* refactor ckpt_to_diffuser to allow converted pipeline to remain in memory
- This idea was introduced by Damian
- Note that although I attempted to use the updated HuggingFace module
pipelines/stable_diffusion/convert_from_ckpt.py, it was unable to
convert safetensors files for reasons I didn't dig into.
- Default is to extract EMA weights.
* add --ckpt_convert option to load legacy ckpt files as diffusers models
- not quite working - I'm getting artifacts and glitches in the
converted diffuser models
- leave as draft for time being
* do not include safety checker in converted files
* add ability to control which vae is used
API now allows the caller to pass an external VAE model to the
checkpoint conversion process. In this way, if an external VAE is
specified in the checkpoint's config stanza, this VAE will be used
when constructing the diffusers model.
Tested with both regular and inpainting 1.X models.
Not tested with SD 2.X models!
---------
Co-authored-by: Jonathan <34005131+JPPhoto@users.noreply.github.com>
Co-authored-by: Damian Stewart <null@damianstewart.com>
This PR changes the codeowner for the installer directory from
@tildebyte to @ebr due to the former's time commitments.
Further reorganization of the codeowners is pending.
1. only load triton on linux machines
2. require pip >= 23.0 so that editable installs can run without setup.py
3. model files default to SD-1.5, not 2.1
4. use diffusers model of inpainting rather than ckpt
5. selected a new set of initial models based on # of likes at huggingface
- launcher scripts are installed *before* the configure script runs,
so that if something goes wrong in the configure script, the user
can run invoke.{sh,bat} and get the option to re-run configure
- fixed typo in invoke.sh which misspelled name of invokeai-configure
Draft PRs are triggering actions on every commit (except
`test-invoke-pip.yml`).
I've added a conditional to each job to only run when the PR is not a
draft.
(maybe there is a reason we are running all applicable workflows on
draft PRs?)
- also remove conda related things
- rename `invoke` to `invokeai`
- rename `configure_invokeai` to `invokeai-configure`
- rename venv back to common `.venv` but add `--prompt InvokeAI`
- remove outdated information
A new infill method, **solid:** solid color. currently using middle
gray.
Fixes#2417
It seems like the runwayml inpainting model specifically expects those
masked areas to be blanked out like this.
I haven't tried the SD 2.0 inpainting model with it yet.