The LoRA trained using train_text_to_image_lora.py cannot be used in ComfyUI.

[llm8047]

Describe the bug

The LoRA trained using train_text_to_image_lora.py cannot be used in ComfyUI.
The error message is as follows:
CLIP model load device: cuda:0, offload device: cpu, current: cpu, dtype: torch.float16
Requested to load SD1ClipModel
loaded completely 9.5367431640625e+25 235.84423828125 True
lora key not loaded: unet.down_blocks.0.attentions.0.transformer_blocks.0.attn1.to_k.lora.down.weight
lora key not loaded: unet.down_blocks.0.attentions.0.transformer_blocks.0.attn1.to_k.lora.up.weight
lora key not loaded: unet.down_blocks.0.attentions.0.transformer_blocks.0.attn1.to_out.0.lora.down.weight
lora key not loaded: unet.down_blocks.0.attentions.0.transformer_blocks.0.attn1.to_out.0.lora.up.weight
lora key not loaded: unet.down_blocks.0.attentions.0.transformer_blocks.0.attn1.to_q.lora.down.weight
lora key not loaded: unet.down_blocks.0.attentions.0.transformer_blocks.0.attn1.to_q.lora.up.weight
lora key not loaded: unet.down_blocks.0.attentions.0.transformer_blocks.0.attn1.to_v.lora.down.weight
lora key not loaded: unet.down_blocks.0.attentions.0.transformer_blocks.0.attn1.to_v.lora.up.weight
lora key not loaded: unet.down_blocks.0.attentions.0.transformer_blocks.0.attn2.to_k.lora.down.weight
lora key not loaded: unet.down_blocks.0.attentions.0.transformer_blocks.0.attn2.to_k.lora.up.weight
lora key not loaded: unet.down_blocks.0.attentions.0.transformer_blocks.0.attn2.to_out.0.lora.down.weight
lora key not loaded: unet.down_blocks.0.attentions.0.transformer_blocks.0.attn2.to_out.0.lora.up.weight
lora key not loaded: unet.down_blocks.0.attentions.0.transformer_blocks.0.attn2.to_q.lora.down.weight
lora key not loaded: unet.down_blocks.0.attentions.0.transformer_blocks.0.attn2.to_q.lora.up.weight
lora key not loaded: unet.down_blocks.0.attentions.0.transformer_blocks.0.attn2.to_v.lora.down.weight
lora key not loaded: unet.down_blocks.0.attentions.0.transformer_blocks.0.attn2.to_v.lora.up.weight
lora key not loaded: unet.down_blocks.0.attentions.1.transformer_blocks.0.attn1.to_k.lora.down.weight
lora key not loaded: unet.down_blocks.0.attentions.1.transformer_blocks.0.attn1.to_k.lora.up.weight
lora key not loaded: unet.down_blocks.0.attentions.1.transformer_blocks.0.attn1.to_out.0.lora.down.weight
lora key not loaded: unet.down_blocks.0.attentions.1.transformer_blocks.0.attn1.to_out.0.lora.up.weight
lora key not loaded: unet.down_blocks.0.attentions.1.transformer_blocks.0.attn1.to_q.lora.down.weight
lora key not loaded: unet.down_blocks.0.attentions.1.transformer_blocks.0.attn1.to_q.lora.up.weight
lora key not loaded: unet.down_blocks.0.attentions.1.transformer_blocks.0.attn1.to_v.lora.down.weight
lora key not loaded: unet.down_blocks.0.attentions.1.transformer_blocks.0.attn1.to_v.lora.up.weight
lora key not loaded: unet.down_blocks.0.attentions.1.transformer_blocks.0.attn2.to_k.lora.down.weight
lora key not loaded: unet.down_blocks.0.attentions.1.transformer_blocks.0.attn2.to_k.lora.up.weight
lora key not loaded: unet.down_blocks.0.attentions.1.transformer_blocks.0.attn2.to_out.0.lora.down.weight
lora key not loaded: unet.down_blocks.0.attentions.1.transformer_blocks.0.attn2.to_out.0.lora.up.weight
lora key not loaded: unet.down_blocks.0.attentions.1.transformer_blocks.0.attn2.to_q.lora.down.weight
lora key not loaded: unet.down_blocks.0.attentions.1.transformer_blocks.0.attn2.to_q.lora.up.weight
lora key not loaded: unet.down_blocks.0.attentions.1.transformer_blocks.0.attn2.to_v.lora.down.weight
lora key not loaded: unet.down_blocks.0.attentions.1.transformer_blocks.0.attn2.to_v.lora.up.weight
lora key not loaded: unet.down_blocks.1.attentions.0.transformer_blocks.0.attn1.to_k.lora.down.weight
lora key not loaded: unet.down_blocks.1.attentions.0.transformer_blocks.0.attn1.to_k.lora.up.weight
lora key not loaded: unet.down_blocks.1.attentions.0.transformer_blocks.0.attn1.to_out.0.lora.down.weight
lora key not loaded: unet.down_blocks.1.attentions.0.transformer_blocks.0.attn1.to_out.0.lora.up.weight
lora key not loaded: unet.down_blocks.1.attentions.0.transformer_blocks.0.attn1.to_q.lora.down.weight
lora key not loaded: unet.down_blocks.1.attentions.0.transformer_blocks.0.attn1.to_q.lora.up.weight
lora key not loaded: unet.down_blocks.1.attentions.0.transformer_blocks.0.attn1.to_v.lora.down.weight
lora key not loaded: unet.down_blocks.1.attentions.0.transformer_blocks.0.attn1.to_v.lora.up.weight
lora key not loaded: unet.down_blocks.1.attentions.0.transformer_blocks.0.attn2.to_k.lora.down.weight
lora key not loaded: unet.down_blocks.1.attentions.0.transformer_blocks.0.attn2.to_k.lora.up.weight
lora key not loaded: unet.down_blocks.1.attentions.0.transformer_blocks.0.attn2.to_out.0.lora.down.weight
lora key not loaded: unet.down_blocks.1.attentions.0.transformer_blocks.0.attn2.to_out.0.lora.up.weight
lora key not loaded: unet.down_blocks.1.attentions.0.transformer_blocks.0.attn2.to_q.lora.down.weight
lora key not loaded: unet.down_blocks.1.attentions.0.transformer_blocks.0.attn2.to_q.lora.up.weight
lora key not loaded: unet.down_blocks.1.attentions.0.transformer_blocks.0.attn2.to_v.lora.down.weight
lora key not loaded: unet.down_blocks.1.attentions.0.transformer_blocks.0.attn2.to_v.lora.up.weight
lora key not loaded: unet.down_blocks.1.attentions.1.transformer_blocks.0.attn1.to_k.lora.down.weight
lora key not loaded: unet.down_blocks.1.attentions.1.transformer_blocks.0.attn1.to_k.lora.up.weight
lora key not loaded: unet.down_blocks.1.attentions.1.transformer_blocks.0.attn1.to_out.0.lora.down.weight
lora key not loaded: unet.down_blocks.1.attentions.1.transformer_blocks.0.attn1.to_out.0.lora.up.weight
lora key not loaded: unet.down_blocks.1.attentions.1.transformer_blocks.0.attn1.to_q.lora.down.weight
lora key not loaded: unet.down_blocks.1.attentions.1.transformer_blocks.0.attn1.to_q.lora.up.weight
lora key not loaded: unet.down_blocks.1.attentions.1.transformer_blocks.0.attn1.to_v.lora.down.weight
lora key not loaded: unet.down_blocks.1.attentions.1.transformer_blocks.0.attn1.to_v.lora.up.weight
lora key not loaded: unet.down_blocks.1.attentions.1.transformer_blocks.0.attn2.to_k.lora.down.weight
lora key not loaded: unet.down_blocks.1.attentions.1.transformer_blocks.0.attn2.to_k.lora.up.weight
lora key not loaded: unet.down_blocks.1.attentions.1.transformer_blocks.0.attn2.to_out.0.lora.down.weight
lora key not loaded: unet.down_blocks.1.attentions.1.transformer_blocks.0.attn2.to_out.0.lora.up.weight
lora key not loaded: unet.down_blocks.1.attentions.1.transformer_blocks.0.attn2.to_q.lora.down.weight
lora key not loaded: unet.down_blocks.1.attentions.1.transformer_blocks.0.attn2.to_q.lora.up.weight
lora key not loaded: unet.down_blocks.1.attentions.1.transformer_blocks.0.attn2.to_v.lora.down.weight
lora key not loaded: unet.down_blocks.1.attentions.1.transformer_blocks.0.attn2.to_v.lora.up.weight
lora key not loaded: unet.down_blocks.2.attentions.0.transformer_blocks.0.attn1.to_k.lora.down.weight
lora key not loaded: unet.down_blocks.2.attentions.0.transformer_blocks.0.attn1.to_k.lora.up.weight
lora key not loaded: unet.down_blocks.2.attentions.0.transformer_blocks.0.attn1.to_out.0.lora.down.weight
lora key not loaded: unet.down_blocks.2.attentions.0.transformer_blocks.0.attn1.to_out.0.lora.up.weight
lora key not loaded: unet.down_blocks.2.attentions.0.transformer_blocks.0.attn1.to_q.lora.down.weight
lora key not loaded: unet.down_blocks.2.attentions.0.transformer_blocks.0.attn1.to_q.lora.up.weight
lora key not loaded: unet.down_blocks.2.attentions.0.transformer_blocks.0.attn1.to_v.lora.down.weight
lora key not loaded: unet.down_blocks.2.attentions.0.transformer_blocks.0.attn1.to_v.lora.up.weight
lora key not loaded: unet.down_blocks.2.attentions.0.transformer_blocks.0.attn2.to_k.lora.down.weight
lora key not loaded: unet.down_blocks.2.attentions.0.transformer_blocks.0.attn2.to_k.lora.up.weight

Reproduction

no

Logs

System Info

no

Who can help?

No response

[asomoza]

Hi, the loras trained with diffusers are in the diffusers format, to use it with comfyui you will need to convert it. You can get an example on how to do this here

[llm8047]

Hi, the loras trained with diffusers are in the diffusers format, to use it with comfyui you will need to convert it. You can get an example on how to do this here
This issue has been resolved, thank you

[asomoza]

closing as resolved then, glad you could resolve it.