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.
Main Features
Fully automated from start to end.
Handles from 2 to a potentially unlimited number source pictures.
Flexible prompting.
Flexible video lengths (v2).
Increased generation speed (v2).
Can produce looping and non-looping videos.
Works on 12GB VRAM cards and higher.
Getting Started
Replace the models, clip, and LoRas by those you usually use.
Set the folder location of your pictures, in the node Load Images from Folder (KJ).
Set the outputs width and length(s).
Write your prompt(s)
Click "Run".
Usage & Tips
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.
Custom Nodes
Required
Optional
ComfyUI-Impact-Pack (for multi-prompting) (v1)
ComfyUI-GIMM-VFI (for interpolation)
Models Used
Wan 2.2 14B I2V, Quantized:
• https://huggingface.co/QuantStack/Wan2.2-I2V-A14B-GGUF/tree/main
Lightx2v LoRas :
• https://civarchive.com/models/1585622?modelVersionId=2361379
• https://civarchive.com/models/1585622?modelVersionId=2014449
Fun LoRa:
• https://huggingface.co/alibaba-pai/Wan2.2-Fun-Reward-LoRAs/tree/main
Description
FAQ
Comments (10)
I was meaning to ask you more questions about your process, but now that you dropped the workflow I'll just try it out and understand it better! 😘
Thanks for sharing!
Yes it's the same workflow as in https://civitai.com/images/109652821. I just simplified it a bit for better compatibility.
Eager to see what will come out of it!
Great workflow. It actually get FFLF to be great. thanks.
This is the best workflow for long loops I have found, thank you very much for sharing!
Thanks for the feedback, I appreciate.
why are there two high noise speed loras?
I thought combining both would improve motion, but you can remove the wan21 one if you prefer.
I love the workflow, but I can't seem to get it to execute more than two image transitions. Is it capped by VRAM or something? I'm using a 3090, using the stock workflow, loading in a folder with four images, but otherwise no settings changed.
Hi, I can run it on a 3060 with 25 images.
There is no capping, but verify that in the node "Load Images From Folder (KJ)", the "image load cap" setting is set to match at least the number of images in your folder (by default it is set to 4).
Also there must be something going out of the "For Loop End" node (connect the "value 1" output to anyhting), otherwise it won't loop more than once.
Let me know if it solves your issue.
@qdr1en actually I think I just didn't realize it made a bunch of clips and I wasn't checking there's a fully combined one