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
Only MiniMax-H3 can do !
#38
by sunnyboxs - opened
A short Chinese video generated by MiniMax-H3. The results are incredible, especially the character expressions, emotional details, and overall visual impact.
In my opinion, MiniMax-H3 is currently one of the best open-source models.
Among open-source models, few can achieve this level of quality.
Of course, this is only my personal opinion based on my own experience. 😆