WAN-L.O.V.E. is hybrid Wan Low Overhead VRAM Efficiency Image-to-Video Fast (4-step) All-In-One model (full checkpoint: UNET, CLIP and VAE). All you need to encode source images is this model and, optionally, <a target="_blank" rel="ugc" href="https://civarchive.com/models/1329096?modelVersionId=1501088">CLIP Vision model for Wan</a>. Use CFG 1 and Euler sampler and beta scheduler and model shift 8-12. Enjoy! In ComfyUI just use usual default workflow with checkpoint loader, CLIP vision loader and sampler. Note: If you look for Wan 2.2 14B all-in-one version, then <a target="_blank" rel="ugc" href="https://civarchive.com/models/1824594?modelVersionId=2064786">try this</a> checkpoint, the same 1-pass workflow as for Wan 2.1 will work pretty well. Real 49 frames of 720p video generation with Wan 2.1 14B on i5-11400 with RTX 3050 4Gb and 32 Gb RAM via ComfyUI: <img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/bd373628-a3b6-41c9-9a87-70adea2a3f5a/width=525/bd373628-a3b6-41c9-9a87-70adea2a3f5a.jpeg" /> And the easy-peasy one-pass workflow (<a target="_blank" rel="ugc" href="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/98af5463-fc75-4be3-a04c-b50f3e18dd5d/original=true,quality=90/wan21_checkpoint_workflow.jpeg">open this picture in a new tab</a>): <img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/98af5463-fc75-4be3-a04c-b50f3e18dd5d/original=true,quality=90/wan21_checkpoint_workflow.jpeg" alt="wan21_checkpoint_workflow.png" />

WAN-L.O.V.E. Low VRAM Image-to-Video Fast All-In-One

fp8 e4m3<ul><li>model marked as "pruned" is just 1.3B with lightning LoRA</li><li>model marked as "full" is 1.3B with many improvements integrated</li></ul><a rel="ugc" href="https://civitai.com/search/models?baseModel=Wan%20Video%201.3B%20t2v&amp;modelType=LORA&amp;sortBy=models_v9">LoRAs for this model</a>

Files with SHA256: 5aace07e9d664044d72b35dccd5720517738647717bbfecff58d54b56db2e2e9