lllyasviel / lllyasviel/stable-diffusion-webui-forge

Support For T5XXL Unchained

Open
#2,758 6 comments 2 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
13k
Forks
1.7k
PR merge metrics
No merged PRs in 30d

Description

Someone made an updated t5 with new vocab.

https://github.com/Kaoru8/T5XXL-Unchained

https://github.com/kohya-ss/sd-scripts/issues/1987

https://huggingface.co/Kaoru8/T5XXL-Unchained/tree/main

This is a fork of the T5-XXL encoder that uses an extended tokenizer to facilitate Flux uncensoring and offer other benefits to tokenization. More info is on the project's [GitHub page](https://github.com/Kaoru8/T5XXL-Unchained).

As of 17.3.2025, third-party tools like [ComfyUI](https://github.com/comfyanonymous/ComfyUI) and [Kohya's training scripts](https://github.com/kohya-ss/sd-scripts) don't yet support the new architecture. Their respective developers have been notified of this release, and may or may not choose to officially support it in a future update to their code. In the meantime, temporary patches for both tools are available in the GitHub repo linked above.

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

No repository files, tests, or entry points are named. Start by reviewing the T5XXL-Unchained repository, its Hugging Face model files, and the linked sd-scripts issue to determine the required architecture changes; done means stable-diffusion-webui-forge can load and use the updated encoder.

Written by the indexing model from the issue text.

Assessment

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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.