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
LoRA Training with MiniMax H3 - Question
#43
by Tomcat2048 - opened
How easy is it to train LoRAs for this model? Have training weights been released? Can it be trained using a consumer level card (RTX 5090 for example)?
Thanks for this amazing new model by the way - early test results on my machine are very promising compared to any other Open model currently out there!
I will publish minmax h3 fp8 in next few days ,could be running on single card for 5090 (vllm omni) and need at least 60 gb Memory for offloading