workflow for AI music video "Kali"
created a month ago
upscale
video
lora
44 nodes

634

140

Credits
latentdream on civitai provided the underlying workflow I tweaked
Outputs
Description

You can see the NSFW version of "Kali" video here https://www.youtube.com/watch?v=59U-kfgLQYM&list=PLVCJTJhkunkQSY_QZBMFclmB9-LXOi8WY&index=4

Equipment used for making AI footage: Hunyuan GGUF model on Comfyui running on a Windows 10 PC with 3060 RTX 12GB VRAM. for most of it. (Kling and Minimax have featured in a few shots at the end but mostly it is home made).

Then it was all put together using Shotcut and Davinci. I ran out of time for color grading.

It took 5 days, which is where I set my limit on how long to spend on these currently. Most of that time is redoing stuff that doesnt work. The uncensored version of this will be available via my website on another streaming service (YT wont let body parts show, and I already have a strike for other crimes) probably vimeo, tbd.

The mp4 clips will also contain workflows that might be slightly differently tweaked and I included a second workflow from my folder. I dont recall which I used for what so muck about and see what works.

Follow my above linked YT channel for future workflows and videos

Built-in nodes
SamplerCustomAdvanced
BasicGuider
ModelSamplingSD3
FluxGuidance
BetaSamplingScheduler
EmptyHunyuanLatentVideo
RandomNoise
Custom nodes
ImageUpscaleWithModel
ImageScale
FILM VFI
UpscaleModelLoader
MathExpression|pysssss
GetImageSize+
LatentUpscaleBy
VAEDecodeTiled
BasicScheduler
VHS_VideoCombine
VHS_LoadVideo
UNETLoader
KSamplerSelect
VAELoader
LoraLoaderModelOnly
DualCLIPLoader
UnetLoaderGGUF
CLIPTextEncode
Custom files
new

These are separate files that the creator has uploaded for this workflow.

2 - HUN_BASIC_V2V-MBEDIT-4.json

0
0
0
0