MiniMax-AI / MiniMax-AI/MiniMax-Music3

[Question] Is using a smaller text encoder possible?

Open
#5 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
No language data
Stars
896
Forks
84
PR merge metrics
No merged PRs in 30d

Description

Does anyone know if it is possible to use a smaller text encoder?
It is the bottleneck on my machine and I would assume that the actual music is generated by the diffusion model.
Maybe the text encoder could even be completely omitted if one knows how to prompt it correctly? At least I don't know how I would do that using ComfyUI.

I'd appreciate any feedback.

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

The issue names no files, tests, or entry points. Start by locating the text-encoder and diffusion-model integration, then determine whether a smaller encoder or no encoder is supported and document the feasibility and required configuration.

Written by the indexing model from the issue text.

Assessment

Tech stack
machine-learning
Domain
ai, machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.