : <a target="_blank" rel="ugc" href="https://huggingface.co/spaces/Marne/Real-ESRGAN/blob/main/RealESRGAN_x4plus_anime_6B.pth">RealESRGAN_x4plus_anime_6B.pth</a></li></ul>in models/upscale_models<h2 id="custom-nodes-:-8yno7m8po">📦Custom Nodes :</h2><ul><li><a target="_blank" rel="ugc" href="https://github.com/pythongosssss/ComfyUI-Custom-Scripts">ComfyUI-Custom-Scripts</a></li><li><a target="_blank" rel="ugc" href="https://github.com/city96/ComfyUI-GGUF">ComfyUI-GGUF</a></li><li><a target="_blank" rel="ugc" href="https://github.com/kijai/ComfyUI-KJNodes">ComfyUI-KJNodes</a></li><li><a target="_blank" rel="ugc" href="https://github.com/Kosinkadink/ComfyUI-VideoHelperSuite">ComfyUI-VideoHelperSuite</a></li><li><a target="_blank" rel="ugc" href="https://github.com/Smirnov75/ComfyUI-mxToolkit">ComfyUI-mxToolkit</a></li><li><a target="_blank" rel="ugc" href="https://github.com/facok/ComfyUI-HunyuanVideoMultiLora">ComfyUI-HunyuanVideoMultiLora</a></li><li><a target="_blank" rel="ugc" href="https://github.com/rgthree/rgthree-comfy">rgthree-comfy</a></li><li><a target="_blank" rel="ugc" href="https://github.com/Fannovel16/ComfyUI-Frame-Interpolation">ComfyUI-Frame-Interpolation</a></li><li><a target="_blank" rel="ugc" href="https://github.com/WASasquatch/was-node-suite-comfyui">WAS Node Suite</a></li><li><a target="_blank" rel="ugc" href="https://github.com/kijai/ComfyUI-Florence2">ComfyUI-Florence2</a></li><li><a target="_blank" rel="ugc" href="https://github.com/yuvraj108c/ComfyUI-Upscaler-Tensorrt">ComfyUI-Upscaler-Tensorrt</a></li><li><a target="_blank" rel="ugc" href="https://github.com/pollockjj/ComfyUI-MultiGPU">ComfyUI-MultiGPU</a></li><li><a target="_blank" rel="ugc" href="https://github.com/lldacing/ComfyUI_PuLID_Flux_ll">ComfyUI_PuLID_Flux_ll</a></li></ul><h3 id="pulid-need-your-python-to-have-insightface-:-7by78ta4b">PuLID need your python to have Insightface :</h3>Check your python version :<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/cca6ff29-e044-41c7-a680-2c54623824e0/width=525/cca6ff29-e044-41c7-a680-2c54623824e0.jpeg" />for windows portable version : (the path depends on where you unzipped ComfyUI)<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/0137d2c6-21f8-4266-88fc-f16efcc0145c/width=525/0137d2c6-21f8-4266-88fc-f16efcc0145c.jpeg" />Download Insightface whl which corresponds here : <a target="_blank" rel="ugc" href="https://github.com/Gourieff/Assets/tree/main/Insightface">Assets/Insightface</a> (Here my local python is on 310 and mobile version in 312)Then install all prerequisites and insightface :<pre><code>python.exe -m pip install --use-pep517 facexlibpython.exe -m pip install git+https://github.com/rodjjo/filterpy.git
python.exe -m pip install onnxruntime==1.19.2 onnxruntime-gpu==1.15.1 insightface-0.7.3-cp310-cp310-win_amd64.whl</code></pre><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/31b98d41-5766-4d75-b3fb-2270a47ddc47/width=525/31b98d41-5766-4d75-b3fb-2270a47ddc47.jpeg" />

FACE to VIDEO simple workflow WAN2.1 | GGUF | PuLID | UPSCALE | TeaCache

Bugfix : upscaling nodeAdd : <ul><li>LoRA,</li><li>Change of execution order between interpolation and upscaling, really independent and better optimized.</li></ul>

Files with SHA256: 01a39ecccab53125acd6928402d1b66e70800742e29561cec34dcd454572a8a4