Hello Everyone^^ ✨
I am so incredibly excited to share this with you all! This workflow was created as a massive Thank You to celebrate reaching 1K followers here on CivitAI!
☕ Get any works I've created "Concept Request", or Order Commission here:
https://ko-fi.com/lumi_nami/commissions
Support my works on patreon^^
(some exclusive NSFW works with sound also available here)
https://www.patreon.com/LumiNami
🤖 What is this workflow?
"This is a seamless, looping video workflow designed to easily switch between multiple image references. It is highly optimized for generating Live Wallpapers and General NSFW anime style videos using the power of Wan Video 2.2 I2V 14B."
Watch the Demo Video to know how to set up this workflow^^
🛠️ Version 1.1 - The Optimization & Fixes Update! ^^
Hello everyone! Thank you so much for all your feedback on the initial release. This version focuses heavily on simplifying the workflow, removing visual bloat, and fixing the pesky custom node errors that popped up on fresh installs! ✨
What's new and improved in v1.1:
🔄 Node Replacements: Swapped out problematic/deprecated nodes causing unknown errors with simpler, stable alternatives.
🧹 Streamlined Interface: Removed MMAudio and complex visual bloat to strictly focus on single-concept generation (1st group nodes). Improved the use of "pin nodes" and subgraphs for a much cleaner look.
⚙️ Better Generation Flow: Optimized SET_GET, Fast groups, and Switcher nodes for easier usage and troubleshooting.
🐛 Bug Fixes: Resolved the known "AIO disconnected" and "save text" errors.
📚 Built-in Resources: Added helpful notes inside the workflow containing used model and custom node list.
✅ Fully Sanity Tested: Ran complete, from-scratch tests across various GPUs (Ampere (3070, A4500), Ada (4060 Ti, 4090), Blackwell (5090)). It runs smoothly from missing node downloads all the way to the final result without a single error! (Note: performance still depends on your specific system).
Read my Patreon post below for more in-depth explanation about this fixed version:
>>> Go to Patreon post <<<
✨ Key Features v1.0
Semi-Automated: Set your prompts, upload your images, adjust the light blue nodes, and hit Run!
Long Video Generation: Create (up to 15s+) videos using Stable Video Infinity (SVI 2.0 PRO).
Better Adherence: Better results and prompt adherence powered by Very Big Video Reasoning (VBVR) Wan 2.2 LoRA.
High-Quality Upscaling: Generates at 720p 24fps (by default), then upscales to a stunning 1080p 60fps final render using SEEDVR2 and RIFE VFI.
Built-in Audio: Video-to-Sound effects generated with MMAudio (with plans to upgrade to AudioX in the future!).
⚙️ How the Looping Magic Works
The core looping logic is heavily inspired by the amazing "Wan 2.2 Perfect Loops" workflow by @Caravel. Here is the simplified breakdown of how it creates a seamless loop based on my understanding:
First, it generates "Main" video which you can completely control the resolution, length, and FPS.
Next, it takes the very beginning frames and the very last frames of that Main video to generate an "In-Between" transition video. (Note: the number of frames is the half of your inputted FPS.)
Finally, it blends those Main and In-Between videos seamlessly together to create the perfect loop!
🚀 How to Use (Step-by-Step)
(1st) Set IMG & Prompts: Go to this group node and paste your prompts into the text box (check inside the nodes for extra tips!). Upload the images you want to use (up to 6!).
(2nd) Generation Settings: Select which of your uploaded images to process (1-6). Here you also set your concept type, name, resolution, length, FPS, seeds, etc on the light blue nodes.
(3rd) Main Video IMG2VID: Choose whether you want the Default or SVI workflow for your Main video. Customize any light blue nodes you want. Important: Bypass any unused group nodes before you click "Run" XD.
(4th) In-Between VID: Upload your freshly generated "Main" video into the Load Main Video node. Right below it, manually adjust the video length by frame count and tweak any light blue nodes if you wish. Run!
(5th) Video Combine, Upscale & Interpolate: Upload both your "Main" and "In-Between" videos here. You can fine-tune the final look by adjusting brightness, contrast, and saturation in the LayerColor Node. (Bypass MMAudio if you don't want sound). Run and Done!
The light blue nodes in question:
🎥 Results
The final video is a FHD 60FPS seamless looping video which the resolution, duration, and FPS depends on your settings. But, by default is:
Main Default (5s) + In-Between (4s) : 1080p, 60fps, 9s
Main SVI (2 batches of 5s) + In-Between (4s) : 1080p, 60fps, 13s
🖥️ Tested Hardware
RTX 5090: Runs very smoothly on Main & In-Between steps. (Note: You may experience an Out Of Memory error during the Upscaling step when upscaling Main SVI video with 2 or 3 batches).
RTX 6000 Ada: Runs incredibly smoothly across all steps, though slightly slower than the 5090.
Other GPUs: Definitely possible! Just always make sure to adjust the resolution or video length to match your system's capabilities.
⚠️ Known Issues (v1.0)
The generated video might look contrasty on "Main SVI batch 2 & 3" and "In-Between" generated videos. Don't worry, this gets slightly fixed and smoothed out during the SEEDVR2 upscale step at the end!
On default workflow to generate (720p, 24f, 4-5s) video, it really needs a massive amount of VRAM. On 3rd & 4th step a 24GB VRAM card is recommended to run it smoothly, while the 5th step requires at least 32GB VRAM card while still need to full model offload 😨.
🌱 Future Updates & Feedback
This is just v1.0, and I plan to keep tweaking and improving this workflow! Please let me know in the comments if you run into any problems or have suggestions to make it even better ^^
🙌 Special Thanks
A massive shoutout to @Caravel for the amazing [Wan 2.2 Perfect Loops] which serves as the core of this heavily modified workflow! And a huge thank you to @Coffee_ICE for helping me out with the SEEDVR2 upscale experiments!
I also want to give a massive shoutout and credit to @NRDX for his incredible Live Wallpaper Style LoRA! This model is an absolute pioneer for this workflow, It has been a huge inspiration and foundation for my generations since Wan 2.1. The results in this workflow wouldn't be the same without it, so please go check out if you're interested! ✨
Your help made this workflow possible >w<
I'll also write the same license that applies when modify the "Wan 2.2 Perfect Loops" workflow below and share the same permission as it should be:
License Information: These workflows are licensed under the GNU Affero General Public License, version 3 (AGPLv3) and constitute the "Program" under the terms of the license. If you modify and use these workflows in a networked service, you must make your modified versions available to users interacting with that service, as required by Section 13 of the AGPLv3.
Read the full license here: https://www.gnu.org/licenses/agpl-3.0.en.html#license-text
Description
🌱 Version 1.0 - Initial Release! ^^
Hello everyone! This is the very first version of my seamless looping workflow, released specially for my 1k Followers Celebration! 🎉
What's included in this first release:
✨ Semi-automated pipeline for generating seamless Live Wallpapers & General NSFW video using Wan 2.2 I2V 14B.
🪄 High-quality upscaling to 1080p 60fps (SEEDVR2 + RIFE VFI).
🎵 Video-to-Sound effects powered by MMAudio.
⏳ Long Video Generation using Stable Video Infinity (SVI).
🎯 Better results and prompt adherence powered by Very Big Video Reasoning (VBVR) Wan 2.2.
🖼️ Easy-to-use image reference switching (upload up to 6 prompts/images).
Can't wait to see what you create with this! Let me know in the comments if you have any feedback or suggestions for future updates. Have fun! ✨
FAQ
Comments (17)
Hey, this workflow seems very interesting. But I don’t think I’m the only one who is unable to use it, there’s just too much going on. Could you please create a simplified version of the workflow using just one image as both the starting and ending point, which would be very useful for creating simple loops? Just keep the core concepts.. Or maybe you could make a short video, where you go over how to use it, set it up..
Hello @Nomi_in_Space^^ Thank you so much for the feedback! I totally understand that this workflow definitely look overwhelming at first glance.
And sure! I'm going to put them together into a short, step-by-step tutorial video on how to use and set the entire workflow! I'll add some clear visual guides so it's easier to follow along. ✨
Then, I'll upload it into the main post along with the examples as soon as it's ready!
Oh, this is the best workflow I could find, but like the “perfect loop” workflow you mentioned, I encountered many issues during actual operation, such as “AIO nodes” showing "disconnected" and “save text” errors. Could you please you make a video demonstrating how to use it？
哦，这是我目前能找到的最佳工作流方案，但正如你提到的完美循环工作流一样，我在实际操作中遇到了诸多问题，比如AIO节点显示“断开连接”和“save text”报错。能请您能录制一段使用教程视频吗？
Hello @djh515064403973^^
I'm glad you like the workflow! But, I totally understand your frustration with those issues. Actually, the “AIO nodes” showing "disconnected" is some of the uncleaned part from the workflow when I simplify them. Before, both "Seed HIGH1" and "Seed LOW1" nodes were inside the AIO Nodes. But, since the seed input value showed on AIO Nodes can't configure the randomize or use last seed.. I decided to move the seed nodes back outside in the end, which is why it showing "disconnected" as now.
While the "save text" errors was caused by the nodes itself require "text" as an input and there are 0 nodes connected to this input. In the workflow, the text string was connected to "file" input instead of "text". Because we only needed it to append the initial concept name as the filename prefix and not saving the (.txt) file into the specified "root directory".
Regarding to those errors, I'll try to fix it and maybe uploaded it as v1.1 (or add the fixed workflow into the download file) later! Also, I'll create the demonstration video which showing how to use and set up the entire workflow.
I'll update the main post along with the demonstration video and let you know as soon as the video is ready! Thank you so much for your feedback! ✨
@LumiNami oh，Thank you for your reply. I have seen your works before when learning to make live wallpapers, and really like your works. I am looking forward to your future updates ✨
感谢你的回复，之前学习制作动态壁纸时就看到过你的作品，非常喜欢您的作品，十分期待您后续的更新✨
Hello everyone! ^^
The Demo Video is officially available to watch now! [ see post or here: https://civitai.com/posts/27236013 ] 🎬
I really hope this helps make it much easier to understand how to set up the workflow and generate the looping videos! I'm so sorry if the video feels a bit too long or goes a little too fast in some parts! XD
Also, @djh515064403973 and @Nomi_in_Space!! The demo video is ready now, you can watch it right up in the example videos on this model page! ^^
Thank you so much all for the feedback and waiting! I'll definitely fix this workflow in future updates! 🌸✨
Thanks for the video and great workflow. However, the problem is not solved with an explanation. After hours of trying to get it to work, I can't install many of the nodes. They conflict with existing extensions, are discontinued, etc. Hoping for a v1.1!
nice job！o(≧v≦)o
Kinda getting annoyed with subgraphs being a part of every workflow. It doesn't help that comfy and comfy manager can't see into them so if you're missing a node you have to navigate to the subgraph and then look for missing nodes again. And then the nodes that aren't a part of the manager repository and force you to install from outside. I stop using the workflow if I run into that.
I'll never understand why you'd use 100Gigs of WAN models to generate ... 8 bit anime. I'll pass unless someone posts a 30s REALISTIC video without any degradation.
hi!
help plz
"ValueError: VACE only works properly with T2V models."
on step 4
i'm use:
Wan2_2_Fun_VACE_module_A14B_HIGH_bf16.safetensors
Wan2_2_Fun_VACE_module_A14B_LOW_bf16.safetensors
and
Wan2_2-I2V-A14B-LOW_fp8_e4m3fn_scaled_KJ
Wan2_2-I2V-A14B-HIGH_fp8_e4m3fn_scaled_KJ
Hello @MugenMan! It seems that you ran into an error in "4th In-between" group nodes which using "VACE" framework and must use "T2V" based wan2.2 model to be able to run properly^^
You can try to change your base model from "I2V" to T2V" and give it another shot!
> Wan2_2-T2V-A14B-LOW_fp8_e4m3fn_scaled_KJ
> Wan2_2-T2V-A14B-HIGH_fp8_e4m3fn_scaled_KJ
@LumiNami It was obvious, but it caught me off guard, so I decided to check...
And how compatible is this with the loras that are trained for i2v?
Naturally, I will check it myself, but I would like to know how it was meant
@LumiNami I checked.
The video's image is degrading, even without loras, hmmm
What could be my problem?
Hi, video 2 for in-between vid seems to be missing. I got this error from wan video sampler, "expected stride to be a single integer value or a list of 2 values to match the convolution dimensions, but got stride=[1, 2, 2]", do you know what might cause it? Thx
I've attempted three times to install this very complex workflow and its very, very high amount of dependencies on clean installs of comfyUI.
I'm giving up. Passerby, do not waste two hours with this bloat.
Hi, thanks for your feedback! It's true that the workflow is very complex right now. I'm actually still working on it to make it simpler and easier to generate. You can definitely just skip this workflow for now, or wait for the updated version in the future! ^^