InvokeAI/invokeai
Lincoln Stein 4e0b5d85ba convert custom VAEs into diffusers
- When a legacy checkpoint model is loaded via --convert_ckpt and its
  models.yaml stanza refers to a custom VAE path (using the 'vae:'
  key), the custom VAE will be converted and used within the diffusers
  model. Otherwise the VAE contained within the legacy model will be
  used.

- Note that the heuristic_import() method, which imports arbitrary
  legacy files on disk and URLs, will continue to default to the
  the standard stabilityai/sd-vae-ft-mse VAE. This can be fixed after
  the fact by editing the models.yaml stanza using the Web or CLI
  UIs.

- Fixes issue #2917
2023-03-23 13:14:19 -04:00
..
app fix(nodes): fix step_callback + fast latents generation 2023-03-16 20:03:08 +11:00
assets Various fixes 2023-01-30 18:42:17 -05:00
backend convert custom VAEs into diffusers 2023-03-23 13:14:19 -04:00
configs support both epsilon and v-prediction v2 inference 2023-03-05 22:51:40 -05:00
frontend convert custom VAEs into diffusers 2023-03-23 13:14:19 -04:00
version fix issue with invokeai.version 2023-03-03 01:34:38 -05:00
__init__.py Various fixes 2023-01-30 18:42:17 -05:00
README CODEOWNERS coarse draft 2023-03-03 14:36:43 -05:00

Organization of the source tree:

app -- Home of nodes invocations and services
assets -- Images and other data files used by InvokeAI
backend -- Non-user facing libraries, including the rendering
	core.
configs -- Configuration files used at install and run times
frontend -- User-facing scripts, including the CLI and the WebUI
version -- Current InvokeAI version string, stored
	in version/invokeai_version.py