This model was originally uploaded to Huggingface by Max Woolf - if Max would like to claim ownership of this model, please contact us.
A LoRA for SDXL 1.0 Base which improves output image quality after loading it and using wrong as a negative prompt during inference. You can demo image generation using this LoRA in this Colab Notebook.
Benefits of using this LoRA:
Higher detail in textures/fabrics, particularly at full 1024x1024 resolution.
Higher color saturation and vibrance.
Higher sharpness for blurry/background objects.
Better at anatomically-correct hands.
Less likely to have random artifacts.
Appears to allow the model to follow the input prompt with a more expected behavior, particularly with prompt weighting such as the Compel syntax.
Description
Diffusers
FAQ
Comments (25)
is this working in A1111?
Desperately need a safetensor version of this for A1111.
You can use this script to convert the .bin file to .safetensors: https://github.com/harrywang/finetune-sd/blob/main/convert-to-safetensors.py
(I have tested it on this file and it works fine)
1. Download the RAW text file - to the same directory you extracted the .bin file - and save as .py extension
2. Open CMD in that folder
3. Enter "python convert-to-safetensors.py --file pytorch_lora_weights.bin"
4. The script will convert the bin file to a safetensors file of the same name. You can rename this to "wrong_lora" after if you want.
Thanks, converted and uploaded here: https://mega.nz/file/eMEjgJyT#oeAnAIlTJxpakWVLT4AOgjJnrir2lB9_sDMGPNdZ_ww
Edit: This doesn't seem to be working, i do get the exact same result with the LoRA than without it :-/
That script is at least six months old, so i bet it does not support SDXL.
Ah crap, you're right. I didn't do proper A/B testing on it and now I notice a load of errors in the Comfy console. Need another way of converting for SDXL I guess
Has anyone tried the workflow in this tutorial? (7) How to Run and Convert Stable Diffusion Diffusers (.bin Weights) & Dreambooth Models to CKPT File - YouTube
Has anyone converted this to safetensors successfully?
@Polygon safetensors no longer exists there
@alenknight must have been a glitch; it's definitely there now.
no safetensor version.. it's useless for most people here.
looks promising but as others have said - safetensors or bust
You can find the safetensors here and its working: https://huggingface.co/minimaxir/sdxl-wrong-lora/blob/refs%2Fpr%2F2/pytorch_lora_weights.safetensors
Safetensors (A1111) version: https://huggingface.co/minimaxir/sdxl-wrong-lora/blob/refs%2Fpr%2F2/pytorch_lora_weights.safetensors
yeah this was removed. doesn't exist there anymore
It's like when Pikachu started working out vs 3 months later.
what happens if I use this in SD 1.5?