UPDATE: WAN 2.2 Smooth SVI Pro Workflow V.2 (03/25/2026)
Updated the workflow to use the ComfyUI-NAG. I tried to give more control over every video/extension so each could be costumized freely. You should have a lot of control now. Make sure to fully update your Comfyui and the extensions.
There are detailed notes now. Make sure to read them. :)
Download the videos on the Showcase and drag to ComfyUI for their full worklfow. I tried some different setups: 32 fps with no interpolation, 24 fps with interpolation, euler/simple and uni_pc/sgm_uniform... These are just examples on how you can mess and have fun with the setup. ^^
You can turn on and off Video Interpolation for each extension. Make sure your setup can handle Interpolation of longer videos.
I tried to make everything easy to find or change using very simple subgraphs. If you want to add or change something it should not be hard to do so.
Added a simple Node for saving the last frame of each video/extension. Some suggested this for helping with their video editing and creation.
The videos on the showcase used the following Model and Loras:
Models: Smooth Mix Wan 2.2 I2V v2
Light Loras:
HIGH - wan2.2_i2v_A14b_high_noise_lora_rank64_lightx2v_4step_1022.safetensors
LOW - lightx2v_T2V_14B_cfg_step_distill_v2_lora_rank128_bf16.safetensors
SVI Pro Loras:
HIGH - SVI_v2_PRO_Wan2.2-I2V-A14B_HIGH_lora_rank_128_fp16.safetensors
LOW - SVI_v2_PRO_Wan2.2-I2V-A14B_LOW_lora_rank_128_fp16.safetensors
Used extensions:
Have fun!
======================================================
WAN 2.2 Smooth SVI Pro Workflow
Its a big workflow. Make sure to fully update your Comfyui and the extensions.
Used extensions:
==========================================================
Its divided in sections to make it easy to navigate.
MODEL SETUP
Here you select and set up your High and Low Models (safetensors or GGUF), your Light Loras, the SVI Pro Lora, your Shift for model Sampling, the Scheduler and Sigma and finally Clip, VAE and your prefered Sampler.
The videos on the showcase used the following Model and Loras:
Models: Smooth Mix Wan 2.2 I2V v2
Light Loras:
HIGH - wan2.2_i2v_A14b_high_noise_lora_rank64_lightx2v_4step_1022.safetensors
LOW - lightx2v_T2V_14B_cfg_step_distill_v2_lora_rank128_bf16.safetensors
SVI Pro Loras:
HIGH - SVI_v2_PRO_Wan2.2-I2V-A14B_HIGH_lora_rank_128_fp16.safetensors
LOW - SVI_v2_PRO_Wan2.2-I2V-A14B_LOW_lora_rank_128_fp16.safetensors
There is a Note on the workflow with suggestion for values for Shift, Sheculer and Sigma. Be sure to check it!
VIDEO SETTINGS
Set your Starting Image and the video resolution. Its set to 720x480 as default.
VIDEO EXTENSIONS
Set how many times you want to extend your video. You can extend up to 5 times! Thats more than enough for 99% of people. More advance users will known how to go even further.
FIRST VIDEO/EXTENSION (1/2/3/4/5)
The 'NODES GUIDE' you help you easily find all you need to set up!
Set your High and Low Loras if you plan to use then
Set the total lenght - in seconds - for each video.
You can also set your Noise/Seed
Type your Positive and Negative Prompts!
=====================================================
VIDEO INTERPOLATION
I decided not to include video interpolation. Long videos makes it very common to users to run out of memory. If you really want to inerpolate video during the generations just add adn connect an interpolation node between 'Upscale Image By' and 'Video Combine'.
There are several free tools that can be used to do the same. The videos on the Showcase used Aiarty Video Enhancer (Paid), Flowframes (free) and DaVinci Resolve (free).
Just use your favorite tool for it! :)
=====================================================
Have fun!
Description
FAQ
Comments (6)
Do you plan to release a smoothmix LTX 2.3 anytime soon? I'm happy to provide compute if needed
Love the workflow so far, the end result is practically seamless, will definitely be using this. thanks for all of your hard work DP
Is there a good way to loop the same extension multiple times? to repeat a general motion for much longer (same loras, same prompt)
Hi, when I run another extension it starts loading everything from the beginning and I have the fixed seed.
EDIT: For anyone running into the issue that the workflow keeps restarting from First Video despite fixed seeds. For me it was caused by the Clean VRAM Used node inside the Upscaler subgraphs. I am assuming it is messing with comfyui's caching.
Is it just me or does the negative prompt do absolutely nothing with SVI models on this workflow? Everything else is working great but I would like to correct some weird model behaviors with negative prompts and can't, I have to write more strong positive prompts but often they are not enough