blazing fast, only 1 minute 10 second generating 5 second clip in 0.4 mp resolution.
use this model from huggingface: https://huggingface.co/MATLOWAI/minimax-h3-fused-turbo-int8-convrot/tree/main/diffusion_models
change manualsigmas according your preference steps:
4 steps:
0.9999166, 0.9728326, 0.9230769, 0.8, 0.0
6 steps:
0.9999166, 0.9868421, 0.9638554, 0.9230769, 0.8695652, 0.8, 0.0
8 steps:
1.0, 0.9882352941, 0.9729729730, 0.9523809524, 0.9230769231, 0.8780487805, 0.8, 0.6315789474, 0.0
must use sage attention and triton for faster generation, install this if you have issue installing sage attention and triton in comfy ui: https://github.com/DazzleML/comfyui-triton-and-sageattention-installer
Description
better model
FAQ
Comments (3)
I see the prompt format you have used is different from the one provided by the Minimax H3 prompt guide. Why?
This works ok. I got it to do image to video but had to use a lightning lora to make up for the too few steps it does. Seems the resolution table is slightly different. The animation seems a little weaker than my old setup but it's definitely faster.
Useless for any practice quality.
Incompatible with latent upscale - slower than int8 convrot with turbo lora.
No i2v and ref2v.