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
No official trainer? We open-sourced a working fine-tuning pipeline for H3
#27
by ka1029 - opened
We got supervised fine-tuning working on H3 π ~150-line trainer + latent caching on top of the official Diffusers integration. Wrote up the conventions that silently break training (timestep = 1βΟ, data-ward velocity, dual shifted schedules). Feedback welcome:
https://github.com/IAmIronMan42/MiniMax-H3-FineTuning
When fine-tuning a distilled model, can we achieve the expected results? Dose it degrade the performance of the distilled model? And will image blurriness occur after training?