Image-Text-to-Video
Diffusers
Safetensors
MiniMaxH3ModularPipeline
text-to-video
image-to-video
video-to-video
text-to-audio-video
image-to-audio-video
image-text-to-audio-video
video-to-audio-video
audio-to-audio-video
audio-video-generation
multimodal
synchronized-audio-video
reference-to-audio-video
sparse-attention inference
#48
by mzbac - opened
will it be released soon? currently the inference speed on Mac is very bad due to weak compute and the full self-attention make it unusable ..
get better hardware.
also you can always use sageattention
Was rainfusion attention used to train this model, or MSA? Or some kind of VSA?