mirror of
https://github.com/invoke-ai/InvokeAI
synced 2024-08-30 20:32:17 +00:00
2f9dcd7906
There are actually two Stable Diffusion v2 legacy checkpoint configurations: 1) "epsilon" prediction type for Stable Diffusion v2 Base 2) "v-prediction" type for Stable Diffusion v2-768 This commit adds the configuration file needed for epsilon prediction type models as well as the UI that prompts the user to select the appropriate configuration file when the code can't do so automatically. |
||
---|---|---|
.. | ||
.husky | ||
.yarn/releases | ||
dist | ||
patches | ||
public/locales | ||
src | ||
__init__.py | ||
.babelrc | ||
.eslintignore | ||
.eslintrc.js | ||
.gitignore | ||
.prettierignore | ||
.prettierrc.js | ||
.yarnrc | ||
.yarnrc.yml | ||
favicon.ico | ||
index.d.ts | ||
index.html | ||
package.json | ||
README.md | ||
stats.html | ||
tsconfig.json | ||
tsconfig.node.json | ||
vite.config.ts | ||
yarn.lock |
InvokeAI UI dev setup
The UI is in invokeai/frontend
.
Environment set up
Install node (includes npm) and yarn.
From invokeai/frontend/
run yarn install --immutable
to get everything set up.
Dev
- Start the dev server:
yarn dev
- Start the InvokeAI UI per usual:
invokeai --web
- Point your browser to the dev server address e.g.
http://localhost:5173/
To build for dev: yarn build-dev
To build for production: yarn build