SVI Extend
https://github.com/vita-epfl/Stable-Video-Infinity/tree/svi_wan22
Create videos and extend them seemlessly using SVI.
Following SVI LoRAs are mandatory:
switch between default behaviour, anchor_samples and end_frames within the same subgraphs
connect an image to a part and enable the respective toggles to use end_frames or anchor_samples
NEW! v3
Extend existing videos using https://github.com/wallen0322/ComfyUI-Wan22FMLF
enable "video extension" toggle inside the settings
uses source video resolution by default
rescale video using the megapixel slider by enabling "video rescale" toggle
use included version of the nodes from inside .zip or download the latest version straight from the git if issues arise
More info inside the workflow.
AIO i2v+t2v
All in One workflow for for basic WAN 2.2 video generation.
Following features included:
Switch seemlessly between 2 and 3 sampler solutions
Toggle between i2v or t2v
Postprod
Facedetailer
uses t2v Model + LoRA for inpainting - resources needed included in workflow
Toggle between GIMM VFI and RIFE VFI Interpolation
Upscale
Tensorrt Upscale with Model
Basic Video Upscale with Model
RTX Video Super Resolution Upscale (insanely fast for decent quality)
Frame Clipper
Seamless Loops using custom RIFE nodes https://github.com/Artificial-Sweetener/comfyui-WhiteRabbit
Upscale + Interpolate
I recommend using this workflow instead of upscaling with the generating workflows, since you never really know what kind of results you get, ending up upscaling a bad video and wasting time. I included toggles so you can't use multiple interpolation or upscale nodes at once by mistake.
This includes:
WAN Facedetailer
use any WAN 2.2 T2V low model + the following T2V LoRA:
lower resolution from 768 to 512 if you have VRAM issues
Put the following file into "ComfyUI\models\ultralytics\bbox":
WAN Refiner (massive VRAM cost)
increase denoise if you want more inpainting
Sharpen, Gamma, Brightness and Contrast control
Frame clipper (remove unwanted frames at the start and/or end)
GIMM VFI + RIFE VFI interpolation (I recommend GIMM VFI, much higher quality but also much slower)
Tensorrt Upscale + Basic Video Upscale
both use basic image upscaling models
Tensorrt (faster than Basic Video Upscale) with AnimeSharp4x is recommended for anime
RTX Video Super Resolution Upscale
insanely fast
decent quality
FlashSVR + SeedVR2
experimental
Video upscale models that are more intricate than basic image upscaling models
haven't had great results for anime yet
takes a LOT longer
Saving last frame for manual extensions
mmaudio
added Audio combine node
combine audio from an existing video with the generated audio on top
generate nsfw audio with the nsfw model and then combine that video with another generated audio track from the base model for background noises
removed interpolation for easier and faster audio generation - you have the following options:
upload raw unupscaled video to MMAudio Video node and upscaled video to Combine video node
upload upscaled video to both nodes but lower custom_width and custom_height of the MMAudio video node to about half for faster generation and to prevent VRAM issues
upload raw video to both nodes and upscale afterwards
Inspired by https://civarchive.com/models/2137833
Following resources necessary (ComfyUI\models\mmaudio):
https://huggingface.co/Kijai/MMAudio_safetensors/resolve/main/mmaudio_synchformer_fp16.safetensors
Description
reworked subgraphs to show LoRAs from the outside
no more having to go into subgraphs to adjust LoRAs
adjust up to 6 LoRAs per subgraph
this feature uses subgraphs widgets which are only available on ComfyUI >0.4
added WanCutLastSlot node to the end of the FLF2V subgraphs to trimm the flashing latents
this should fix frame flashes at the end
color drift can still appear
lowering part length to 4s seems to help preventing color drift
made it easier to use additional anchor/end samples
resolution will also be more accurately calculated to keep the resolution of the samples the same
added Facedetailer to postprod
FAQ
Comments (13)
SyntaxError: Unexpected non-whitespace character after JSON at position 4 (line 1 column 5)，I noticed that some people in the comments section have the same problem as me: no nodes are showing up in red.
Can you see at which step/node the generation halts? I can't reproduce this error :( Which ComfyUI version are you running?
A quick screenshot of your full workflow could help identifying if you maybe missed a connection here or there.
@ggll It seems to be an issue with the FLF2V SVI nodes, the "ComfyUI-CustomNodes-Template" is not necessary to get the Workflow running, I don't have them installed either.
What seems to fix the issue is deleting the folder ComfyUI\custom_nodes\ComfyUI-Wan-SVI2Pro-FLF and the manually installing the node by cloning his github https://github.com/Well-Made/ComfyUI-Wan-SVI2Pro-FLF
@LastAssignment Thank you. It was indeed an issue with the FLF2V SVI nodes, and I have resolved it.
@ggll Awesome, good to know that it helped you!
Imported the SVI Extend 2.1 (Example) First Video (FLF2V) all nodes inside the subgraph is bypassed xD
And you can easily "unbypass" them when needed by just right clicking on the subgraph -> bypass. They are bypassed so I don't get errors thrown everytime I press generation on subgraphs that are not in use.
@LastAssignment Yeah! I meant, even tho it's bypassed, inside of the subgraph is bypassed.
@arimintzu Uh, I don't understand the issue. That is the whole point of bypassing subgraphs :) https://i.imgur.com/s03VkFd.mp4
@LastAssignment Nothing to worry then sir! Maybe something was off on my side... https://imgur.com/p4tkHFi
@arimintzu Oh yeah, that's weird and shouldn't happen even when unpacking the subgraph.
This is a well organized and very easy to use workflow. Thank you.
Btw, the individual part saving has some wrong connections in v2.1. Between split images and video combine nodes in the extend video subgraphs.
Oh, thank you for noticing! Gonna fix it asap.
Edit: Fixed version should be up at any moment.