Text-to-Video
MiniMax H3
Safetensors
lora
adapter
comfyui
reference-to-video
audio-video
synchronized-audio
few-step
turbo
accelerated-inference
hyperflow
lightx2v
dynamic-rank
svd
bfloat16
pruned-model
curve-form
Instructions to use drbaph/MiniMax-H3-Turbo-Lora-ComfyUI with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Inference
- Notebooks
- Google Colab
- Kaggle
Older version currently working better
#2
by cushycrux - opened
The 500 step version gives me either bad audio (4 steps) or a deep fried image (8 steps). The older version works well on audio and image at 8-10 steps. It's probably the working sigma shift, we have to find?
The 500 step version gives me either bad audio (4 steps) or a deep fried image (8 steps). The older version works well on audio and image at 8-10 steps. It's probably the working sigma shift, we have to find?
use the custom node and the workflow from the below repo for now until comfyui merge kijai's PR
drbaph changed discussion status to closed