mlc-ai / mlc-ai/web-stable-diffusion

How to use SD 2.1?

Open
#31 3 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Jupyter Notebook
Stars
3.7k
Forks
238
PR merge metrics
No merged PRs in 30d

Description

Excited to see support for Stable Diffusion v2.1 in https://github.com/mlc-ai/web-stable-diffusion/pull/29. As I don't have the hardware to build this, would it be possible to run the GitHub Action to create the needed files?

I am not sure I understand what would need to change in order to move from v1.5 to v2.1. I imagine I would need a different .wasm file and tokenizer.json, as well as to point cacheUrl somewhere else.

Any help would be much appreciated as I would love to see the quality of images with the newer model. Thanks!

FYI: @masahi, @spectrometerHBH & @tqchen

PS: Sorry for this issue sounding so similar to https://github.com/mlc-ai/web-llm/issues/89, but it's the same asks so I figured it didn't need much changing.

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

Read PR #29 first to understand the existing Stable Diffusion v2.1 support. Then inspect the GitHub Action and the referenced .wasm, tokenizer.json, and cacheUrl setup to determine how the v1.5 usage flow should change. Done means the needed files can be generated and the v2.1 usage steps are clear.

Written by the indexing model from the issue text.

Assessment

Tech stack
github-actions, wasm
Domain
machine-learning, web-dev
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.