v2.0 update!
New features include:
- Extend videos
- Selective LoRA stacks
- Light, SVI and additional LoRA toggles on the main loader node.
A simple workflow for "infinite length" video extension provided by SVI v2.0 where you can give infinite prompts - separated by new lines - and define each scene's length - separated by ",".
Put simply, you load your models, set your image size, write your prompts separated by enter and length for each prompt separated by commas, then hit run.
Detailed instructions per node.
Load video
If you want to extend an existing video, load it here. By default your video generation will use the same size (rounded to 16) as the original video. You can override this at the Sampler node.
Selective LoRA stackers
Copy-pastable if you need more stacks - just make sure you chain-connect these nodes! These were a little tricky to implement, but now you can use different LoRA stacks for different loops. For example, if you want to use a "WAN jump" LoRA only at the 2nd and 4th loop, you set "Use at part" parameter to 2, 4. Make sure you separate them using commas. By default I included two sets of LoRA stacks. You can overlapping stacks no problem. Toggling them off or setting "Use at part" to 0 - or a number higher than the prompts you're giving it - is the same as not using them.
Load models
Load your High and Low noise models, SVI LoRAs, Light LoRAs here as well as CLIP and VAE.
Settings
Set your reference / anchor image, video width / height and steps for both High and Low noise sampling.
Give your prompts here - each new line (enter, linebreak) is a prompt.
Then finally give the length you want for each prompt. Separate them by ",".
Sampler
"Use source video" - enable it, if you want to extend existing videos.
"Override video size" - if you enable it, the video will be the width and height specified in the Settings node.
You can set random or manual seed here.
I have also included the previous versions' base and fully extended (no subgraph) version for manual engineering and / or simpler troubleshooting.
Custom nodes
Needed for SVI
rgthree-comfy
ComfyUI-KJNodes
ComfyUI-VideoHelperSuite
ComfyUI-Wan22FMLF
Needed for the workflow
ComfyUI-Easy-Use
ComfyUI_essentials
HavocsCall's Custom ComfyUI Nodes
ComfyUI LoRA Manager
Description
FAQ
Comments (17)
is this so complicate
Unless you want to engineer it, you basically have to use the settings node only, just set size and prompt, then run.
It's about as simple as this can be made, even fully extended it's twenty-some node altogether plus another dozen for setting things.
@yorgash this still complicate
@yorgash Internet at its best
There's a brief jump cut in between the clips, what do you think is the problem? No loras, only the defaults settings from the wf.
Not sure, there shouldn't be any, I either have none or a huge one, no in-betweens.
For me the jump only happens when there's a substantial change in the background.
But so far I've only met that problem twice out of dozens of generations.
I have the same problem, but a very nice workflow!!
I think the exact lightning loras solves this problem or the new update. I noticed I used a different lightx2v version for v1 of the wf.
nice but how apply separate lora's for each clips ?
I'm already thinking the next update should include a separate panel for applying LoRAs to different parts.
It will need some engineering and probably a huge block for LoRAs and logic.
@yorgash This workflow is great, It would be amazing if you could set it up so we could apply different loras to different sections.
@yorgash the workflow works nicely, perhaps if you can find a way is to have toggles to enable / disable loras from the main view. I needed to go into the subgraph to disable the lightx2v lora loaders as the model I'm using has lightning already integrated.
@AIDreaming I'll put a toggle for light LoRAs in the update (soon).
@jbear2447 I have managed to implement that, will update now.
@jharaxofficial568 @jbear2447 @AIDreaming
V2.0 is released, the separate LoRA stacking as well as the toggles included.
Additionally you can load and extend existing videos too.
@yorgash good job
Amazing workflow! Kudos!