VERSION 3 NOTESFirst off, this has a custom node I made for predicting flow to help smooth transitions iteration to iteration. Place the whole folder (included in workflow download) in your custom nodes.Version 3 is an experiment at this point. Could use some more testing and tweaking, but it has some cool features so wanted to share.<ul><li>Predictive Flow - this is probably the coolest one and is working the best right now. Basically at the end of an iteration, it predicts the beginning of what the next iteration should start like. This gets converted to a latent to get blended in with your subsequent iteration. Should reduce jitters from iteration to iteration</li><li>Noise adaptation - if your iterations start losing quality and get noisier, it should dynamically switch to adding more steps and adjusting sampler parameters</li><li>Face ID - Not working yet since I'm running into wan compatibility issues, but it's intended to prevent face warping. I'm working on this still.</li></ul><hr />So from version 2, I added a new T2V feature for it. With this, you can change the workflow to start from a T2V prompt creation instead of an I2V workflow for the first iteration. Then subsequent iterations will go off I2V so you can continue your T2V prompt for however many loops you want.Heads up that FLF on T2V still references the uploaded image. I'm wanting a future version to reference the first image of the T2V created vod, but I haven't got the conditional logic set up yet.<h2 id="notes-on-credits:">Notes on credits:</h2>I got the base of it from <a target="_blank" rel="ugc" href="https://civarchive.com/models/1829052?modelVersionId=2070152">https://civarchive.com/models/1829052?modelVersionId=2070152</a>I got most of the florence stuff from <a target="_blank" rel="ugc" href="https://civarchive.com/models/1687498/wan-2221-i2v-2-workflows-merge-fusionx-lora-2-sampler-florence-caption-last-frame-color-match?modelVersionId=2061133">https://civarchive.com/models/1687498/wan-2221-i2v-2-workflows-merge-fusionx-lora-2-sampler-florence-caption-last-frame-color-match?modelVersionId=2061133</a>The stuff around FLF was mainly me messing around so I added that myself and also made some adjustments from the previous two workflows mentioned to what I liked more.<h2 id="what-does-it-do">What does it do?</h2>It's basically a for-loop gguf wan2.2 workflow. You can set up however many iterations to go through. There is an option for the last iteration you have to go to a FLF workflow which should help continuity a bit.<h2 id="features:">Features:</h2><ul><li>For-loop based I2V gguf workflow</li><li>T2V first iteration to I2V gguf workflow</li><li>Auto captioning per iteration + customizable after text per iteration</li><li>Auto sizing images (to avoid mat errors)</li><li>Last For-loop iteration goes to FLF (optional selection)</li><li>Upscale + Interpolate</li><li>Individual Loras per high and low lora per iteration (power lora so easier selection)</li><li>Using ClownsharKSampler</li></ul>To be added at some point... maybe (once I study up on these more)<ul><li>VACE integration (wanting to look into Phantom too)</li><li>Spline Integration</li></ul>So far I've been finding good results with linear/euler + beta57, but always looking for better options.

Wan2.2 I2V GGUF Workflow (For-Loop w/ Individual Loras + Auto Caption + Predictive Flow + FLF + T2V -> I2V + Upscale/Interpolate)

THIS IS AN EXPERIMENTAL VERSION. I will remove this one final v3 is made and more testing is done.THIS USES A CUSTOM NODE I MADE. Put the whole folder predictive_flow into your custom_nodes and restart comfyui for it to work.<ul><li>Custom node: Motion Prediction - Smooths transitions between iterations, so less abrupt jitters in motion</li><li>Adaptive Noise Steps: Calculates amount of noise added since start. If certain threshold is reached, increases step count and reduces denoising</li><li>Preventative Face Degradation (not working) - Trying to guide model into keeping reference image face. Doesn't break things, but doesn't do anything I think currently.</li></ul>

Files with SHA256: c9f86054adf7c2b6e1781b3e008646963a543bd566d2e1413d7a5fce5778b9c6