`LoraUpDownModel` has no attribute `up_model`

[cppietime]

While attempting to use the extension with a Locon model as a Lora, trying to generate a prompt produces the following stacktrace:

Traceback (most recent call last):
  File "F:\StableDiffusion\stable-diffusion-webui\modules\call_queue.py", line 56, in f
    res = list(func(*args, **kwargs))
  File "F:\StableDiffusion\stable-diffusion-webui\modules\call_queue.py", line 37, in f
    res = func(*args, **kwargs)
  File "F:\StableDiffusion\stable-diffusion-webui\modules\txt2img.py", line 56, in txt2img
    processed = process_images(p)
  File "F:\StableDiffusion\stable-diffusion-webui\modules\processing.py", line 503, in process_images
    res = process_images_inner(p)
  File "F:\StableDiffusion\stable-diffusion-webui\modules\processing.py", line 642, in process_images_inner
    uc = get_conds_with_caching(prompt_parser.get_learned_conditioning, negative_prompts, p.steps, cached_uc)
  File "F:\StableDiffusion\stable-diffusion-webui\modules\processing.py", line 587, in get_conds_with_caching
    cache[1] = function(shared.sd_model, required_prompts, steps)
  File "F:\StableDiffusion\stable-diffusion-webui\modules\prompt_parser.py", line 140, in get_learned_conditioning
    conds = model.get_learned_conditioning(texts)
  File "F:\StableDiffusion\stable-diffusion-webui\repositories\stable-diffusion-stability-ai\ldm\models\diffusion\ddpm.py", line 669, in get_learned_conditioning
    c = self.cond_stage_model(c)
  File "F:\StableDiffusion\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1130, in _call_impl
    return forward_call(*input, **kwargs)
  File "F:\StableDiffusion\stable-diffusion-webui\modules\sd_hijack_clip.py", line 229, in forward
    z = self.process_tokens(tokens, multipliers)
  File "F:\StableDiffusion\stable-diffusion-webui\modules\sd_hijack_clip.py", line 254, in process_tokens
    z = self.encode_with_transformers(tokens)
  File "F:\StableDiffusion\stable-diffusion-webui\modules\sd_hijack_clip.py", line 302, in encode_with_transformers
    outputs = self.wrapped.transformer(input_ids=tokens, output_hidden_states=-opts.CLIP_stop_at_last_layers)
  File "F:\StableDiffusion\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1130, in _call_impl
    return forward_call(*input, **kwargs)
  File "F:\StableDiffusion\stable-diffusion-webui\venv\lib\site-packages\transformers\models\clip\modeling_clip.py", line 811, in forward
    return self.text_model(
  File "F:\StableDiffusion\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1130, in _call_impl
    return forward_call(*input, **kwargs)
  File "F:\StableDiffusion\stable-diffusion-webui\venv\lib\site-packages\transformers\models\clip\modeling_clip.py", line 721, in forward
    encoder_outputs = self.encoder(
  File "F:\StableDiffusion\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1130, in _call_impl
    return forward_call(*input, **kwargs)
  File "F:\StableDiffusion\stable-diffusion-webui\venv\lib\site-packages\transformers\models\clip\modeling_clip.py", line 650, in forward
    layer_outputs = encoder_layer(
  File "F:\StableDiffusion\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1130, in _call_impl
    return forward_call(*input, **kwargs)
  File "F:\StableDiffusion\stable-diffusion-webui\venv\lib\site-packages\transformers\models\clip\modeling_clip.py", line 379, in forward
    hidden_states, attn_weights = self.self_attn(
  File "F:\StableDiffusion\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1130, in _call_impl
    return forward_call(*input, **kwargs)
  File "F:\StableDiffusion\stable-diffusion-webui\venv\lib\site-packages\transformers\models\clip\modeling_clip.py", line 268, in forward
    query_states = self.q_proj(hidden_states) * self.scale
  File "F:\StableDiffusion\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1130, in _call_impl
    return forward_call(*input, **kwargs)
  File "F:\StableDiffusion\stable-diffusion-webui\extensions-builtin\Lora\lora.py", line 305, in lora_Linear_forward
    lora_apply_weights(self)
  File "F:\StableDiffusion\stable-diffusion-webui\extensions-builtin\Lora\lora.py", line 273, in lora_apply_weights
    self.weight += lora_calc_updown(lora, module, self.weight)
  File "F:\StableDiffusion\stable-diffusion-webui\extensions\a1111-sd-webui-locon\scripts\main.py", line 612, in lora_calc_updown
    updown = rebuild_weight(module, target)
  File "F:\StableDiffusion\stable-diffusion-webui\extensions\a1111-sd-webui-locon\scripts\main.py", line 536, in rebuild_weight
    up = module.up_model.weight.to(orig_weight.device, dtype=orig_weight.dtype)
AttributeError: 'LoraUpDownModule' object has no attribute 'up_model'

Checkpoint: anythingV3_fp16.ckpt [812cd9f9d9]

[KohakuBlueleaf]

Do you have any other extension for lora? Lot of them are not compatible of my extension

[cppietime]

My extensions are: The builtin:

• LORA
• LDSR
• ScuNET
• SwinIR
• prompt-bracket-checker

And:

• sd-webui-controlnet
• sd_civitai_extension

[KohakuBlueleaf]

What's your lora model? I may need the file that cause error to find where cause the bug

[cppietime]

I tried both versions of this model (NSFW): https://civitai.com/models/19987/beegirlz Both result in the error. After attempting to include this LORA in the prompt, all subsequent prompts result in the same error until restarting, even after removing the LORA

[Gourieff]

So am I, the same error, trying to use with this lora https://civitai.com/models/27615/delicate-armor?modelVersionId=33064

[KohakuBlueleaf]

@Gourieff I will suggest you to use new extension https://github.com/KohakuBlueleaf/a1111-sd-webui-lycoris