Hunyuan fp8 with fast lora for "I've Got All That You Need" music video.
created a month ago
video
lora
29 nodes

1.9k

267

Credits
adapted from workflow suggested on https://www.youtube.com/@BenjisAIPlayground
Outputs
example image output 0 for workflow.
example image output 1 for workflow.
example image output 2 for workflow.
example image output 3 for workflow.
example image output 4 for workflow.
example image output optimized_comfy_workflows_user_uploads/67f1b649-4c3c-47f6-88b7-e596bc19fcf2/assets/stills 1.webp for workflow.
Description

Workflow used on music video "I've Got All That You Need" by Mark DK Berry (EDM Music video)

(The video example I used this on will be available on my YT channel shortly If it is SFW enough that they release it - https://www.youtube.com/watch?v=qaWW0JvD7Cg&list=PLVCJTJhkunkQSY_QZBMFclmB9-LXOi8WY

otherwise check my website www.MarkDKBerry.com for links to where it ends up. the NSFW version too.)

Equipment used for making AI footage: Hunyuan fp8 model with Fastvideo lora & tea cache on Comfyui running on a Windows 10 PC with 3060 RTX 12GB VRAM. Then it was all put together using Davinci. I ran out of time for color grading.

I applied a new workflow for this video, and it gave me better quality and was faster. This was due to switching out the Hunyuan model and lowering the steps while keeping the Fastvideo lora in. I also used Tea cache. I decided to set it in a different aspect ratio more suitable to phone devices this time too.

It took about 4 days total, but I didn't have time to give it a color grading, which I normally would if I set a 5 day limit on a project.

The uncensored version of this song edit 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) the uncensored veriosn is up on my vimeo account.

Follow and support me on my social media accounts as I continue this journey into AI music video creation. I hope you enjoyed this one.

markdkberry.com

markdkberry.bandcamp.com

IG @ markdkberry

X @ markdkberry

#aimusicvideo #ai #music #musicvideo #markdkberry #garage #edm

Built-in nodes
ModelSamplingSD3
FluxGuidance
RandomNoise
EmptyHunyuanLatentVideo
SamplerCustomAdvanced
BetaSamplingScheduler
BasicGuider
Custom nodes
VAELoader
VAEDecode
DualCLIPLoader
UNETLoader
UnetLoaderGGUF
HyVideoCFG
VAEDecodeTiled
TeaCacheHunyuanVideoSampler
CLIPTextEncode
VHS_VideoCombine
HunyuanVideoLoraLoader
LoraLoaderModelOnly
KSamplerSelect
BasicScheduler
3
0
0
0