Skip to content

the training details of minimax h3 model #1585

Description

@xinjiu612

I am currently training a LoRA for the MiniMax-H3 FL2VA model. However, after training on 10k videos, both the video clarity and temporal consistency have noticeably degraded. I am unsure if this issue stems from the prompts, the dataset, or certain training parameters.
I noticed that DiffSynth open-sourced a LoRA checkpoint (https://modelscope.ai/models/DiffSynth-Studio/MiniMax-H3-LoRA-LineartAnime). Could you share the specific training details for this model? I am particularly interested in the prompt design (how to align with the original MiniMax prompt templates), training steps, batch size, timestep shift, learning rate, and LoRA rank. I would love to reference these details to improve my training quality and consistency. Thank you!

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions