fix(model-manager): add Z-Image LoRA/DoRA detection support

[Pfannkuchensack]

Summary

Fix Z-Image LoRA/DoRA model detection failing during installation.

Z-Image LoRAs use different key patterns than SD/SDXL LoRAs. The base LoRA_LyCORIS_Config_Base class only checked for key suffixes like lora_A.weight and lora_B.weight, but Z-Image LoRAs (especially those in DoRA format) use:

• lora_down.weight / lora_up.weight (standard LoRA format)
• dora_scale (DoRA weight decomposition)

This PR overrides _validate_looks_like_lora in LoRA_LyCORIS_ZImage_Config to recognize Z-Image specific patterns:

• Keys starting with diffusion_model.layers. (Z-Image S3-DiT architecture)
• Keys ending with lora_down.weight, lora_up.weight, lora_A.weight, lora_B.weight, or dora_scale

Related Issues / Discussions

Fixes installation of Z-Image LoRAs trained with DoRA (Weight-Decomposed Low-Rank Adaptation).

QA Instructions

1. Download a Z-Image LoRA in DoRA format (e.g., from CivitAI with keys like diffusion_model.layers.X.attention.to_k.lora_down.weight)
2. Try to install the LoRA via Model Manager
3. Verify the model is recognized as a Z-Image LoRA and installs successfully
4. Verify the LoRA can be applied when generating with Z-Image

Merge Plan

Standard merge, no special considerations.

Checklist

• The PR has a short but descriptive title, suitable for a changelog
• Tests added / updated (if applicable)
• ❗Changes to a redux slice have a corresponding migration
• Documentation added / updated (if applicable)
• Updated What's New copy (if doing a release after this PR)

[Pfannkuchensack]

Tested with https://civitai.com/models/2240502/zit-cutout-dress-01

[nphSi]

My Onetrainer trained loras install now but give error on gen.

[2025-12-27 09:00:29,105]::[InvokeAI]::ERROR --> Error while invoking session 5c876236-38b2-4e92-a340-121b4c29df3b, invocation e84246fe-7d29-43e9-90bf-603e2e641ccb (z_image_text_encoder): Unsupported lora format: dict_keys(['to_k
.alpha', 'to_q.alpha', 'to_v.alpha'])
[2025-12-27 09:00:29,105]::[InvokeAI]::ERROR --> Traceback (most recent call last):
File "C:\Invoke.venv\Lib\site-packages\invokeai\app\services\session_processor\session_processor_default.py", line 130, in run_node
output = invocation.invoke_internal(context=context, services=self._services)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Invoke.venv\Lib\site-packages\invokeai\app\invocations\baseinvocation.py", line 244, in invoke_internal
output = self.invoke(context)
^^^^^^^^^^^^^^^^^^^^
File "C:\Invoke.venv\Lib\site-packages\torch\utils_contextlib.py", line 116, in decorate_context
return func(*args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "C:\Invoke.venv\Lib\site-packages\invokeai\app\invocations\z_image_text_encoder.py", line 59, in invoke
prompt_embeds = self._encode_prompt(context, max_seq_len=Z_IMAGE_MAX_SEQ_LEN)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Invoke.venv\Lib\site-packages\invokeai\app\invocations\z_image_text_encoder.py", line 83, in _encode_prompt
exit_stack.enter_context(
File "C:\Users\xxx\AppData\Roaming\uv\python\cpython-3.12.9-windows-x86_64-none\Lib\contextlib.py", line 526, in enter_context
result = _enter(cm)
^^^^^^^^^^
File "C:\Users\xxx\AppData\Roaming\uv\python\cpython-3.12.9-windows-x86_64-none\Lib\contextlib.py", line 137, in enter
return next(self.gen)
^^^^^^^^^^^^^^
File "C:\Invoke.venv\Lib\site-packages\invokeai\backend\patches\layer_patcher.py", line 39, in apply_smart_model_patches
for patch, patch_weight in patches:
^^^^^^^
File "C:\Invoke.venv\Lib\site-packages\invokeai\app\invocations\z_image_text_encoder.py", line 190, in _lora_iterator
lora_info = context.models.load(lora.lora)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Invoke.venv\Lib\site-packages\invokeai\app\services\shared\invocation_context.py", line 392, in load
return self._services.model_manager.load.load_model(model, submodel_type)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Invoke.venv\Lib\site-packages\invokeai\app\services\model_load\model_load_default.py", line 71, in load_model
).load_model(model_config, submodel_type)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Invoke.venv\Lib\site-packages\invokeai\backend\model_manager\load\load_default.py", line 57, in load_model
cache_record = self._load_and_cache(model_config, submodel_type)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Invoke.venv\Lib\site-packages\invokeai\backend\model_manager\load\load_default.py", line 78, in _load_and_cache
loaded_model = self._load_model(config, submodel_type)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Invoke.venv\Lib\site-packages\invokeai\backend\model_manager\load\model_loaders\lora.py", line 137, in _load_model
model = lora_model_from_z_image_state_dict(state_dict=state_dict, alpha=None)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Invoke.venv\Lib\site-packages\invokeai\backend\patches\lora_conversions\z_image_lora_conversion_utils.py", line 117, in lora_model_from_z_image_state_dict
layer = any_lora_layer_from_state_dict(values)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "C:\Invoke.venv\Lib\site-packages\invokeai\backend\patches\layers\utils.py", line 35, in any_lora_layer_from_state_dict
raise ValueError(f"Unsupported lora format: {state_dict.keys()}")
ValueError: Unsupported lora format: dict_keys(['to_k.alpha', 'to_q.alpha', 'to_v.alpha'])

Lora:
https://huggingface.co/nphSi/Z-Image-Lora/blob/main/ZIdT%20Ashley%20Williams%20(vrtlAshleyWilliams).safetensors

[Pfannkuchensack]

Can you try again with the now made changes? @nphSi

[nphSi]

Can you try again with the now made changes? @nphSi

That was fast 👍 - Works now. Thanks!!