ruru.XL
Hello! Introducing LoRA, the SDXL model from the ruru series.
LoRA is an anime-oriented model within the SDXL family, capable of producing even more delicate, adorable, and beautiful outputs.
It's designed with higher steps and resolutions in mind, so please be prepared for longer processing times.
But I'm sure you'll notice a distinctive difference compared to what we've had before in an instant!
Base Model:
Recommended Settings
Step: 55 or higher
Resolution: 1024 x 1024 or higher
Sampler: Euler a / DPM++ 2S a Karras (Of course, other options are welcome too! We look forward to hearing your feedback!)
TI: negativeXL
Be cautious with {{{{nsfw}}}} content
Reducing negativity and increasing positivity may introduce a bit more randomness into the outputs.
Enjoy this model!
Description
This time, we made some significant changes. One of the notable differences is the number of steps. Previously, we used my home's RTX 4090, but this time, I borrowed an H100 from a friend.
The base remains Animagine-XL.
Updated the dataset (from WD14-moat to ML-Danbooru).
Optimized the settings (approximately three times the number of steps for the same epoch).
Optimal strength: 0.6 to 0.8.
DPM++ 2Sa Karras is the best choice.
Negative-XL is not necessary (please refer to Animagine-XL for guidance).
FAQ
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.