<h1 id="i2v-first-last-frame-loop-upscale-and-interpolate-or-all-in-one-wan-2.2-workflow">🎬 I2V · First Last Frame · Loop — Upscale &amp; Interpolate | All-in-One Wan 2.2 Workflow</h1>A 3-in-1 ComfyUI workflow for WAN 2.2 video generation - because switching between separate workflows got old fast. Everything you need is loaded once in a central Control Center, and you just flip a switch for the branch you want. This makes using my other workflows obsolete. But you can still use them if you prefer to have a single workflow for each task.<hr /><h2 id="what-this-workflow-can-do">✨ What this workflow can do</h2>🖼️ Image to Video (I2V) Your everyday workhorse. Load an image, write a prompt, run it. Supports a Batch Image Loader to automatically process all images from a folder sequentially — no manual loading per run.🔁 First Last Frame (FLF) Define the start and end frame of your scene and let the model figure out what happens in between. Great for controlled transitions and cinematic shots.🔄 Loop Like FLF, but uses the same image for both start and end — generating a seamless loop. Perfect for endlessly repeating clips.⬆️ Upscale &amp; Interpolate Both can be toggled independently via Fast Groups Bypasser nodes. Use one, both, or neither — your choice.💾 Save Last Frame Extracts and saves the final frame of your video for chaining into the next run. The secret sauce behind long-form video generation.<hr /><h2 id="key-features">⚙️ Key Features</h2><ul><li>🎛️ Central Control Center - set your model, VAE, CLIP, resolution, steps and Speed LoRAs once, use across all branches</li><li>⚡ Lightning LoRA support (Lightx2v / High + Low) with a dual-step sampler setup for faster renders</li><li>🔀 Dynamic Prompts support with wildcard syntax for flexible, randomized prompting</li><li>🧩 Power LoRA Loaders per branch - each branch has its own independent LoRA setup</li><li>📦 Supports both FP8 scaled, Model merges and GGUF model variants</li></ul><hr /><h2 id="model-folder-structure">📁 Model Folder Structure</h2>Place your files inside your ComfyUI installation as follows:<ul><li><code>models/diffusion_models</code> → Wan 2.2 model files</li><li><code>models/LoRAs</code> → Speed LoRAs and concept LoRAs</li><li><code>models/vae</code> → VAE</li><li><code>models/text_encoders</code> → CLIP / text encoder</li></ul>⚠️ After loading the workflow, click each model loader and select your files from the dropdown. Paths won't resolve automatically.<hr />Full setup instructions, recommended LoRA strengths and all download links are included inside the workflow in the markdown guide node. 📋

Files with SHA256: 3d202a097d9f28363711a07343465f8dde25b7d486679f25d7cf54fead6591f6