Since people asked me for LoRA for PIXHELL :) here it is
Use it WELL!
Few tips and tricks:
The lora will give you great results for a base and overall pixelart feel, but for optimal pixelart results use this extension for automatic1111:
https://github.com/AUTOMATIC1111/stable-diffusion-webui-pixelization
This way you're results will look like the examples I've uploaded!
Enjoy!
Official YouTube Channel: [CLICK HERE]
Patreon: [CLICK HERE]
Discord: [CLICK HERE]
Description
The LoRA was extracted properly this time with 768 vectors from the network.
Also it's converted to fp16 so people should not experience errors now.
Give it a try, let me know how it behaves for you!
FAQ
Comments (9)
So after I Install the Github thing
https://github.com/AUTOMATIC1111/stable-diffusion-webui-pixelization
And place the 3 checkpoints into it, what next?
How do I use it? or does it just use it on everything automatically and I should just activate it for your model, and disable it if I dont want to use the Pixel Extension, you didn't really explain this and how to use it/ not use it.
That extension only works in the extras tab, it adds a checkbox at the bottom to enable it.
@Megasherru my bad man. I really should have explained in depth more how it works. @woobly thanks! you saved the day.
:) A friend of mine, one content creator is making a video using this model for a challenge. So once he posts the video i'll put it in the description of the model showing his steps.
here is instruction how to use LoRA with WebUI: https://github.com/d3vilh/stable-diffusion-howto#lora-models-configuration
I have the error message:
RuntimeError: The size of tensor a (768) must match the size of tensor b (1024) at non-singleton dimension 1
My test promt - tree, <lora:pixhell21Lora_v20:1>
You need SD21 based checkpoint
The base model is named as v2-1_768-ema-pruned. I input the same prompt but I got noting. I don't know what should I do after putting three .pth file. Please tell me how can I make one scenery like author‘s. PLEASE! THANKS A LOT!!!!.
The outputs I show them in the gallery, somebody plz help
The pictures look great. But I see no difference with or without this LoRa whichever base model I chose (SD 2.1 / IlluminuttyDiffusion)
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.