gokaygokay/Light-Fix-Kontext-Dev-LoRA · Cannot use in diffusers

When I try to load lora in diffusers,errors :
File /opt/conda/envs/kontext/lib/python3.10/site-packages/diffusers/loaders/lora_conversion_utils.py:917, in _convert_kohya_flux_lora_to_diffusers(state_dict)
    914 if has_mixture:
    915     return _convert_mixture_state_dict_to_diffusers(state_dict)
--> 917 return _convert_sd_scripts_to_ai_toolkit(state_dict)

File /opt/conda/envs/kontext/lib/python3.10/site-packages/diffusers/loaders/lora_conversion_utils.py:629, in _convert_kohya_flux_lora_to_diffusers.<locals>._convert_sd_scripts_to_ai_toolkit(sds_sd)
    611     assign_remaining_weights(
    612         [
    613             (
   (...)
    624         sds_sd,
    625     )
    627 if any("final_layer" in k for k in sds_sd):
    628     # Notice the swap in processing for "final_layer".
--> 629     assign_remaining_weights(
    630         [
    631             (
    632                 "norm_out.linear.{lora_key}.weight",
    633                 "lora_unet_final_layer_adaLN_modulation_1.{orig_lora_key}.weight",
    634                 swap_scale_shift,
    635             ),
    636             ("proj_out.{lora_key}.weight", "lora_unet_final_layer_linear.{orig_lora_key}.weight", None),
    637         ],
    638         sds_sd,
    639     )
    641 remaining_keys = list(sds_sd.keys())
    642 te_state_dict = {}

File /opt/conda/envs/kontext/lib/python3.10/site-packages/diffusers/loaders/lora_conversion_utils.py:555, in _convert_kohya_flux_lora_to_diffusers.<locals>._convert_sd_scripts_to_ai_toolkit.<locals>.assign_remaining_weights(assignments, source)
    553 target_key = target_fmt.format(lora_key=lora_key)
    554 source_key = source_fmt.format(orig_lora_key=orig_lora_key)
--> 555 value = source.pop(source_key)
    556 if transform:
    557     value = transform(value)

KeyError: 'lora_unet_final_layer_adaLN_modulation_1.lora_down.weight'
Seems not a correct koyha format, anyone konw how to resolve it? many thanks!