Complete Kohya LoRA conversion for Qwen and Z-Image (#14080)
* Fix Kohya LoRA conversion for Z-Image modules whose names contain underscores
_convert_non_diffusers_z_image_lora_to_diffusers reverses Kohya's `.`->`_`
flattening with a blanket `_`->`.` split, guarded only by a small
protected-n-gram list (attention to_q/k/v/out, feed_forward) plus post-hoc
fixes for context_refiner/noise_refiner. Z-Image's other modules whose names
contain underscores were over-split: all_final_layer, all_x_embedder,
adaLN_modulation, cap_embedder and t_embedder came out as all.final.layer,
adaLN.modulation, ... and failed to load with "unexpected keys".
Extend the existing dot->underscore post-normalization to re-merge these
names, so Kohya (lora_unet_) Z-Image LoRAs load.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
* Fix Kohya LoRA conversion for Qwen top-level (non-block) modules
_convert_non_diffusers_qwen_lora_to_diffusers's convert_key hardcodes the
transformer_blocks prefix and assumes every lora_unet_ key lives under a block:
it strips a transformer_blocks_ prefix and re-prepends transformer_blocks.,
which collapses the top-level modules (img_in, txt_in, proj_out, norm_out.linear,
time_text_embed.timestep_embedder.linear_1/2) onto each other. They end up as
transformer_blocks..weight / ...a.down.weight and trip the 'state_dict should be
empty' guard.
Resolve these six modules via an explicit flattened->dotted map before the block
logic runs, preserving the .lora_down/.lora_up/.alpha suffix, so Kohya (lora_unet_)
Qwen LoRAs load.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>
