5 Commits

Author SHA1 Message Date
Vladimir Mandic 56fabd4950 add joy-image-edit-plus
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2026-07-13 11:26:33 +02:00
Vladimir Mandic ec2e37ee6e enhance automated testing
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2026-06-03 09:27:34 +02:00
CalamitousFelicitousness bd60372cc5 refactor(pipelines): move per-arch transformer specs into packages
Specs for chrono, cogview, flux2_klein, glm, hunyuandit, hyimage, joy,
kandinsky, longcat, nucleus, ovis, pixart and prx lived module-level in
model_<arch>.py. Move each into pipelines/<arch>/__init__.py to match
the layout used by anima, bria, ernie, f_lite, lens, qwen, step1x and
vibe.

Each model_<arch>.py now imports its spec lazily inside the load
function, so the package only gets pulled in when that arch is actually
loaded (kandinsky 2.x never goes through native dispatch and stays
untouched).

Also drop the "without this spec..." crash paragraph from the new
package docstrings plus ernie/__init__.py and bria/__init__.py.
2026-05-31 00:24:33 +01:00
CalamitousFelicitousness e302518d73 feat(pipelines): wire native_spec for arches without from_single_file
CogView3+, CogView4, GLM-Image, HunyuanDiT, Joy, Kandinsky3 UNet,
PixArt, PRX. These classes lack from_single_file entirely; the UNET
dropdown fell through to cls.from_pretrained(local_file), which
decodes the .safetensors header as UTF-8 and crashes "is not a valid
JSON file".

TransformerSpec(cls=...) module-level in each model_<arch>.py.
Kandinsky3 also needs subfolder='unet' since it loads a UNet not a
transformer.
2026-05-31 00:24:33 +01:00
Vladimir Mandic 82e9745c65 add joyai-image-edit
Signed-off-by: Vladimir Mandic <mandic00@live.com>
2026-05-08 14:44:00 +02:00