LTX 2.3 Remaster any Video
This workflow allows you to remaster some existing video, you can specify an driving video and it is used as input for the generation. You can also specify up to 4 keyframes to drive your video generation (easy to extend)
LTX 2.3 Extend any Video
This workflow allows to extend videos and stitch the new part seamless onto the existing video.
LTX 2.3 Sound to Video
Added a basic LTX Sound to video workflow that can be used for music videos. Or other use cases.
LTX 2.3 Bounce V 2.5
Added a basic LTX workflow to use the bounce 2.5 lora.
Better Details due to Detailer lora
Referenced new Distill Lora 1.1
LTX 2.3
Added a basic LTX workflow to use the bounce lora
WAN I2V 2.2 / 2.1 - Resume Video + Upscale + Interpolation
ChangeLog
WAN 2.2: Added quality workflow for liquids. Slow but good quality!
WAN 2.2 Lightning 8 Steps added as reference WAN 2.2 workflow with lightningX!
V1_0_6_2_Quality added, since the causVid version did not work well with my newest "big splash" lora...
V1_0_6_2: Replaced the Int node with comfyui base because it caused some troubles for some users
V1_0_6_1: with the causVid lora generations times of < 1minute possible,
Since a lot of ppl were asking how my personal Workflow looks like here it is! It has some handy features like inbuilt upscaling and continuation of videos with the last generated frames. Don't use more than 1-3 continuations because the Quality loss is quite huge.
It's optimized for a 4090 and 24GB of Memory. But by playing with the params less is possible.
Input Modes
Image -> Use a input images selected by the user
Image Directory -> Set a input directory and load with every run another image as source
Resume Last Frame -> Load the last frame of last generation as input image. Ensure you have done one before
Resume From Video Last Frame -> Select an input video and resume from the last frame. This is helpful if you want to do several continuation attempts of one source video
Quality Options
Face Fix-> Uses ReActor to fix the face. I turn this mostly off for wan because its already good enough
Upscale -> Upscales the output to maximize the quality
Remarks:
The ReActor Node is optional, i have my own modified version with disabled NSFW check, you can add any face swap node there, but wan is really good with faces so its not needed
Description
This is the normal non CausVid Edition
FAQ
Comments (15)
Deleting all the crappy workflows i've used from this site that never work or give junk results. This is the one that works, and it works very well. Thank you for this.
i lost some time searching it, you need that specific encoder for it to work
Why is no one talking about your two posts next to each other interacting? That was brilliant with the water
I came in here to see if anyone had commented on it. Such a cool effect
Has someone can explain what`s the difference between the basic teacache and blockswap with this?I use 4090 and the basic workflow i2v make 5s outputs will consume 228.8s,thks!!!
nice workflow. two things you could add, one is i.e. a cfg schedule if using causvid. starting with high cfg and ending with cfg=1 (sometimes help with motions). and second you could autocalc the image dimension. i personally hate it that i have to manually resize the image, because most of my images dont have the standard size/ratio. (for resizing you could use i.e. 16*round((a/b)**0.5*c/16) for each side, a is image width (or height), b is image_width*image_height and c is max number of pixel). so if you want 720p quality you just use 921600 pixel for c and no matter the image size and ratio, it autoscales the image so that it has a total of 921600 pixel
Amazing workflow! Thanks!
I have one question tho. If I set the frame number to 81 and frame_rate to16, I am expecting a 5s video but get a 4s one instead. Do you have any idea why? Thanks!
Well that's interesting. Cant answer it I think it might be something to ask for Kijai
The frames give you the amount of time; increasing them can eat up memory, so try increasing them a little: 4 seconds =106 frames
Anyone know how this works on a rtx5080? What settings to save vram?
Set TORCHDYNAMO_VERBOSE=1 error. I'm using portable version if that matters. I have install triton, sage, and flash attention just fine. I used the accelerated_270_312.txt file to do so.
Sorry, I still get Missing Node types: Int-🔬