Initially built with photoshootings and music video clips in mind, the workflow actually automates the production of any type of long cinematic sequence. If you have a story to tell with your pictures, this is the workflow you need.<h2 id="main-features">Main Features</h2><ul><li>Fully automated from start to end.</li><li>Handles from 2 to a potentially unlimited number source pictures.</li><li>Flexible prompting.</li><li>Flexible video lengths (v2).</li><li>Increased generation speed (v2).</li><li>Can produce looping and non-looping videos.</li><li>Works on 12GB VRAM cards and higher.</li></ul><h2 id="getting-started">Getting Started</h2><ol><li>Replace the models, clip, and LoRas by those you usually use.</li><li>Set the folder location of your pictures, in the node Load Images from Folder (KJ).</li><li>Set the outputs width and length(s).</li><li>Write your prompt(s)</li><li>Click "Run".</li></ol><h2 id="usage-and-tips">Usage &amp; Tips</h2>By default, the same prompt is used for all generations, but you can use different prompts instead, by connecting the Concatenate node to the Positive Prompt node.If Wan makes unwanted hard cuts, it probably means there is too much "distance" between the start and the end frame. You can increase the number of frames, increase the number of steps, and/or increase the lightx2v LoRas strength to avoid that effect, to a certain extent. On the contrary, if the character barely moves, decrease the number of frames to make him move faster.(v1) For a non-looping video, disconnect the count connector in the Load Images From Folder (KJ) node from the total connector in the For Loop Start node, and set the total as “number of images - 1”. Images are sorted by name, so if you need to rename your images, remember that “10” comes before “9” (and before “2”), but “09” comes before “10”.An example prompt is provided, but feel free to experiment alternative prompts and settings. Enjoy, and if you are satisfied with the result, post your best takes.<h2 id="custom-nodes">Custom Nodes</h2>Required<ul><li><a target="_blank" rel="ugc" href="https://github.com/yolain/ComfyUI-Easy-Use">ComfyUI-Easy-Use</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 rel="ugc" href="https://github.com/ClownsharkBatwing/RES4LYF">RES4LYF</a> (v2)</li></ul>Optional<ul><li><a target="_blank" rel="ugc" href="https://github.com/ltdrdata/ComfyUI-Impact-Pack">ComfyUI-Impact-Pack</a> (for multi-prompting) (v1)</li><li><a target="_blank" rel="ugc" href="https://github.com/kijai/ComfyUI-GIMM-VFI">ComfyUI-GIMM-VFI</a> (for interpolation)</li></ul><h2 id="models-used">Models Used</h2>Wan 2.2 14B I2V, Quantized:• <a target="_blank" rel="ugc" href="https://huggingface.co/QuantStack/Wan2.2-I2V-A14B-GGUF/tree/main">https://huggingface.co/QuantStack/Wan2.2-I2V-A14B-GGUF/tree/main</a>Lightx2v LoRas :• <a target="_blank" rel="ugc" href="https://civarchive.com/models/1585622?modelVersionId=2361379">https://civarchive.com/models/1585622?modelVersionId=2361379</a>• <a target="_blank" rel="ugc" href="https://civarchive.com/models/1585622?modelVersionId=2014449">https://civarchive.com/models/1585622?modelVersionId=2014449</a>Fun LoRa:• <a target="_blank" rel="ugc" href="https://huggingface.co/alibaba-pai/Wan2.2-Fun-Reward-LoRAs/tree/main">https://huggingface.co/alibaba-pai/Wan2.2-Fun-Reward-LoRAs/tree/main</a>

Wan 2.2 I2V - Multi First-to-Last-Frame (FFLF) video. Automated, Easy, Looping, Multi-Prompting.

<ul><li>Improved Speed: by sampling at a low resolution with the high-noise model before upscaling the latent.</li><li>Added Flexible video lengths.</li><li>Visually cleaner than v1.</li><li>Refined default settings.</li><li>Dependencies: added RES4LYF custom nodes, removed ImpactPack.</li></ul>

Files with SHA256: b29c96e2636377858a62541fd13bda56a6950e09a28987f39f503663305f88ff