InvokeAI/invokeai/app
blessedcoolant dc1681a0de fix: clip vision model auto param
Setting to 'auto' works only for InvokeAI config and auto detects the SD model but will override if user explicitly sets it. If auto used with checkpoint models, we raise an error. Checkpoints will always need to set to non-auto.
2024-04-03 12:40:11 +05:30
..
api [mm] Do not write diffuser model to disk when convert_cache set to zero (#6072) 2024-03-29 16:11:08 -04:00
assets/images tweaks in response to psychedelicious review of PR 2023-07-26 15:27:04 +10:00
invocations fix: clip vision model auto param 2024-04-03 12:40:11 +05:30
services fix(config): handle windows paths in invokeai.yaml migration for legacy_conf_dir 2024-04-02 08:06:59 -04:00
shared tidy(nodes): move all field things to fields.py 2024-03-01 10:42:33 +11:00
util feat(mm): move HF token helper to route 2024-03-20 15:05:25 +11:00
__init__.py fix: make invocation_context.py accessible to mkdocs 2024-03-01 10:42:33 +11:00
api_app.py Check for cuDNN version compatibility issues on startup. Prior to this check, the app would silently run with ~50% performance degradation caused by a cuDNN version mismatch. 2024-03-28 07:32:06 +11:00
run_app.py feat: single app entrypoint with CLI arg parsing 2024-03-19 09:24:28 +11:00