<h1 id="foton's-wan-2.2-image2video-workflow">Foton's Wan 2.2 Image2Video workflow</h1><p><span style="color:rgb(64, 192, 87)"><strong>Designed for 12GB or lower VRAM.</strong></span><br /><span style="color:rgb(134, 142, 150)">Can be modified to work with more demanding models, but there's a lot of workflows for that already.</span></p><h2 id="features">Features</h2><ul><li><p>Easy generation config</p></li><li><p>Lora Support</p></li><li><p>Advanced Cropping</p></li><li><p>Built-in Upscaling and Interpolation</p></li><li><p>Add audio track (not audio sync)</p></li></ul><h2 id="v2.0-update">v2.0 update</h2><ul><li><p>Tested with ComfyUI 0.43.0</p></li><li><p>Added new nodes for cropping input images. (Be aware that If you create multiple crops it will generate multiple videos in sequence). Examples:<img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/ccd6cfb2-d634-4aae-8b22-d9d55347ea1f/original=true/ccd6cfb2-d634-4aae-8b22-d9d55347ea1f.jpeg" /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/c39b77e4-0ccc-4bf7-b008-4e32afbd7f24/original=true/c39b77e4-0ccc-4bf7-b008-4e32afbd7f24.jpeg" /></p></li><li><p>The downside of a new crop tool is that it doesn't save crop settings inside the workflow. As a workaround I added a Save Image node for cropped outputs if you want to use them later.<br /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/57f34abe-b7a6-440b-8c0b-f33df2f3df31/original=true/57f34abe-b7a6-440b-8c0b-f33df2f3df31.jpeg" /></p></li><li><p>Removed deprecated (outdated) nodes.</p></li><li><p>Included Seed VR2 upscaler as an alternative.</p></li><li><p>(Advanced/experimentall) Added a Torch Compile switch that is turned off by default. In short, it optimizes generation speed for consecutive videos by 15-20%, but your first generation will be much slower. When you change model/loras, output resolution of number of frames it will recompile again.<br /><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/9d8bfd85-3ecc-41a9-9783-2237f5c13584/original=true/9d8bfd85-3ecc-41a9-9783-2237f5c13584.jpeg" /></p></li></ul><p></p><hr /><h2 id="easy-generation-config">Easy Generation Config</h2><p>Uses Lightning Lora by default to speed up generation considerably (3 min vs 15+mins on my 4070) at the cost of motion dynamics. Can be disabled with 1 click but will require 20-30 steps.</p><p><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/ef67f59d-a42a-4ebd-810e-7aaa9d8db8d8/original=true/ef67f59d-a42a-4ebd-810e-7aaa9d8db8d8.jpeg" /></p><p></p><h2 id="lora-support">Lora Support</h2><p>Support up to 2 Loras, you can add more manually with higher VRAM.</p><p></p><h2 id="advanced-cropping">Advanced Cropping</h2><p>Lets you crop images to fit landscape image into portrait and vice versa. Use offset to adjust crop center. Example:</p><p><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/b43e9a0d-05f0-42a9-bba8-d0bc91b0607a/original=true/b43e9a0d-05f0-42a9-bba8-d0bc91b0607a.jpeg" /></p><p></p><h2 id="built-in-upscaling-and-interpolation">Built-in Upscaling and Interpolation</h2><p>Uses RIFE interpolation to generate frames. Use <strong>rife49.pth</strong> or <strong>rife47.pth</strong> for best results. You can replace Remacri upscaler with any other ESRGAN model like UltraSharp, R-ESRGAN4x, etc.</p><p>Blend_factor does some initial color correction for Remacri - it tends to desaturate images. Set it to 0 if you're using another upscale model and the result is too saturated.</p><p><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/0d0043d0-f028-4b31-b817-7148140f8ad2/original=true/0d0043d0-f028-4b31-b817-7148140f8ad2.jpeg" /></p><p></p><h2 id="save-last-frames">Save Last Frames</h2><p>Saves a number of last frames if you want to use them to generate a new video and then stitch them together. (Sometimes last frame has motion blur, so I added an option to save as many as you want).</p><p><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/3ce2e1fe-f428-48a0-9aa2-abf16dbe55dc/original=true/3ce2e1fe-f428-48a0-9aa2-abf16dbe55dc.jpeg" /></p><p></p><h2 id="add-audio">Add audio</h2><p>Audio is not syncronised, this requires another workflow entirely with SI2V models.</p><p><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/4a9c84e6-a499-4b8b-bb86-6a30a377f123/original=true/4a9c84e6-a499-4b8b-bb86-6a30a377f123.jpeg" /></p><p></p><p></p><p></p>

Files with SHA256: 269b471a9a3dcd3df99f15f2d7bfe55fc8bbd0daee264347facd02525e33a82b