lora-inspector
lora-inspector copied to clipboard
LoRA (Low-Rank Adaptation) inspector for Stable Diffusion
Is there a way to see lora block weights individually? I seem to only get noticeable weights on B8. I'd like to be able to extract the individual block weights...
Since you referenced Zyin055's repo, "Inspect-Embedding-Training" Which output parameter shows me that the strength is too high (overtrained / inflexible)? I use his script for embeddings with great success. Forgive...
```bash python lora-inspector.py -v /mnt/900/lora/boo_v2.safetensors ``` ``` down_block_0_proj_in weight average magnitude: 1.4924503799105646 down_block_0_proj_in weight average strength: 0.017584813472947592 down_block_0_proj_out weight average magnitude: 1.5157774537695803 down_block_0_proj_out weight average strength: 0.017854483676551985 unet_down_block_0_transformer_block_0_attentions_to_k weight average...
LoHA
Support for fed para (LoHA) - Combine weights of `a` and `b`. I think this is how to do it...
This project desperately needs an UI. Please consider it.