thu-ml / thu-ml/TurboDiffusion

TurboWan2.1 only apply rCM

Open
#87 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
3.7k
Forks
277
Avg merge
2h 57m
Merged PRs (30d)
2

Description

Hi all,

As the document illustrated, TurboDiffusion primarily uses SageAttention, SLA for attention acceleration, and rCM for timestep distillation.
Is it possible we can only apply rCM and obtain the model without changing its structure?

If so, is there any pretrained model for TurboWan2.1 only apply rCM?

Thanks

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 asks whether TurboWan2.1 can use only rCM without changing its structure and whether such a pretrained model exists. Start by reviewing the TurboDiffusion documentation and model entry points for TurboWan2.1, then determine whether the request has an existing implementation path; done means a documented answer or a clearly scoped implementation plan.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning, performance
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.